Reading a file with newlines as a tuple in pig - hadoop

Question

Is it possible to change the record delimiter from newline to some other string so as to read a file with newlines into a single tuple in pig.

Answer 1

Yes.
A = LOAD '...' USING PigStorage(',') AS (...); //comma is the delimeter for fields
SET textinputformat.record.delimiter '<delimeter>'; // record delimeter, by default it is `\n`. You can change to any delimeter.

Answer 2

As mentioned here
You can use PigStorage
A = LOAD '/some/path/COMMA-DELIM-PREFIX*' USING PigStorage(',') AS (f1:chararray, ...);
B = LOAD '/some/path/SEMICOLON-DELIM-PREFIX*' USING PigStorage('\t') AS (f1:chararray, ...);
You can even try writing load/store UDF.
There is java code example for both load and store.
Load Functions : LoadFunc abstract class has the main methods for loading data and for most use cases it would suffice to extend it. You can read more here
Example
The loader implementation in the example is a loader for text data
with line delimiter as '\n' and '\t' as default field delimiter (which
can be overridden by passing a different field delimiter in the
constructor) - this is similar to current PigStorage loader in Pig.
The implementation uses an existing Hadoop supported Inputformat -
TextInputFormat - as the underlying InputFormat.
public class SimpleTextLoader extends LoadFunc {
protected RecordReader in = null;
private byte fieldDel = '\t';
private ArrayList<Object> mProtoTuple = null;
private TupleFactory mTupleFactory = TupleFactory.getInstance();
private static final int BUFFER_SIZE = 1024;
public SimpleTextLoader() {
}
/**
* Constructs a Pig loader that uses specified character as a field delimiter.
*
* #param delimiter
* the single byte character that is used to separate fields.
* ("\t" is the default.)
*/
public SimpleTextLoader(String delimiter) {
this();
if (delimiter.length() == 1) {
this.fieldDel = (byte)delimiter.charAt(0);
} else if (delimiter.length() > 1 & & delimiter.charAt(0) == '\\') {
switch (delimiter.charAt(1)) {
case 't':
this.fieldDel = (byte)'\t';
break;
case 'x':
fieldDel =
Integer.valueOf(delimiter.substring(2), 16).byteValue();
break;
case 'u':
this.fieldDel =
Integer.valueOf(delimiter.substring(2)).byteValue();
break;
default:
throw new RuntimeException("Unknown delimiter " + delimiter);
}
} else {
throw new RuntimeException("PigStorage delimeter must be a single character");
}
}
#Override
public Tuple getNext() throws IOException {
try {
boolean notDone = in.nextKeyValue();
if (!notDone) {
return null;
}
Text value = (Text) in.getCurrentValue();
byte[] buf = value.getBytes();
int len = value.getLength();
int start = 0;
for (int i = 0; i < len; i++) {
if (buf[i] == fieldDel) {
readField(buf, start, i);
start = i + 1;
}
}
// pick up the last field
readField(buf, start, len);
Tuple t = mTupleFactory.newTupleNoCopy(mProtoTuple);
mProtoTuple = null;
return t;
} catch (InterruptedException e) {
int errCode = 6018;
String errMsg = "Error while reading input";
throw new ExecException(errMsg, errCode,
PigException.REMOTE_ENVIRONMENT, e);
}
}
private void readField(byte[] buf, int start, int end) {
if (mProtoTuple == null) {
mProtoTuple = new ArrayList<Object>();
}
if (start == end) {
// NULL value
mProtoTuple.add(null);
} else {
mProtoTuple.add(new DataByteArray(buf, start, end));
}
}
#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);
}
}
Store Functions : StoreFunc abstract class has the main methods for storing data and for most use cases it should suffice to extend it
Example
The storer implementation in the example is a storer for text data
with line delimiter as '\n' and '\t' as default field delimiter (which
can be overridden by passing a different field delimiter in the
constructor) - this is similar to current PigStorage storer in Pig.
The implementation uses an existing Hadoop supported OutputFormat -
TextOutputFormat as the underlying OutputFormat.
public class SimpleTextStorer extends StoreFunc {
protected RecordWriter writer = null;
private byte fieldDel = '\t';
private static final int BUFFER_SIZE = 1024;
private static final String UTF8 = "UTF-8";
public PigStorage() {
}
public PigStorage(String delimiter) {
this();
if (delimiter.length() == 1) {
this.fieldDel = (byte)delimiter.charAt(0);
} else if (delimiter.length() > 1delimiter.charAt(0) == '\\') {
switch (delimiter.charAt(1)) {
case 't':
this.fieldDel = (byte)'\t';
break;
case 'x':
fieldDel =
Integer.valueOf(delimiter.substring(2), 16).byteValue();
break;
case 'u':
this.fieldDel =
Integer.valueOf(delimiter.substring(2)).byteValue();
break;
default:
throw new RuntimeException("Unknown delimiter " + delimiter);
}
} else {
throw new RuntimeException("PigStorage delimeter must be a single character");
}
}
ByteArrayOutputStream mOut = new ByteArrayOutputStream(BUFFER_SIZE);
#Override
public void putNext(Tuple f) throws IOException {
int sz = f.size();
for (int i = 0; i < sz; i++) {
Object field;
try {
field = f.get(i);
} catch (ExecException ee) {
throw ee;
}
putField(field);
if (i != sz - 1) {
mOut.write(fieldDel);
}
}
Text text = new Text(mOut.toByteArray());
try {
writer.write(null, text);
mOut.reset();
} catch (InterruptedException e) {
throw new IOException(e);
}
}
#SuppressWarnings("unchecked")
private void putField(Object field) throws IOException {
//string constants for each delimiter
String tupleBeginDelim = "(";
String tupleEndDelim = ")";
String bagBeginDelim = "{";
String bagEndDelim = "}";
String mapBeginDelim = "[";
String mapEndDelim = "]";
String fieldDelim = ",";
String mapKeyValueDelim = "#";
switch (DataType.findType(field)) {
case DataType.NULL:
break; // just leave it empty
case DataType.BOOLEAN:
mOut.write(((Boolean)field).toString().getBytes());
break;
case DataType.INTEGER:
mOut.write(((Integer)field).toString().getBytes());
break;
case DataType.LONG:
mOut.write(((Long)field).toString().getBytes());
break;
case DataType.FLOAT:
mOut.write(((Float)field).toString().getBytes());
break;
case DataType.DOUBLE:
mOut.write(((Double)field).toString().getBytes());
break;
case DataType.BYTEARRAY: {
byte[] b = ((DataByteArray)field).get();
mOut.write(b, 0, b.length);
break;
}
case DataType.CHARARRAY:
// oddly enough, writeBytes writes a string
mOut.write(((String)field).getBytes(UTF8));
break;
case DataType.MAP:
boolean mapHasNext = false;
Map<String, Object> m = (Map<String, Object>)field;
mOut.write(mapBeginDelim.getBytes(UTF8));
for(Map.Entry<String, Object> e: m.entrySet()) {
if(mapHasNext) {
mOut.write(fieldDelim.getBytes(UTF8));
} else {
mapHasNext = true;
}
putField(e.getKey());
mOut.write(mapKeyValueDelim.getBytes(UTF8));
putField(e.getValue());
}
mOut.write(mapEndDelim.getBytes(UTF8));
break;
case DataType.TUPLE:
boolean tupleHasNext = false;
Tuple t = (Tuple)field;
mOut.write(tupleBeginDelim.getBytes(UTF8));
for(int i = 0; i < t.size(); ++i) {
if(tupleHasNext) {
mOut.write(fieldDelim.getBytes(UTF8));
} else {
tupleHasNext = true;
}
try {
putField(t.get(i));
} catch (ExecException ee) {
throw ee;
}
}
mOut.write(tupleEndDelim.getBytes(UTF8));
break;
case DataType.BAG:
boolean bagHasNext = false;
mOut.write(bagBeginDelim.getBytes(UTF8));
Iterator<Tuple> tupleIter = ((DataBag)field).iterator();
while(tupleIter.hasNext()) {
if(bagHasNext) {
mOut.write(fieldDelim.getBytes(UTF8));
} else {
bagHasNext = true;
}
putField((Object)tupleIter.next());
}
mOut.write(bagEndDelim.getBytes(UTF8));
break;
default: {
int errCode = 2108;
String msg = "Could not determine data type of field: " + field;
throw new ExecException(msg, errCode, PigException.BUG);
}
}
}
#Override
public OutputFormat getOutputFormat() {
return new TextOutputFormat<WritableComparable, Text>();
}
#Override
public void prepareToWrite(RecordWriter writer) {
this.writer = writer;
}
#Override
public void setStoreLocation(String location, Job job) throws IOException {
job.getConfiguration().set("mapred.textoutputformat.separator", "");
FileOutputFormat.setOutputPath(job, new Path(location));
if (location.endsWith(".bz2")) {
FileOutputFormat.setCompressOutput(job, true);
FileOutputFormat.setOutputCompressorClass(job, BZip2Codec.class);
} else if (location.endsWith(".gz")) {
FileOutputFormat.setCompressOutput(job, true);
FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);
}
}
}