提取Pig中CSV文件的第一行

我有几个CSV文件，文件头总是第一行。在Pig中，将该行作为字符串从CSV文件中取出的最佳方法是什么？使用sed、awk等进行预处理不是一个选项

我试着用常规的PigStorage和piggybankcsvloader加载文件，但我不清楚如何才能得到第一行，如果有的话

如果需要的话，我愿意编写一个UDF。

免责声明：我对Java不太在行

您将需要一个UDF。我不确定你到底想要什么，但是这个UDF将获取一系列CSV文件并将它们转换为地图，其中键是文件顶部的值。这应该是一个足够的骨架，这样你就可以把它变成你想要的

我在远程和本地进行的两个测试表明，这将起作用

package myudfs;
import java.io.IOException;
import org.apache.pig.LoadFunc;

import java.util.Map;
import java.util.HashMap;
import java.util.ArrayList;
import org.apache.pig.data.Tuple;
import org.apache.pig.data.TupleFactory;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.InputFormat;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;

import org.apache.pig.PigException;
import org.apache.pig.backend.executionengine.ExecException;
import org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigSplit;

public class ExampleCSVLoader extends LoadFunc {
    protected RecordReader in = null;
    private String fieldDel = "" + '\t';
    private Map<String, String> outputMap = null;
    private TupleFactory mTupleFactory = TupleFactory.getInstance();

    // This stores the fields that are defined in the first line of the file
    private ArrayList<Object> topfields = null;

    public ExampleCSVLoader() {}

    public ExampleCSVLoader(String delimiter) {
        this();
        this.fieldDel = delimiter;
    }

    @Override
    public Tuple getNext() throws IOException {
        try {
            boolean notDone = in.nextKeyValue();
            if (!notDone) {
                outputMap = null;
                topfields = null;
                return null;
            }

            String value = in.getCurrentValue().toString();
            String[] values = value.split(fieldDel);
            Tuple t =  mTupleFactory.newTuple(1);

            ArrayList<Object> tf = new ArrayList<Object>();

            int pos = 0;
            for (int i = 0; i < values.length; i++) {
                if (topfields == null) {
                    tf.add(values[i]);
                } else {
                    readField(values[i], pos);
                    pos = pos + 1;
                }
            }
            if (topfields == null) {
                topfields = tf;
                t = mTupleFactory.newTuple();
            } else {
                t.set(0, outputMap);
            }

            outputMap = null;
            return t;
        } catch (InterruptedException e) {
            int errCode = 6018;
            String errMsg = "Error while reading input";
            throw new ExecException(errMsg, errCode,
                    PigException.REMOTE_ENVIRONMENT, e);
        }

    }

    // Applies foo to the appropriate value in topfields
    private void readField(String foo, int pos) {
        if (outputMap == null) {
            outputMap = new HashMap<String, String>();
        }
        outputMap.put((String) topfields.get(pos), foo);
    }

    @Override
    public InputFormat getInputFormat() {
        return new TextInputFormat();
    }

    @Override
    public void prepareToRead(RecordReader reader, PigSplit split) {
        in = reader;
    }

    @Override
    public void setLocation(String location, Job job)
            throws IOException {
        FileInputFormat.setInputPaths(job, location);
    }
}

生成此输出：

A: {M: map[]}
()
([D#PLEASE,E#WORK,F#FOO])
([D#OR,E#EVERYTHING,F#WILL])
([D#BE,E#FOR,F#NAUGHT])
()
([A#Hello,B#This,C#is])
([A#FOO,B#BAR,C#BING])
([A#BANG,B#BOSH])

s是文件的顶行。getNext要求我们返回一些内容，否则文件将停止处理。因此，它们返回一个空模式。

免责声明：我不擅长Java

您将需要一个UDF。我不确定你到底想要什么，但是这个UDF将获取一系列CSV文件并将它们转换为地图，其中键是文件顶部的值。这应该是一个足够的骨架，这样你就可以把它变成你想要的

我在远程和本地进行的两个测试表明，这将起作用

package myudfs;
import java.io.IOException;
import org.apache.pig.LoadFunc;

import java.util.Map;
import java.util.HashMap;
import java.util.ArrayList;
import org.apache.pig.data.Tuple;
import org.apache.pig.data.TupleFactory;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.InputFormat;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;

import org.apache.pig.PigException;
import org.apache.pig.backend.executionengine.ExecException;
import org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigSplit;

public class ExampleCSVLoader extends LoadFunc {
    protected RecordReader in = null;
    private String fieldDel = "" + '\t';
    private Map<String, String> outputMap = null;
    private TupleFactory mTupleFactory = TupleFactory.getInstance();

    // This stores the fields that are defined in the first line of the file
    private ArrayList<Object> topfields = null;

    public ExampleCSVLoader() {}

    public ExampleCSVLoader(String delimiter) {
        this();
        this.fieldDel = delimiter;
    }

    @Override
    public Tuple getNext() throws IOException {
        try {
            boolean notDone = in.nextKeyValue();
            if (!notDone) {
                outputMap = null;
                topfields = null;
                return null;
            }

            String value = in.getCurrentValue().toString();
            String[] values = value.split(fieldDel);
            Tuple t =  mTupleFactory.newTuple(1);

            ArrayList<Object> tf = new ArrayList<Object>();

            int pos = 0;
            for (int i = 0; i < values.length; i++) {
                if (topfields == null) {
                    tf.add(values[i]);
                } else {
                    readField(values[i], pos);
                    pos = pos + 1;
                }
            }
            if (topfields == null) {
                topfields = tf;
                t = mTupleFactory.newTuple();
            } else {
                t.set(0, outputMap);
            }

            outputMap = null;
            return t;
        } catch (InterruptedException e) {
            int errCode = 6018;
            String errMsg = "Error while reading input";
            throw new ExecException(errMsg, errCode,
                    PigException.REMOTE_ENVIRONMENT, e);
        }

    }

    // Applies foo to the appropriate value in topfields
    private void readField(String foo, int pos) {
        if (outputMap == null) {
            outputMap = new HashMap<String, String>();
        }
        outputMap.put((String) topfields.get(pos), foo);
    }

    @Override
    public InputFormat getInputFormat() {
        return new TextInputFormat();
    }

    @Override
    public void prepareToRead(RecordReader reader, PigSplit split) {
        in = reader;
    }

    @Override
    public void setLocation(String location, Job job)
            throws IOException {
        FileInputFormat.setInputPaths(job, location);
    }
}

生成此输出：

A: {M: map[]}
()
([D#PLEASE,E#WORK,F#FOO])
([D#OR,E#EVERYTHING,F#WILL])
([D#BE,E#FOR,F#NAUGHT])
()
([A#Hello,B#This,C#is])
([A#FOO,B#BAR,C#BING])
([A#BANG,B#BOSH])

---

s是文件的顶行。getNext要求我们返回一些内容，否则文件将停止处理。因此，它们返回一个空模式。

如果您的CSV符合Excel2007的CSV约定，您可以使用Piggybank已经提供的加载程序

---

它有一个选项可以跳过CSV标题skip_INPUT_header

如果您的CSV符合Excel 2007的CSV约定，您可以使用Piggybank已经提供的加载程序

---

它有一个跳过CSV标题的选项skip_INPUT_header

您所说的“将该行作为字符串从CSV文件中取出”是什么意思？您所说的“将该行作为字符串从CSV文件中取出”是什么意思？