diff --git a/edp-examples/README.rst b/edp-examples/README.rst new file mode 100644 index 0000000..549baf4 --- /dev/null +++ b/edp-examples/README.rst @@ -0,0 +1,4 @@ +EDP Examples +============ + +* Pig job example - trim spaces in input file diff --git a/edp-examples/pig-job/README.rst b/edp-examples/pig-job/README.rst new file mode 100644 index 0000000..0fc93af --- /dev/null +++ b/edp-examples/pig-job/README.rst @@ -0,0 +1,4 @@ +Example Pig job +=============== + +This script trims spaces in input text diff --git a/edp-examples/pig-job/example.pig b/edp-examples/pig-job/example.pig new file mode 100644 index 0000000..4141906 --- /dev/null +++ b/edp-examples/pig-job/example.pig @@ -0,0 +1,3 @@ +A = load '$INPUT' using PigStorage(':') as (fruit: chararray); +B = foreach A generate com.hadoopbook.pig.Trim(fruit); +store B into '$OUTPUT' USING PigStorage(); diff --git a/edp-examples/pig-job/expected_output b/edp-examples/pig-job/expected_output new file mode 100644 index 0000000..60a0142 --- /dev/null +++ b/edp-examples/pig-job/expected_output @@ -0,0 +1,4 @@ +pomegranate +banana +apple +lychee \ No newline at end of file diff --git a/edp-examples/pig-job/input b/edp-examples/pig-job/input new file mode 100644 index 0000000..d2079b5 --- /dev/null +++ b/edp-examples/pig-job/input @@ -0,0 +1,4 @@ + pomegranate + banana + apple + lychee \ No newline at end of file diff --git a/edp-examples/pig-job/udf.jar b/edp-examples/pig-job/udf.jar new file mode 100644 index 0000000..2eba702 Binary files /dev/null and b/edp-examples/pig-job/udf.jar differ