pamio

A = load '/tmp/alice.txt';
B = foreach A generate flatten(TOKENIZE((chararray)$0)) as word;
C = filter B by word matches '\\w+';
D = group C by word;
E = foreach D generate COUNT(C), group;
store E into '/tmp/alice_wordcount';

pamio

REGISTER contrib/piggybank/java/piggybank.jar                           
DEFINE SUBSTRING org.apache.pig.piggybank.evaluation.string.SUBSTRING();
A = load 'gutenberg/sample.txt';                                        
C = foreach A generate SUBSTRING((chararray)$0, 0, 5);                  
dump C;

pamio

input = {"Root"=>[{"1"=>[{"4"=>"leaf4", "5"=>"leaf5"}]}, {"2"=>[{"6"=>"leaf6", "7"=>"leaf7"}]}]}

def traverse(path = "")
  self.each do|key, value|
    if value.is_a?(Hash)
      path += "#{key}=>"
      value.traverse(path)
    else
      if value.is_a?(Array)
        path += "#{key}=>"