org.apache.flink.api.java.io.TextOutputFormat Java Examples

public static <T extends DataInstance> void writeDataToARFFFolder(DataFlink<T> data, String path) throws Exception {

        DataSet<T> dataSet = data.getDataSet();

        DataFlinkWriter.writeHeader(dataSet.getExecutionEnvironment(), data, path, false);

        dataSet.writeAsFormattedText(path + "/data/", FileSystem.WriteMode.OVERWRITE, new TextOutputFormat.TextFormatter<T>() {
                    @Override
                    public String format(T value) {
                        return ARFFDataWriter.dataInstanceToARFFString(value);
                    }
                }
        );

        dataSet.getExecutionEnvironment().execute();

    }
 

public static <T extends DataInstance> void writeHeader(ExecutionEnvironment env, DataFlink<T> data, String path,
                                                         boolean includeRanges) {

    DataSource<String> name = env.fromElements("@relation " + data.getName());
    name.writeAsText(path + "/name.txt", FileSystem.WriteMode.OVERWRITE);

    DataSource<Attribute> attData = env.fromCollection(data.getAttributes().getFullListOfAttributes());

    attData.writeAsFormattedText(path + "/attributes.txt", FileSystem.WriteMode.OVERWRITE, new TextOutputFormat.TextFormatter<Attribute>() {
        @Override
        public String format(Attribute att) {
            return ARFFDataWriter.attributeToARFFStringWithIndex(att,includeRanges);
        }
    });
}
 

@Test
public void testChangingFileNames() {
	org.apache.hadoop.fs.Path hdfsPath = new org.apache.hadoop.fs.Path(hdfsURI + "/hdfsTest");
	Path path = new Path(hdfsPath.toString());

	String type = "one";
	TextOutputFormat<String> outputFormat = new TextOutputFormat<>(path);

	outputFormat.setWriteMode(FileSystem.WriteMode.NO_OVERWRITE);
	outputFormat.setOutputDirectoryMode(FileOutputFormat.OutputDirectoryMode.ALWAYS);

	try {
		outputFormat.open(0, 2);
		outputFormat.writeRecord(type);
		outputFormat.close();

		outputFormat.open(1, 2);
		outputFormat.writeRecord(type);
		outputFormat.close();

		assertTrue("No result file present", hdfs.exists(hdfsPath));
		FileStatus[] files = hdfs.listStatus(hdfsPath);
		Assert.assertEquals(2, files.length);
		for (FileStatus file : files) {
			assertTrue("1".equals(file.getPath().getName()) || "2".equals(file.getPath().getName()));
		}

	} catch (IOException e) {
		e.printStackTrace();
		Assert.fail(e.getMessage());
	}
}
 

@Test
public void testChangingFileNames() {
	org.apache.hadoop.fs.Path hdfsPath = new org.apache.hadoop.fs.Path(hdfsURI + "/hdfsTest");
	Path path = new Path(hdfsPath.toString());

	String type = "one";
	TextOutputFormat<String> outputFormat = new TextOutputFormat<>(path);

	outputFormat.setWriteMode(FileSystem.WriteMode.NO_OVERWRITE);
	outputFormat.setOutputDirectoryMode(FileOutputFormat.OutputDirectoryMode.ALWAYS);

	try {
		outputFormat.open(0, 2);
		outputFormat.writeRecord(type);
		outputFormat.close();

		outputFormat.open(1, 2);
		outputFormat.writeRecord(type);
		outputFormat.close();

		assertTrue("No result file present", hdfs.exists(hdfsPath));
		FileStatus[] files = hdfs.listStatus(hdfsPath);
		Assert.assertEquals(2, files.length);
		for (FileStatus file : files) {
			assertTrue("1".equals(file.getPath().getName()) || "2".equals(file.getPath().getName()));
		}

	} catch (IOException e) {
		e.printStackTrace();
		Assert.fail(e.getMessage());
	}
}
 

private OneInputStreamOperatorTestHarness<Row, Object> createSink(
		boolean override,
		boolean partition,
		boolean dynamicGrouped,
		LinkedHashMap<String, String> staticPartitions,
		AtomicReference<FileSystemOutputFormat<Row>> sinkRef) throws Exception {
	String[] columnNames = new String[]{"a", "b", "c"};
	String[] partitionColumns = partition ? new String[]{"c"} : new String[0];

	TableMetaStoreFactory msFactory = new FileSystemCommitterTest.TestMetaStoreFactory(
			new Path(outputFile.getPath()));
	FileSystemOutputFormat<Row> sink = new FileSystemOutputFormat.Builder<Row>()
			.setMetaStoreFactory(msFactory)
			.setTempPath(new Path(tmpFile.getPath()))
			.setOverwrite(override)
			.setPartitionColumns(partitionColumns)
			.setPartitionComputer(
					new RowPartitionComputer("default", columnNames, partitionColumns))
			.setFormatFactory(TextOutputFormat::new)
			.setDynamicGrouped(dynamicGrouped)
			.setStaticPartitions(staticPartitions)
			.build();

	sinkRef.set(sink);

	return new OneInputStreamOperatorTestHarness<>(
			new StreamSink<>(new OutputFormatSinkFunction<>(sink)),
			// test parallelism
			3, 3, 0);
}
 

public <T> TextOutputFormat.TextFormatter<T> compileOutput(TransformationDescriptor<T, String> formattingDescriptor) {
    Function<T, String> format = formattingDescriptor.getJavaImplementation();
    return new TextOutputFormat.TextFormatter<T>(){

        @Override
        public String format(T value) {
            return format.apply(value);
        }
    };
}
 

@Test
public void testChangingFileNames() {
	org.apache.hadoop.fs.Path hdfsPath = new org.apache.hadoop.fs.Path(hdfsURI + "/hdfsTest");
	Path path = new Path(hdfsPath.toString());

	String type = "one";
	TextOutputFormat<String> outputFormat = new TextOutputFormat<>(path);

	outputFormat.setWriteMode(FileSystem.WriteMode.NO_OVERWRITE);
	outputFormat.setOutputDirectoryMode(FileOutputFormat.OutputDirectoryMode.ALWAYS);

	try {
		outputFormat.open(0, 2);
		outputFormat.writeRecord(type);
		outputFormat.close();

		outputFormat.open(1, 2);
		outputFormat.writeRecord(type);
		outputFormat.close();

		assertTrue("No result file present", hdfs.exists(hdfsPath));
		FileStatus[] files = hdfs.listStatus(hdfsPath);
		Assert.assertEquals(2, files.length);
		for (FileStatus file : files) {
			assertTrue("1".equals(file.getPath().getName()) || "2".equals(file.getPath().getName()));
		}

	} catch (IOException e) {
		e.printStackTrace();
		Assert.fail(e.getMessage());
	}
}
 

/**
 * 
 * <pre>
 *             (SRC A)     
 *             /     \      
 *        (SINK A)    (SINK B)
 * </pre>
 */
@Test
public void testBranchingWithMultipleDataSinksSmall() {
	try {
		String outPath1 = "/tmp/out1";
		String outPath2 = "/tmp/out2";

		// construct the plan
		ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
		env.setParallelism(DEFAULT_PARALLELISM);
		DataSet<Long> source1 = env.generateSequence(0,1);

		source1.writeAsText(outPath1);
		source1.writeAsText(outPath2);

		Plan plan = env.createProgramPlan();
		OptimizedPlan oPlan = compileNoStats(plan);
		
		// ---------- check the optimizer plan ----------
		
		// number of sinks
		Assert.assertEquals("Wrong number of data sinks.", 2, oPlan.getDataSinks().size());
		
		// sinks contain all sink paths
		Set<String> allSinks = new HashSet<String>();
		allSinks.add(outPath1);
		allSinks.add(outPath2);
		
		for (SinkPlanNode n : oPlan.getDataSinks()) {
			String path = ((TextOutputFormat<String>)n.getSinkNode().getOperator()
					.getFormatWrapper().getUserCodeObject()).getOutputFilePath().toString();
			Assert.assertTrue("Invalid data sink.", allSinks.remove(path));
		}
		
		// ---------- compile plan to job graph to verify that no error is thrown ----------
		
		JobGraphGenerator jobGen = new JobGraphGenerator();
		jobGen.compileJobGraph(oPlan);
	} catch (Exception e) {
		e.printStackTrace();
		Assert.fail(e.getMessage());
	}
}
 

/**
 * 
 * <pre>
 *             (SRC A)     
 *             /     \      
 *        (SINK A)    (SINK B)
 * </pre>
 */
@Test
public void testBranchingWithMultipleDataSinksSmall() {
	try {
		String outPath1 = "/tmp/out1";
		String outPath2 = "/tmp/out2";

		// construct the plan
		ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
		env.setParallelism(DEFAULT_PARALLELISM);
		DataSet<Long> source1 = env.generateSequence(0,1);

		source1.writeAsText(outPath1);
		source1.writeAsText(outPath2);

		Plan plan = env.createProgramPlan();
		OptimizedPlan oPlan = compileNoStats(plan);
		
		// ---------- check the optimizer plan ----------
		
		// number of sinks
		Assert.assertEquals("Wrong number of data sinks.", 2, oPlan.getDataSinks().size());
		
		// sinks contain all sink paths
		Set<String> allSinks = new HashSet<String>();
		allSinks.add(outPath1);
		allSinks.add(outPath2);
		
		for (SinkPlanNode n : oPlan.getDataSinks()) {
			String path = ((TextOutputFormat<String>)n.getSinkNode().getOperator()
					.getFormatWrapper().getUserCodeObject()).getOutputFilePath().toString();
			Assert.assertTrue("Invalid data sink.", allSinks.remove(path));
		}
		
		// ---------- compile plan to job graph to verify that no error is thrown ----------
		
		JobGraphGenerator jobGen = new JobGraphGenerator();
		jobGen.compileJobGraph(oPlan);
	} catch (Exception e) {
		e.printStackTrace();
		Assert.fail(e.getMessage());
	}
}
 

public FormattingMapper(TextOutputFormat.TextFormatter<T> formatter) {
	this.formatter = formatter;
}
 

public FormattingMapper(TextOutputFormat.TextFormatter<T> formatter) {
	this.formatter = formatter;
}
 

public FormattingMapper(TextOutputFormat.TextFormatter<T> formatter) {
	this.formatter = formatter;
}
 

/**
 * 
 * <pre>
 *             (SRC A)     
 *             /     \      
 *        (SINK A)    (SINK B)
 * </pre>
 */
@Test
public void testBranchingWithMultipleDataSinksSmall() {
	try {
		String outPath1 = "/tmp/out1";
		String outPath2 = "/tmp/out2";

		// construct the plan
		ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
		env.setParallelism(DEFAULT_PARALLELISM);
		DataSet<Long> source1 = env.generateSequence(0,1);

		source1.writeAsText(outPath1);
		source1.writeAsText(outPath2);

		Plan plan = env.createProgramPlan();
		OptimizedPlan oPlan = compileNoStats(plan);
		
		// ---------- check the optimizer plan ----------
		
		// number of sinks
		Assert.assertEquals("Wrong number of data sinks.", 2, oPlan.getDataSinks().size());
		
		// sinks contain all sink paths
		Set<String> allSinks = new HashSet<String>();
		allSinks.add(outPath1);
		allSinks.add(outPath2);
		
		for (SinkPlanNode n : oPlan.getDataSinks()) {
			String path = ((TextOutputFormat<String>)n.getSinkNode().getOperator()
					.getFormatWrapper().getUserCodeObject()).getOutputFilePath().toString();
			Assert.assertTrue("Invalid data sink.", allSinks.remove(path));
		}
		
		// ---------- compile plan to job graph to verify that no error is thrown ----------
		
		JobGraphGenerator jobGen = new JobGraphGenerator();
		jobGen.compileJobGraph(oPlan);
	} catch (Exception e) {
		e.printStackTrace();
		Assert.fail(e.getMessage());
	}
}
 

/**
 * Writes a DataStream to the file specified by path in text format.
 *
 * <p>For every element of the DataStream the result of {@link Object#toString()} is written.
 *
 * @param path
 *            The path pointing to the location the text file is written to
 * @param writeMode
 *            Controls the behavior for existing files. Options are
 *            NO_OVERWRITE and OVERWRITE.
 *
 * @return The closed DataStream.
 */
@PublicEvolving
public DataStreamSink<T> writeAsText(String path, WriteMode writeMode) {
	TextOutputFormat<T> tof = new TextOutputFormat<>(new Path(path));
	tof.setWriteMode(writeMode);
	return writeUsingOutputFormat(tof);
}
 

/**
 * run area calculation process
 * @param path path to config file
 * @throws Exception
 */
public void run(String path) throws Exception {

    readConfig(path);

    FlinkEnvManager fem = new FlinkEnvManager(path, "areaJob",
            TableIdentifier.RAW_TWITTER_DATA.get(),
            "HighScore");

    DataSet<Tuple2<Key,Value>> rawTwitterDataRows = fem.getDataFromAccumulo();

    DataSet<Tuple2<String,String>> geoList = rawTwitterDataRows.flatMap(new GeoExtrationFlatMap());

    DataSet<Tuple2<String,String>> reducedGroup = geoList
                                                    .groupBy(0)
                                                    .reduceGroup(new CoordGroupReduce());

    DataSet<Tuple3<String,Double,Integer>> userRanking = reducedGroup.flatMap(new GeoCalcFlatMap())
            .sortPartition(1, Order.DESCENDING).setParallelism(1);

    DataSet<Tuple2<Text,Mutation>> topTen = userRanking
            .groupBy(2)
            .reduceGroup(new TopTenGroupReduce("ac"));

    topTen.output(fem.getHadoopOF());

    fem.getExecutionEnvironment().execute("AreaProcess");

    TextOutputFormat<String> tof = new TextOutputFormat<>(new Path("file:///tmp/areauserranking"));
    tof.setWriteMode(FileSystem.WriteMode.OVERWRITE);

    userRanking.writeAsText("file:///tmp/areauserranking", FileSystem.WriteMode.OVERWRITE).setParallelism(1);



    fem.getExecutionEnvironment().execute("AreaCalculationProcess");

}
 

/**
 * run area calculation process
 * @param path path to config file
 * @throws Exception
 */
public void run(String path) throws Exception {

    readConfig(path);

    FlinkEnvManager fem = new FlinkEnvManager(path, "pathJob",
            TableIdentifier.RAW_TWITTER_DATA.get(),
            "HighScore");


    DataSet<Tuple2<Key,Value>> rawTwitterDataRows = fem.getDataFromAccumulo();

    DataSet<Tuple2<String,String>> geoList = rawTwitterDataRows.flatMap(new PathGeoExtrationFlatMap());

    DataSet<Tuple2<String,String>> reducedGroup = geoList
                                                    .groupBy(0)
                                                    .reduceGroup(new PathCoordGroupReduce());

    DataSet<Tuple3<String,Double,Integer>> userRanking = reducedGroup.flatMap(new PathGeoCalcFlatMap())
            .sortPartition(1, Order.DESCENDING).setParallelism(1);

    DataSet<Tuple2<Text,Mutation>> topTen = userRanking
                                                    .groupBy(2)
                                                    .reduceGroup(new TopTenGroupReduce("td"));

    topTen.output(fem.getHadoopOF());

    fem.getExecutionEnvironment().execute("PathProcess");

    TextOutputFormat<String> tof = new TextOutputFormat<>(new Path("file:///tmp/pathuserranking"));
    tof.setWriteMode(FileSystem.WriteMode.OVERWRITE);

    userRanking.writeAsText("file:///tmp/pathuserranking", FileSystem.WriteMode.OVERWRITE).setParallelism(1);



    fem.getExecutionEnvironment().execute("PathCalculationProcess");

}
 

/**
 * Writes a DataStream to the file specified by path in text format.
 *
 * <p>For every element of the DataStream the result of {@link Object#toString()} is written.
 *
 * @param path
 *            The path pointing to the location the text file is written to
 * @param writeMode
 *            Controls the behavior for existing files. Options are
 *            NO_OVERWRITE and OVERWRITE.
 *
 * @return The closed DataStream.
 */
@PublicEvolving
public DataStreamSink<T> writeAsText(String path, WriteMode writeMode) {
	TextOutputFormat<T> tof = new TextOutputFormat<>(new Path(path));
	tof.setWriteMode(writeMode);
	return writeUsingOutputFormat(tof);
}
 

/**
 * Writes a DataStream to the file specified by path in text format.
 *
 * <p>For every element of the DataStream the result of {@link Object#toString()} is written.
 *
 * @param path
 *            The path pointing to the location the text file is written to
 * @param writeMode
 *            Controls the behavior for existing files. Options are
 *            NO_OVERWRITE and OVERWRITE.
 *
 * @return The closed DataStream.
 *
 * @deprecated Please use the {@link org.apache.flink.streaming.api.functions.sink.filesystem.StreamingFileSink} explicitly using the
 * {@link #addSink(SinkFunction)} method.
 */
@Deprecated
@PublicEvolving
public DataStreamSink<T> writeAsText(String path, WriteMode writeMode) {
	TextOutputFormat<T> tof = new TextOutputFormat<>(new Path(path));
	tof.setWriteMode(writeMode);
	return writeUsingOutputFormat(tof);
}
 

/**
 * Writes a DataStream to the file specified by path in text format.
 *
 * <p>For every element of the DataStream the result of {@link Object#toString()} is written.
 *
 * @param path
 *            The path pointing to the location the text file is written to.
 *
 * @return The closed DataStream.
 */
@PublicEvolving
public DataStreamSink<T> writeAsText(String path) {
	return writeUsingOutputFormat(new TextOutputFormat<T>(new Path(path)));
}
 

/**
 * Writes a DataSet as text file(s) to the specified location.
 *
 * <p>For each element of the DataSet the result of {@link Object#toString()} is written.
 *
 * @param filePath The path pointing to the location the text file is written to.
 * @param writeMode Control the behavior for existing files. Options are NO_OVERWRITE and OVERWRITE.
 * @return The DataSink that writes the DataSet.
 *
 * @see TextOutputFormat
 * @see DataSet#writeAsText(String) Output files and directories
 */
public DataSink<T> writeAsText(String filePath, WriteMode writeMode) {
	TextOutputFormat<T> tof = new TextOutputFormat<>(new Path(filePath));
	tof.setWriteMode(writeMode);
	return output(tof);
}
 

/**
 * Writes a DataSet as text file(s) to the specified location.
 *
 * <p>For each element of the DataSet the result of {@link Object#toString()} is written.<br/>
 * <br/>
 * <span class="strong">Output files and directories</span><br/>
 * What output how writeAsText() method produces is depending on other circumstance
 * <ul>
 *   <li>
 * A directory is created and multiple files are written underneath. (Default behavior)<br/>
 * This sink creates a directory called "path1", and files "1", "2" ... are writen underneath depending on <a href="https://flink.apache.org/faq.html#what-is-the-parallelism-how-do-i-set-it">parallelism</a>
 * <pre>{@code .
 * └── path1/
 *     ├── 1
 *     ├── 2
 *     └── ...}</pre>
 * Code Example
 * <pre>{@code dataset.writeAsText("file:///path1");}</pre>
 *   </li>
 *   <li>
 * A single file called "path1" is created when parallelism is set to 1
 * <pre>{@code .
 * └── path1 }</pre>
 * Code Example
 * <pre>{@code // Parallelism is set to only this particular operation
 *dataset.writeAsText("file:///path1").setParallelism(1);
 *
 * // This will creates the same effect but note all operators' parallelism are set to one
 *env.setParallelism(1);
 *...
 *dataset.writeAsText("file:///path1"); }</pre>
 *   </li>
 *   <li>
 * A directory is always created when <a href="https://ci.apache.org/projects/flink/flink-docs-master/setup/config.html#file-systems">fs.output.always-create-directory</a>
 * is set to true in flink-conf.yaml file, even when parallelism is set to 1.
 * <pre>{@code .
 * └── path1/
 *     └── 1 }</pre>
 * Code Example
 * <pre>{@code // fs.output.always-create-directory = true
 *dataset.writeAsText("file:///path1").setParallelism(1); }</pre>
 *   </li>
 * </ul>
 *
 * @param filePath The path pointing to the location the text file or files under the directory is written to.
 * @return The DataSink that writes the DataSet.
 *
 * @see TextOutputFormat
 */
public DataSink<T> writeAsText(String filePath) {
	return output(new TextOutputFormat<T>(new Path(filePath)));
}
 

/**
 * Writes a DataSet as text file(s) to the specified location.
 *
 * <p>For each element of the DataSet the result of {@link Object#toString()} is written.<br/>
 * <br/>
 * <span class="strong">Output files and directories</span><br/>
 * What output how writeAsText() method produces is depending on other circumstance
 * <ul>
 *   <li>
 * A directory is created and multiple files are written underneath. (Default behavior)<br/>
 * This sink creates a directory called "path1", and files "1", "2" ... are writen underneath depending on <a href="https://flink.apache.org/faq.html#what-is-the-parallelism-how-do-i-set-it">parallelism</a>
 * <pre>{@code .
 * └── path1/
 *     ├── 1
 *     ├── 2
 *     └── ...}</pre>
 * Code Example
 * <pre>{@code dataset.writeAsText("file:///path1");}</pre>
 *   </li>
 *   <li>
 * A single file called "path1" is created when parallelism is set to 1
 * <pre>{@code .
 * └── path1 }</pre>
 * Code Example
 * <pre>{@code // Parallelism is set to only this particular operation
 *dataset.writeAsText("file:///path1").setParallelism(1);
 *
 * // This will creates the same effect but note all operators' parallelism are set to one
 *env.setParallelism(1);
 *...
 *dataset.writeAsText("file:///path1"); }</pre>
 *   </li>
 *   <li>
 * A directory is always created when <a href="https://ci.apache.org/projects/flink/flink-docs-master/setup/config.html#file-systems">fs.output.always-create-directory</a>
 * is set to true in flink-conf.yaml file, even when parallelism is set to 1.
 * <pre>{@code .
 * └── path1/
 *     └── 1 }</pre>
 * Code Example
 * <pre>{@code // fs.output.always-create-directory = true
 *dataset.writeAsText("file:///path1").setParallelism(1); }</pre>
 *   </li>
 * </ul>
 *
 * @param filePath The path pointing to the location the text file or files under the directory is written to.
 * @return The DataSink that writes the DataSet.
 *
 * @see TextOutputFormat
 */
public DataSink<T> writeAsText(String filePath) {
	return output(new TextOutputFormat<T>(new Path(filePath)));
}
 

/**
 * Writes a DataSet as text file(s) to the specified location.
 *
 * <p>For each element of the DataSet the result of {@link Object#toString()} is written.
 *
 * @param filePath The path pointing to the location the text file is written to.
 * @param writeMode Control the behavior for existing files. Options are NO_OVERWRITE and OVERWRITE.
 * @return The DataSink that writes the DataSet.
 *
 * @see TextOutputFormat
 * @see DataSet#writeAsText(String) Output files and directories
 */
public DataSink<T> writeAsText(String filePath, WriteMode writeMode) {
	TextOutputFormat<T> tof = new TextOutputFormat<>(new Path(filePath));
	tof.setWriteMode(writeMode);
	return output(tof);
}
 

/**
 * Writes a DataStream to the file specified by path in text format.
 *
 * <p>For every element of the DataStream the result of {@link Object#toString()} is written.
 *
 * @param path
 *            The path pointing to the location the text file is written to.
 *
 * @return The closed DataStream.
 *
 * @deprecated Please use the {@link org.apache.flink.streaming.api.functions.sink.filesystem.StreamingFileSink} explicitly using the
 * {@link #addSink(SinkFunction)} method.
 */
@Deprecated
@PublicEvolving
public DataStreamSink<T> writeAsText(String path) {
	return writeUsingOutputFormat(new TextOutputFormat<T>(new Path(path)));
}
 

/**
 * Writes a DataStream to the file specified by path in text format.
 *
 * <p>For every element of the DataStream the result of {@link Object#toString()} is written.
 *
 * @param path
 *            The path pointing to the location the text file is written to.
 *
 * @return The closed DataStream.
 */
@PublicEvolving
public DataStreamSink<T> writeAsText(String path) {
	return writeUsingOutputFormat(new TextOutputFormat<T>(new Path(path)));
}
 

/**
 * Writes a DataSet as text file(s) to the specified location.
 *
 * <p>For each element of the DataSet the result of {@link Object#toString()} is written.
 *
 * @param filePath The path pointing to the location the text file is written to.
 * @param writeMode Control the behavior for existing files. Options are NO_OVERWRITE and OVERWRITE.
 * @return The DataSink that writes the DataSet.
 *
 * @see TextOutputFormat
 * @see DataSet#writeAsText(String) Output files and directories
 */
public DataSink<T> writeAsText(String filePath, WriteMode writeMode) {
	TextOutputFormat<T> tof = new TextOutputFormat<>(new Path(filePath));
	tof.setWriteMode(writeMode);
	return output(tof);
}
 

/**
 * Writes a DataSet as text file(s) to the specified location.
 *
 * <p>For each element of the DataSet the result of {@link Object#toString()} is written.<br/>
 * <br/>
 * <span class="strong">Output files and directories</span><br/>
 * What output how writeAsText() method produces is depending on other circumstance
 * <ul>
 *   <li>
 * A directory is created and multiple files are written underneath. (Default behavior)<br/>
 * This sink creates a directory called "path1", and files "1", "2" ... are writen underneath depending on <a href="https://flink.apache.org/faq.html#what-is-the-parallelism-how-do-i-set-it">parallelism</a>
 * <pre>{@code .
 * └── path1/
 *     ├── 1
 *     ├── 2
 *     └── ...}</pre>
 * Code Example
 * <pre>{@code dataset.writeAsText("file:///path1");}</pre>
 *   </li>
 *   <li>
 * A single file called "path1" is created when parallelism is set to 1
 * <pre>{@code .
 * └── path1 }</pre>
 * Code Example
 * <pre>{@code // Parallelism is set to only this particular operation
 *dataset.writeAsText("file:///path1").setParallelism(1);
 *
 * // This will creates the same effect but note all operators' parallelism are set to one
 *env.setParallelism(1);
 *...
 *dataset.writeAsText("file:///path1"); }</pre>
 *   </li>
 *   <li>
 * A directory is always created when <a href="https://ci.apache.org/projects/flink/flink-docs-master/setup/config.html#file-systems">fs.output.always-create-directory</a>
 * is set to true in flink-conf.yaml file, even when parallelism is set to 1.
 * <pre>{@code .
 * └── path1/
 *     └── 1 }</pre>
 * Code Example
 * <pre>{@code // fs.output.always-create-directory = true
 *dataset.writeAsText("file:///path1").setParallelism(1); }</pre>
 *   </li>
 * </ul>
 *
 * @param filePath The path pointing to the location the text file or files under the directory is written to.
 * @return The DataSink that writes the DataSet.
 *
 * @see TextOutputFormat
 */
public DataSink<T> writeAsText(String filePath) {
	return output(new TextOutputFormat<T>(new Path(filePath)));
}