pig自带的pigstorage不能指定行分隔符,所以自己重写了一个简单的UDF类,可以指定列和行的分隔符,之前研究过的简单的,
http://blog.csdn.net/ruishenh/article/details/12048067
但是弊端大,所以这次重写一下。
操作步骤打好包上传到服务器,
grunt> register /home/pig/pig-0.11.0/udflib/myStorage.jar
grunt> cat student;
1,xiaohouzi,25/2,xiaohouzi2,24/3,xiaohouzi3,23
grunt> a = load 'student' using com.hcr.hadoop.pig.MyStorage(',','/');
grunt> dump a;
(1,xiaohouzi,25)
(2,xiaohouzi2,24)
(3,xiaohouzi3,23)
grunt> store a into 'myStorageOut' using com.hcr.hadoop.pig.MyStorage(',','/');
执行提示成功后查看
grunt> cat myStorageOut
1,xiaohouzi,25/2,xiaohouzi2,24/3,xiaohouzi3,23/
源码类
package com.hcr.hadoop.pig;
import java.io.DataOutputStream;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.util.ArrayList;
import java.util.List;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.compress.BZip2Codec;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapreduce.InputFormat;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.OutputFormat;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.LineRecordReader;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.ReflectionUtils;
import org.apache.pig.Expression;
import org.apache.pig.LoadFunc;
import org.apache.pig.LoadMetadata;
import org.apache.pig.PigException;
import org.apache.pig.ResourceSchema;
import org.apache.pig.ResourceSchema.ResourceFieldSchema;
import org.apache.pig.ResourceStatistics;
import org.apache.pig.StoreFunc;
import org.apache.pig.StoreFuncInterface;
import org.apache.pig.backend.executionengine.ExecException;
import org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigSplit;
import org.apache.pig.data.DataType;
import org.apache.pig.data.Tuple;
import org.apache.pig.data.TupleFactory;
import org.apache.pig.impl.logicalLayer.schema.Schema.FieldSchema;
import org.apache.pig.impl.util.StorageUtil;
public class MyStorage extends LoadFunc implements StoreFuncInterface,LoadMetadata {
private static final Log LOG = LogFactory.getLog(MyStorage.class);
private static final String utf8 = "UTF-8";
private static String fieldDel = "\t";
private static String recordDel = "\n";
protected RecordReader recordReader = null;
protected RecordWriter writer = null;
public MyStorage() {
}
public MyStorage(String fieldDel) {
this(fieldDel, "\n");
}
public MyStorage(String fieldDel, String recordDel) {
this.fieldDel = fieldDel;
this.recordDel = recordDel;
}
@Override
public void setLocation(String s, Job job) throws IOException {
FileInputFormat.setInputPaths(job, s);
}
@Override
public InputFormat getInputFormat() throws IOException {
return new MyStorageInputFormat(recordDel);
}
@Override
public void prepareToRead(RecordReader recordReader, PigSplit pigSplit)
throws IOException {
this.recordReader = recordReader;
}
@Override
public Tuple getNext() throws IOException {
try {
boolean flag = recordReader.nextKeyValue();
if (!flag) {
return null;
}
Text value = (Text) recordReader.getCurrentValue();
String[] strArray = value.toString().split(fieldDel);
List lst = new ArrayList<String>();
int i = 0;
for (String singleItem : strArray) {
lst.add(i++, singleItem);
}
return TupleFactory.getInstance().newTuple(lst);
} catch (InterruptedException e) {
throw new ExecException("Read data error",
PigException.REMOTE_ENVIRONMENT, e);
}
}
/**
* */
@Override
public String relToAbsPathForStoreLocation(String location, Path curDir)
throws IOException {
return LoadFunc.getAbsolutePath(location, curDir);
}
@Override
public OutputFormat getOutputFormat() throws IOException {
return new MyStorageOutputFormat(StorageUtil.parseFieldDel(fieldDel),
this.recordDel);
}
@Override
public void setStoreLocation(String location, Job job) throws IOException {
job.getConfiguration().set("mapred.textoutputformat.separator", "");
FileOutputFormat.setOutputPath(job, new Path(location));
if ("true".equals(job.getConfiguration().get(
"output.compression.enabled"))) {
FileOutputFormat.setCompressOutput(job, true);
String codec = job.getConfiguration().get(
"output.compression.codec");
try {
FileOutputFormat.setOutputCompressorClass(job,
(Class<? extends CompressionCodec>) Class
.forName(codec));
} catch (ClassNotFoundException e) {
throw new RuntimeException("Class not found: " + codec);
}
} else {
// This makes it so that storing to a directory ending with ".gz" or
// ".bz2" works.
setCompression(new Path(location), job);
}
}
private void setCompression(Path path, Job job) {
String location = path.getName();
if (location.endsWith(".bz2") || location.endsWith(".bz")) {
FileOutputFormat.setCompressOutput(job, true);
FileOutputFormat.setOutputCompressorClass(job, BZip2Codec.class);
} else if (location.endsWith(".gz")) {
FileOutputFormat.setCompressOutput(job, true);
FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);
} else {
FileOutputFormat.setCompressOutput(job, false);
}
}
@Override
public void checkSchema(ResourceSchema s) throws IOException {
// TODO Auto-generated method stub
}
@Override
public void prepareToWrite(RecordWriter writer) throws IOException {
this.writer = writer;
}
@Override
public void putNext(Tuple t) throws IOException {
try {
writer.write(null, t);
} catch (InterruptedException e) {
throw new IOException(e);
}
}
@Override
public void setStoreFuncUDFContextSignature(String signature) {
// TODO Auto-generated method stub
}
@Override
public void cleanupOnFailure(String location, Job job) throws IOException {
StoreFunc.cleanupOnFailureImpl(location, job);
}
@Override
public void cleanupOnSuccess(String location, Job job) throws IOException {
// TODO Auto-generated method stub
}
@Override
public ResourceSchema getSchema(String location, Job job)
throws IOException {
ResourceSchema rs=new ResourceSchema();
FieldSchema c1 = new FieldSchema("c1", DataType.INTEGER);
FieldSchema c2 = new FieldSchema("c2", DataType.INTEGER);
FieldSchema c3 = new FieldSchema("c3", DataType.DOUBLE);
ResourceFieldSchema fs1 =new ResourceFieldSchema(c1);
ResourceFieldSchema fs2 =new ResourceFieldSchema(c2);
ResourceFieldSchema fs3 =new ResourceFieldSchema(c3);
rs.setFields(new ResourceFieldSchema[]{fs1,fs2,fs3});
return rs;
}
@Override
public ResourceStatistics getStatistics(String location, Job job)
throws IOException {
// TODO Auto-generated method stub
return null;
}
@Override
public String[] getPartitionKeys(String location, Job job)
throws IOException {
// TODO Auto-generated method stub
return null;
}
@Override
public void setPartitionFilter(Expression partitionFilter)
throws IOException {
// TODO Auto-generated method stub
}
}
class MyStorageInputFormat extends TextInputFormat {
private final String recordDel;
public MyStorageInputFormat(String recordDel) {
this.recordDel = recordDel;
}
@Override
public RecordReader<LongWritable, Text> createRecordReader(
InputSplit split, TaskAttemptContext context) {
String delimiter = context.getConfiguration().get(
"textinputformat.record.delimiter");
if (recordDel != null) {
delimiter = recordDel;
}
byte[] recordDelimiterBytes = null;
if (null != delimiter){
try {
recordDelimiterBytes = decode(delimiter).getBytes("UTF-8");
} catch (UnsupportedEncodingException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
return new LineRecordReader(recordDelimiterBytes);
}
/**
* 工作流传过来的列分隔符,有可能是特殊字符,用八进制或者十六进制表示
* @throws IOException
*/
public static String decode(String str) throws IOException {
String re = str;
if (str != null && str.startsWith("\\")) {
str = str.substring(1, str.length());
String[] chars = str.split("\\\\");
byte[] bytes = new byte[chars.length];
for (int i = 0; i < chars.length; i++) {
if (chars[i].equals("t")) {
bytes[i] = 9;
} else if (chars[i].equals("r")) {
bytes[i] = 13;
} else if (chars[i].equals("n")) {
bytes[i] = 10;
} else if (chars[i].equals("b")) {
bytes[i] = 8;
} else {
bytes[i] = Byte.decode(chars[i]);
}
}
try {
re = new String(bytes, "UTF-8");
} catch (UnsupportedEncodingException e) {
throw new IOException(str, e);
}
}
return re;
}
}
class MyStorageOutputFormat extends TextOutputFormat<WritableComparable, Tuple> {
private final byte fieldDel;
private final String recordDel;
public MyStorageOutputFormat(byte delimiter) {
this(delimiter, "\n");
}
public MyStorageOutputFormat(byte delimiter, String recordDel) {
this.fieldDel = delimiter;
this.recordDel = recordDel;
}
protected static class MyRecordWriter extends
TextOutputFormat.LineRecordWriter<WritableComparable, Tuple> {
private static byte[] newline;
private final byte fieldDel;
public MyRecordWriter(DataOutputStream out, byte fieldDel)
throws UnsupportedEncodingException {
this(out, fieldDel, "\n".getBytes("UTF-8"));
}
public MyRecordWriter(DataOutputStream out, byte fieldDel, byte[] record) {
super(out);
this.fieldDel = fieldDel;
this.newline = record;
}
public synchronized void write(WritableComparable key, Tuple value)
throws IOException {
int sz = value.size();
for (int i = 0; i < sz; i++) {
StorageUtil.putField(out, value.get(i));
if (i != sz - 1) {
out.writeByte(fieldDel);
}
}
out.write(newline);
}
}
@Override
public RecordWriter<WritableComparable, Tuple> getRecordWriter(
TaskAttemptContext job) throws IOException, InterruptedException {
Configuration conf = job.getConfiguration();
boolean isCompressed = getCompressOutput(job);
CompressionCodec codec = null;
String extension = "";
if (isCompressed) {
Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(
job, GzipCodec.class);
codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass,
conf);
extension = codec.getDefaultExtension();
}
Path file = getDefaultWorkFile(job, extension);
FileSystem fs = file.getFileSystem(conf);
if (!isCompressed) {
FSDataOutputStream fileOut = fs.create(file, false);
return new MyRecordWriter(fileOut, fieldDel,
this.recordDel.getBytes());
} else {
FSDataOutputStream fileOut = fs.create(file, false);
return new MyRecordWriter(new DataOutputStream(
codec.createOutputStream(fileOut)), fieldDel,
this.recordDel.getBytes());
}
}
}
本人试验 \001 和 \002同样可以
grunt> register /home/pig/pig-0.11.0/udflib/myStorage.jar
grunt> cat X;
keyDataKNZKCZY:ZDKJS:616150:AFS:3842708d_20131219194420-642464756keyDataKNZKCZY:ZDKJS:616614:AFS:3843920d_20131219194420-642464756keyDataKNZKCZY:ZDKJS:616661:AFS:3844040d_20131219194420-642464756
grunt> a = load 'X' using com.hcr.hadoop.pig.MyStorage('\\001','\\002');
grunt> dump a;
(keyData,KNZKCZY:ZDKJS:616150:AFS:3842708,d_20131219194420-642464756)
(keyData,KNZKCZY:ZDKJS:616614:AFS:3843920,d_20131219194420-642464756)
(keyData,KNZKCZY:ZDKJS:616661:AFS:3844040,d_20131219194420-642464756)
grunt>
有的时候如果加载模式不想指定具体模式(比如太多了字段,或者不够公有化)就想使用已存在的模式
实现LoadMetadata接口,然后
重写
@Override
public ResourceSchema getSchema(String location, Job job)
throws IOException {
ResourceSchema rs=new ResourceSchema();
FieldSchema c1 = new FieldSchema("c1", DataType.INTEGER);
FieldSchema c2 = new FieldSchema("c2", DataType.INTEGER);
FieldSchema c3 = new FieldSchema("c3", DataType.DOUBLE);
ResourceFieldSchema fs1 =new ResourceFieldSchema(c1);
ResourceFieldSchema fs2 =new ResourceFieldSchema(c2);
ResourceFieldSchema fs3 =new ResourceFieldSchema(c3);
rs.setFields(new ResourceFieldSchema[]{fs1,fs2,fs3});
return rs;
}
这一个简单的例子中就返回了直接使用模式的形式
grunt> register /home/pig/pig-0.11.0/udflib/myStorage.jar
grunt> a = load 'student' using com.hcr.hadoop.pig.MyStorage(',','/');
grunt> describe a;
a: {c1: int,c2: int,c3: double}
grunt> b = foreach a generate c1,c2,c3;
grunt> describe b;
b: {c1: int,c2: int,c3: double}
本文介绍了如何通过自定义Pig UDF(User Defined Function)来实现对数据的灵活读取、处理和存储,包括指定列和行的分隔符,以适应不同格式的数据需求。通过实例演示了如何打包、注册UDF,并在Pig脚本中调用此UDF进行数据处理。此外,还展示了如何利用此UDF进行数据的存储,以及如何通过LoadMetadata接口返回通用的资源方案,从而实现对多种数据格式的支持。

711

被折叠的 条评论
为什么被折叠?



