abshingate

/**
* Introduction to gist
*/
public class HelloGist{
 
  public static void sayHello(){
    System.out.println("Hello gist");
  }
}

abshingate

<repositories>
	<repository>
		<id>cloudera-releases</id>
		<url>https://repository.cloudera.com/artifactory/cloudera-repos</url>
		<releases>
			<enabled>true</enabled>
		</releases>
		<snapshots>
			<enabled>false</enabled>
		</snapshots>

abshingate

<dependency>
	<groupId>org.apache.hadoop</groupId>
	<artifactId>hadoop-core</artifactId>
	<version>0.20.2-cdh3u6</version>
</dependency>
<dependency>
	<groupId>org.apache.pig</groupId>
	<artifactId>pigunit</artifactId>
	<version>0.10.0-cdh3u4</version>
</dependency>

abshingate

A = load 'src/main/resources/sample.data';
B = foreach A generate flatten(TOKENIZE((chararray)$0)) as word;
C = group B by word;
D = foreach C generate COUNT(B), group;
dump D;

abshingate

Johny, Johny!
Yes, Papa
Eating sugar?
No, Papa
Telling lies?
No, Papa
Open your mouth!
Ha! Ha! Ha!

abshingate

public void testStudentsPigScript() throws Exception {
	PigTest pigTest = new PigTest("src/main/resources/wordcount.pig");
	pigTest.assertOutput("D", new String[] { "(2,No)", "(3,Ha!)",
			"(1,Yes)", "(1,Open)", "(3,Papa)", "(1,your)", "(1,Johny)",
			"(1,lies?)", "(1,Eating)", "(1,Johny!)", "(1,mouth!)",
			"(1,sugar?)", "(1,Telling)", });
}

abshingate

<NotepadPlus>
    <UserLang name="Apache PIG" ext="pig" udlVersion="2.1">
        <Settings>
            <Global caseIgnored="yes" allowFoldOfComments="yes" foldCompact="no" forcePureLC="0" decimalSeparator="0" />
            <Prefix Keywords1="no" Keywords2="no" Keywords3="no" Keywords4="no" Keywords5="no" Keywords6="no" Keywords7="no" Keywords8="no" />
        </Settings>
        <KeywordLists>
            <Keywords name="Comments">00-- 01 02 03/* 04*/</Keywords>
            <Keywords name="Numbers, prefix1"></Keywords>
            <Keywords name="Numbers, prefix2"></Keywords>

abshingate

-bash-3.2$ echo -e "mark||2011\ntony|Mr.|2012\nrichard||2013" > input.txt
-bash-3.2$ cat input.txt
mark||2011
tony|Mr.|2012
richard||2013

abshingate

-bash-3.2$ hadoop fs -copyFromLocal input.txt /user/abhijit/input.txt
-bash-3.2$ hadoop fs -cat /user/abhijit/input.txt
mark||2011
tony|Mr.|2012
richard||2013

abshingate

CREATE EXTERNAL TABLE person
(
    name string,
    title string,
    birth_year string
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
LOCATION '/person';