org.apache.flink.table.descriptors.OldCsv Java Examples

The following examples show how to use org.apache.flink.table.descriptors.OldCsv. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: TableExampleWordCount.java    From flink-learning with Apache License 2.0 5 votes vote down vote up 
public static void main(String[] args) throws Exception {
    StreamExecutionEnvironment blinkStreamEnv = StreamExecutionEnvironment.getExecutionEnvironment();
    blinkStreamEnv.setParallelism(1);
    EnvironmentSettings blinkStreamSettings = EnvironmentSettings.newInstance()
            .useBlinkPlanner()
            .inStreamingMode()
            .build();
    StreamTableEnvironment blinkStreamTableEnv = StreamTableEnvironment.create(blinkStreamEnv, blinkStreamSettings);

    String path = TableExampleWordCount.class.getClassLoader().getResource("words.txt").getPath();
    blinkStreamTableEnv
            .connect(new FileSystem().path(path))
            .withFormat(new OldCsv().field("word", Types.STRING).lineDelimiter("\n"))
            .withSchema(new Schema().field("word", Types.STRING))
            .inAppendMode()
            .registerTableSource("FlieSourceTable");

    Table wordWithCount = blinkStreamTableEnv.scan("FlieSourceTable")
            .groupBy("word")
            .select("word,count(word) as _count");
    blinkStreamTableEnv.toRetractStream(wordWithCount, Row.class).print();

    //打印结果中的 true 和 false，可能会有点疑问，为啥会多出一个字段。
    //Sink 做的事情是先删除再插入，false 表示删除上一条数据，true 表示插入该条数据

    blinkStreamTableEnv.execute("Blink Stream SQL Job");
}
Example #2
Source File: TableExampleWordCount.java    From flink-learning with Apache License 2.0 5 votes vote down vote up 
public static void main(String[] args) throws Exception {
    StreamExecutionEnvironment blinkStreamEnv = StreamExecutionEnvironment.getExecutionEnvironment();
    blinkStreamEnv.setParallelism(1);
    EnvironmentSettings blinkStreamSettings = EnvironmentSettings.newInstance()
            .useBlinkPlanner()
            .inStreamingMode()
            .build();
    StreamTableEnvironment blinkStreamTableEnv = StreamTableEnvironment.create(blinkStreamEnv, blinkStreamSettings);

    String path = TableExampleWordCount.class.getClassLoader().getResource("words.txt").getPath();
    blinkStreamTableEnv
            .connect(new FileSystem().path(path))
            .withFormat(new OldCsv().field("word", Types.STRING).lineDelimiter("\n"))
            .withSchema(new Schema().field("word", Types.STRING))
            .inAppendMode()
            .registerTableSource("FlieSourceTable");

    Table wordWithCount = blinkStreamTableEnv.scan("FlieSourceTable")
            .groupBy("word")
            .select("word,count(word) as _count");
    blinkStreamTableEnv.toRetractStream(wordWithCount, Row.class).print();

    //打印结果中的 true 和 false，可能会有点疑问，为啥会多出一个字段。
    //Sink 做的事情是先删除再插入，false 表示删除上一条数据，true 表示插入该条数据

    blinkStreamTableEnv.execute("Blink Stream SQL Job");
}
Example #3
Source File: HiveCatalogITCase.java    From flink with Apache License 2.0 4 votes vote down vote up 
@Test
public void testGenericTable() throws Exception {
	ExecutionEnvironment execEnv = ExecutionEnvironment.createLocalEnvironment(1);
	BatchTableEnvironment tableEnv = BatchTableEnvironment.create(execEnv);

	tableEnv.registerCatalog("myhive", hiveCatalog);

	TableSchema schema = TableSchema.builder()
		.field("name", DataTypes.STRING())
		.field("age", DataTypes.INT())
		.build();

	FormatDescriptor format = new OldCsv()
		.field("name", Types.STRING())
		.field("age", Types.INT());

	CatalogTable source =
		new CatalogTableBuilder(
			new FileSystem().path(this.getClass().getResource("/csv/test.csv").getPath()),
			schema)
		.withFormat(format)
		.inAppendMode()
		.withComment("Comment.")
		.build();

	Path p = Paths.get(tempFolder.newFolder().getAbsolutePath(), "test.csv");

	CatalogTable sink =
		new CatalogTableBuilder(
			new FileSystem().path(p.toAbsolutePath().toString()),
			schema)
			.withFormat(format)
			.inAppendMode()
			.withComment("Comment.")
			.build();

	hiveCatalog.createTable(
		new ObjectPath(HiveCatalog.DEFAULT_DB, sourceTableName),
		source,
		false
	);

	hiveCatalog.createTable(
		new ObjectPath(HiveCatalog.DEFAULT_DB, sinkTableName),
		sink,
		false
	);

	Table t = tableEnv.sqlQuery(
		String.format("select * from myhive.`default`.%s", sourceTableName));

	List<Row> result = tableEnv.toDataSet(t, Row.class).collect();

	// assert query result
	assertEquals(
		Arrays.asList(
			Row.of("1", 1),
			Row.of("2", 2),
			Row.of("3", 3)),
		result
	);

	tableEnv.sqlUpdate(
		String.format("insert into myhive.`default`.%s select * from myhive.`default`.%s",
			sinkTableName,
			sourceTableName));
	tableEnv.execute("myjob");

	// assert written result
	File resultFile = new File(p.toAbsolutePath().toString());
	BufferedReader reader = new BufferedReader(new FileReader(resultFile));
	String readLine;
	for (int i = 0; i < 3; i++) {
		readLine = reader.readLine();
		assertEquals(String.format("%d,%d", i + 1, i + 1), readLine);
	}

	// No more line
	assertNull(reader.readLine());
}
Example #4
Source File: HiveCatalogITCase.java    From flink with Apache License 2.0 4 votes vote down vote up 
@Test
public void testCsvTableViaAPI() throws Exception {
	EnvironmentSettings settings = EnvironmentSettings.newInstance().useBlinkPlanner().inBatchMode().build();
	TableEnvironment tableEnv = TableEnvironment.create(settings);
	tableEnv.getConfig().addConfiguration(new Configuration().set(CoreOptions.DEFAULT_PARALLELISM, 1));

	tableEnv.registerCatalog("myhive", hiveCatalog);
	tableEnv.useCatalog("myhive");

	TableSchema schema = TableSchema.builder()
		.field("name", DataTypes.STRING())
		.field("age", DataTypes.INT())
		.build();

	FormatDescriptor format = new OldCsv()
		.field("name", Types.STRING())
		.field("age", Types.INT());

	CatalogTable source =
		new CatalogTableBuilder(
			new FileSystem().path(this.getClass().getResource("/csv/test.csv").getPath()),
			schema)
		.withFormat(format)
		.inAppendMode()
		.withComment("Comment.")
		.build();

	Path p = Paths.get(tempFolder.newFolder().getAbsolutePath(), "test.csv");

	CatalogTable sink =
		new CatalogTableBuilder(
			new FileSystem().path(p.toAbsolutePath().toString()),
			schema)
			.withFormat(format)
			.inAppendMode()
			.withComment("Comment.")
			.build();

	hiveCatalog.createTable(
		new ObjectPath(HiveCatalog.DEFAULT_DB, sourceTableName),
		source,
		false
	);

	hiveCatalog.createTable(
		new ObjectPath(HiveCatalog.DEFAULT_DB, sinkTableName),
		sink,
		false
	);

	Table t = tableEnv.sqlQuery(
		String.format("select * from myhive.`default`.%s", sourceTableName));

	List<Row> result = Lists.newArrayList(t.execute().collect());
	result.sort(Comparator.comparing(String::valueOf));

	// assert query result
	assertEquals(
		Arrays.asList(
			Row.of("1", 1),
			Row.of("2", 2),
			Row.of("3", 3)),
		result
	);

	TableEnvUtil.execInsertSqlAndWaitResult(tableEnv,
		String.format("insert into myhive.`default`.%s select * from myhive.`default`.%s",
			sinkTableName,
			sourceTableName));

	// assert written result
	File resultFile = new File(p.toAbsolutePath().toString());
	BufferedReader reader = new BufferedReader(new FileReader(resultFile));
	String readLine;
	for (int i = 0; i < 3; i++) {
		readLine = reader.readLine();
		assertEquals(String.format("%d,%d", i + 1, i + 1), readLine);
	}

	// No more line
	assertNull(reader.readLine());

	tableEnv.executeSql(String.format("DROP TABLE %s", sourceTableName));
	tableEnv.executeSql(String.format("DROP TABLE %s", sinkTableName));
}
Example #5
Source File: HiveCatalogUseBlinkITCase.java    From flink with Apache License 2.0 4 votes vote down vote up 
@Test
public void testBlinkUdf() throws Exception {
	TableSchema schema = TableSchema.builder()
			.field("name", DataTypes.STRING())
			.field("age", DataTypes.INT())
			.build();

	FormatDescriptor format = new OldCsv()
			.field("name", Types.STRING())
			.field("age", Types.INT());

	CatalogTable source =
			new CatalogTableBuilder(
					new FileSystem().path(this.getClass().getResource("/csv/test.csv").getPath()),
					schema)
					.withFormat(format)
					.inAppendMode()
					.withComment("Comment.")
					.build();

	hiveCatalog.createTable(
			new ObjectPath(HiveCatalog.DEFAULT_DB, sourceTableName),
			source,
			false
	);

	hiveCatalog.createFunction(
			new ObjectPath(HiveCatalog.DEFAULT_DB, "myudf"),
			new CatalogFunctionImpl(TestHiveSimpleUDF.class.getCanonicalName()),
			false);
	hiveCatalog.createFunction(
			new ObjectPath(HiveCatalog.DEFAULT_DB, "mygenericudf"),
			new CatalogFunctionImpl(TestHiveGenericUDF.class.getCanonicalName()),
			false);
	hiveCatalog.createFunction(
			new ObjectPath(HiveCatalog.DEFAULT_DB, "myudtf"),
			new CatalogFunctionImpl(TestHiveUDTF.class.getCanonicalName()),
			false);
	hiveCatalog.createFunction(
			new ObjectPath(HiveCatalog.DEFAULT_DB, "myudaf"),
			new CatalogFunctionImpl(GenericUDAFSum.class.getCanonicalName()),
			false);

	testUdf(true);
	testUdf(false);
}