Java 无法使用Flink Table API打印CSV文件

我正在尝试读取一个包含34个字段的文件，以便使用Netbeans在控制台上打印。但是，我只能打印模式。因为与csvreader一起使用的Flink的特定版本中缺少打印选项

请查看代码，并帮助我了解应该更正的位置。我本来会使用

CSVReader

，内置API，但结果证明它不支持超过22个字段，因此求助于使用表API。还尝试使用了

CsvTableSource

version1.5.1flink，但在语法方面没有成功。由于

.field（“%CPU”），Types.FLOAT（））

不断给出类型FLOAT not recognized符号的错误。 我的主要目标是能够读取CSV文件，然后发送到卡夫卡主题，但在此之前，我想检查文件是否已读取，还没有运气

import org.apache.flink.table.api.Table;
import  org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.TableEnvironment;
import org.apache.flink.table.sources.CsvTableSource;
import org.apache.flink.types.Row;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.DataStreamSink;
import org.apache.flink.table.api.Types;
import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.table.sinks.CsvTableSink;
import org.apache.flink.table.sinks.TableSink;
import org.apache.flink.table.api.java.Slide;


public class CsvReader {
  public static void main(String[] args) throws Exception {

StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
TableEnvironment tEnv = TableEnvironment.getTableEnvironment (env);
CsvTableSource csvTableSource = new CsvTableSource("/home/merlin/Experiments/input_container/container_data1.csv",
            new String[] { "%CPU", "MEM", "VSZ", "RSS", "timestamp",
    "OOM_Score", "io_read_count", "io_write_count", "io_read_bytes", "io_write_bytes",
    "io_read_chars", "io_write_chars", "num_fds", "num_ctx_switches_voluntary", "num_ctx_switches_involuntary",
    "mem_rss", "mem_vms", "mem_shared", "mem_text", "mem_lib", "mem_data", "mem_dirty", "mem_uss", "mem_pss",
    "mem_swap", "num_threads", "cpu_time_user", "cpu_time_system", "cpu_time_children_user",
    "cpu_time_children_system", "container_nr_sleeping", "container_nr_running",
    "container_nr_stopped", "container_nr_uninterruptible","container_nr_iowait" },
            new TypeInformation<?>[] {
                    Types.FLOAT(),
                    Types.FLOAT(),
                    Types.FLOAT(),
                    Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT(),
                                            Types.FLOAT()
                            });// lenient

    tEnv.registerTableSource("container", csvTableSource);
    Table result = tEnv
        .scan("container");
        System.out.println(result);
                result.printSchema();


      }
    }
/*tEnv.toAppendStream(result, Row.class).print();         
result.writeToSink(null);print();
            env.execute();*/

这是另一个版本的代码，它也不起作用

package wikiedits;

import static com.sun.xml.internal.fastinfoset.alphabet.BuiltInRestrictedAlphabets.table;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.types.Row;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.DataStreamSink;
import org.apache.flink.table.api.TableEnvironment;
public class Csv {
  public static void main(String[] args) throws Exception {

    final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    StreamTableEnvironment tEnv = TableEnvironment.getTableEnvironment (env);
//TableEnvironment tEnv = TableEnvironment.getTableEnvironment (env);

    CsvTableSource csvTableSource = CsvTableSource
    .builder()
    .path("home/merlin/Experiments/input_container/container_data1.csv")
    .field("%CPU", Types.FLOAT)
    .field("MEM", Types.FLOAT)
    .field("VSZ", Types.FLOAT)
    .field("RSS", Types.FLOAT)
    .field("timestamp", Types.FLOAT)
    .field("OOM_Score", Types.FLOAT)
    .field("io_read_count", Types.FLOAT)
    .field("io_write_count", Types.FLOAT)
    .field("io_read_bytes", Types.FLOAT)
    .field("io_write_bytes", Types.FLOAT)
    .field("io_read_chars", Types.FLOAT)
    .field("io_write_chars", Types.FLOAT)
    .field("num_fds", Types.FLOAT)
    .field("num_ctx_switches_voluntary", Types.FLOAT)
    .field("num_ctx_switches_involuntary", Types.FLOAT)
    .field("mem_rss", Types.FLOAT)
    .field("mem_vms", Types.FLOAT)
    .field("mem_shared", Types.FLOAT)
    .field("mem_text", Types.FLOAT)
    .field("mem_lib", Types.FLOAT)
    .field("mem_data", Types.FLOAT)
    .field("mem_dirty", Types.FLOAT)
    .field("mem_uss", Types.FLOAT)
    .field("mem_pss", Types.FLOAT)
    .field("mem_swap", Types.FLOAT)
    .field("num_threads", Types.FLOAT)
    .field("cpu_time_user", Types.FLOAT)
    .field("cpu_time_system", Types.FLOAT)
    .field("cpu_time_children_user", Types.FLOAT)
    .field("cpu_time_children_system", Types.FLOAT)
    .field("container_nr_sleeping", Types.FLOAT)
    .field("container_nr_running", Types.FLOAT)
    .field("container_nr_stopped", Types.FLOAT)
    .field("container_nr_uninterruptible", Types.FLOAT)
    .field("container_nr_iowait", Types.FLOAT)
    .fieldDelimiter(",")
    .lineDelimiter("\n")
    .ignoreFirstLine()
    .ignoreParseErrors()
    .commentPrefix("%")
    .build();
// name your table source
tEnv.registerTableSource("container", csvTableSource);
Table table = tEnv.scan("container");
DataStream<Row> stream = tEnv.toAppendStream(table, Row.class);
// define the sink as common print on console here
      stream.print();
             // env.execute();

  }
}

---

您必须将

表

转换为

数据流

才能打印它。最简单的方法是将其转换为

数据流

，如下所示：

DataStream<Row> stream = tEnv.toAppendStream(result, Row.class);
// print the stream & execute the program
stream.print();
env.execute();

DataStream-stream=tEnv.toAppendStream（结果，行.类）；
//打印流并执行程序
stream.print（）；
execute（）；

有关更多详细信息，请参阅。

此代码：

package example.flink;

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.java.StreamTableEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.TableEnvironment;
import org.apache.flink.table.sources.CsvTableSource;
import org.apache.flink.types.Row;

public class TestFlink {
    public static void main(String[] args) {

        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        StreamTableEnvironment tEnv = TableEnvironment.getTableEnvironment (env);

        CsvTableSource csvTableSource = CsvTableSource
                .builder()
                .path("container_data.csv")
                .field("%CPU", Types.FLOAT)
                .field("MEM", Types.FLOAT)
                .field("VSZ", Types.FLOAT)
                .field("RSS", Types.FLOAT)
                .field("timestamp", Types.FLOAT)
                .field("OOM_Score", Types.FLOAT)
                .field("io_read_count", Types.FLOAT)
                .field("io_write_count", Types.FLOAT)
                .field("io_read_bytes", Types.FLOAT)
                .field("io_write_bytes", Types.FLOAT)
                .field("io_read_chars", Types.FLOAT)
                .field("io_write_chars", Types.FLOAT)
                .field("num_fds", Types.FLOAT)
                .field("num_ctx_switches_voluntary", Types.FLOAT)
                .field("num_ctx_switches_involuntary", Types.FLOAT)
                .field("mem_rss", Types.FLOAT)
                .field("mem_vms", Types.FLOAT)
                .field("mem_shared", Types.FLOAT)
                .field("mem_text", Types.FLOAT)
                .field("mem_lib", Types.FLOAT)
                .field("mem_data", Types.FLOAT)
                .field("mem_dirty", Types.FLOAT)
                .field("mem_uss", Types.FLOAT)
                .field("mem_pss", Types.FLOAT)
                .field("mem_swap", Types.FLOAT)
                .field("num_threads", Types.FLOAT)
                .field("cpu_time_user", Types.FLOAT)
                .field("cpu_time_system", Types.FLOAT)
                .field("cpu_time_children_user", Types.FLOAT)
                .field("cpu_time_children_system", Types.FLOAT)
                .field("container_nr_sleeping", Types.FLOAT)
                .field("container_nr_running", Types.FLOAT)
                .field("container_nr_stopped", Types.FLOAT)
                .field("container_nr_uninterruptible", Types.FLOAT)
                .field("container_nr_iowait", Types.FLOAT)
                .fieldDelimiter(",")
                .lineDelimiter("\n")
                .ignoreFirstLine()
                .ignoreParseErrors()
                .commentPrefix("%")
                .build();
        // name your table source
        tEnv.registerTableSource("container", csvTableSource);
        Table table = tEnv.scan("container");
        DataStream<Row> stream = tEnv.toAppendStream(table, Row.class);
        // define the sink as common print on console here
        stream.print();
        try {
            env.execute();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

他至少在跑步。我不确定它是否提供了您需要的输出，但它几乎完全是您在最新编辑中输入的内容，但它在IDE中工作。这有用吗

---

如果您的分隔符仍然是一个空格，请记住更改

.fieldDelimiter（“，”）

您的csv文件中有什么？csv文件包含34个带浮点数的字段。全部34个都是数字basicaly@Samso "1.44, 3.22, 5.66"... 等以正确的csv格式？excel/google sheets/Simulator很高兴打开此文件吗？@Sam 0.6 0 18244 3280 1512312018 0 122 11 0 98134 1783 4 56 1 3358720 18681856 2887680 9994224 0 524288 0 495616 805888 0 1 0.02 0.01 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0“变量表”当我复制你的表时，当我试图写“result，Row.class”时，它也会抛出一个错误。它还要求我根据netbeans添加导入，但是这也失败了启动程序。我启动了。还是没什么。它说在线程“main”java.lang.RuntimeException:不可编译的源代码-错误的符号类型：org.apache.flink.table.api.TableEnvironment.toAppendStream将行更改为

StreamTableEnvironment tEnv=TableEnvironment.getTableEnvironment（env）。嘿，我尝试了你提到的，代码编译得很好，但是，当运行时，错误是：线程“main”java.lang.NoClassDefFoundError中的异常：org/apache/flink/api/java/operators/Keys位于CsvReader.main（CsvReader.java:86），即DataStream stream=tEnv.toAppendStream（result，Row.class）；是的，它在终端（通过将jar提交给flink方法）中确实对我有效，但在netbeanside中不起作用。是的，我有上面列出的flink和其他人的确切版本。我没有netbeans，但它与gradle在intellij中工作
Cannot find symbol:method Map

DataStream<Row> stream = tEnv.toAppendStream(result, Row.class);
// print the stream & execute the program
stream.print();
env.execute();

package example.flink;

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.java.StreamTableEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.TableEnvironment;
import org.apache.flink.table.sources.CsvTableSource;
import org.apache.flink.types.Row;

public class TestFlink {
    public static void main(String[] args) {

        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        StreamTableEnvironment tEnv = TableEnvironment.getTableEnvironment (env);

        CsvTableSource csvTableSource = CsvTableSource
                .builder()
                .path("container_data.csv")
                .field("%CPU", Types.FLOAT)
                .field("MEM", Types.FLOAT)
                .field("VSZ", Types.FLOAT)
                .field("RSS", Types.FLOAT)
                .field("timestamp", Types.FLOAT)
                .field("OOM_Score", Types.FLOAT)
                .field("io_read_count", Types.FLOAT)
                .field("io_write_count", Types.FLOAT)
                .field("io_read_bytes", Types.FLOAT)
                .field("io_write_bytes", Types.FLOAT)
                .field("io_read_chars", Types.FLOAT)
                .field("io_write_chars", Types.FLOAT)
                .field("num_fds", Types.FLOAT)
                .field("num_ctx_switches_voluntary", Types.FLOAT)
                .field("num_ctx_switches_involuntary", Types.FLOAT)
                .field("mem_rss", Types.FLOAT)
                .field("mem_vms", Types.FLOAT)
                .field("mem_shared", Types.FLOAT)
                .field("mem_text", Types.FLOAT)
                .field("mem_lib", Types.FLOAT)
                .field("mem_data", Types.FLOAT)
                .field("mem_dirty", Types.FLOAT)
                .field("mem_uss", Types.FLOAT)
                .field("mem_pss", Types.FLOAT)
                .field("mem_swap", Types.FLOAT)
                .field("num_threads", Types.FLOAT)
                .field("cpu_time_user", Types.FLOAT)
                .field("cpu_time_system", Types.FLOAT)
                .field("cpu_time_children_user", Types.FLOAT)
                .field("cpu_time_children_system", Types.FLOAT)
                .field("container_nr_sleeping", Types.FLOAT)
                .field("container_nr_running", Types.FLOAT)
                .field("container_nr_stopped", Types.FLOAT)
                .field("container_nr_uninterruptible", Types.FLOAT)
                .field("container_nr_iowait", Types.FLOAT)
                .fieldDelimiter(",")
                .lineDelimiter("\n")
                .ignoreFirstLine()
                .ignoreParseErrors()
                .commentPrefix("%")
                .build();
        // name your table source
        tEnv.registerTableSource("container", csvTableSource);
        Table table = tEnv.scan("container");
        DataStream<Row> stream = tEnv.toAppendStream(table, Row.class);
        // define the sink as common print on console here
        stream.print();
        try {
            env.execute();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

compile group: 'org.slf4j', name: 'slf4j-simple', version: '1.7.25'
compile group: 'org.apache.flink', name: 'flink-clients_2.11', version: '1.5.1'
compile group: 'org.apache.flink', name: 'flink-table_2.11', version: '1.5.1'
compile group: 'org.apache.flink', name: 'flink-core', version: '1.5.1'
compile group: 'org.apache.flink', name: 'flink-java', version: '1.5.1'
compile group: 'org.apache.flink', name: 'flink-streaming-scala_2.11', version: '1.5.1'
compile group: 'org.apache.flink', name: 'flink-streaming-java_2.11', version: '1.5.1'
compile group: 'org.apache.flink', name: 'flink-runtime_2.11', version: '1.5.1'