cascading.jruby 0.0.9 → 0.0.10

data/bin/make_job

@@ -1,81 +0,0 @@
-#!/usr/bin/env jruby
-
-require 'java'
-
-$LOAD_PATH.unshift(::File.expand_path(::File.join(::File.dirname(__FILE__), "..", "jruby")))
-$LOAD_PATH.unshift(::File.expand_path(::File.join(::File.dirname(__FILE__), "..", "jobs")))
-
-require 'rubygems'
-require 'cascading'
-require 'fileutils'
-require 'optparse'
-require 'ostruct'
-
-include FileUtils
-
-TEMP_DIR = "_temp_jars"
-TEMP_DIR_LIB = ::File.join(TEMP_DIR, "lib")
-CASCADING_JRUBY_HOME = Cascading::PATH
-CASCADING_HOME = ENV["CASCADING_HOME"]
-JRUBY_HOME = ENV["JRUBY_HOME"]
-
-options = OpenStruct.new
-options.input = ARGV[0]
-options.output = "job.jar"
-options.libs = []
-
-OptionParser.new do |opts|
-   opts.banner = "Usage: make_job [options]"
-
-   opts.on("-o", "--output", "Set the name of the output jar file (job.jar by default)") do |v|
-     options.output = v
-   end
-
-   opts.on("-l", "--lib LIBPATH", "Set the path where external libraries are stored") do |path|
-     options.libs << path
-   end
- end.parse!
- 
-p options
-
-# Create temp dir
-mkdir(TEMP_DIR) unless File.exists? TEMP_DIR
-mkdir(TEMP_DIR_LIB) unless File.exists? TEMP_DIR_LIB
-
-def copy(from, to, message=nil)
-  puts message if message 
-  Dir.glob(from).each do |f|
-    cp_r(f, to)
-  end
-end
-
-# Copy job files into TEMP_DIR:
-files = ::File.join(options.input, "**", "*.rb")
-copy(files, TEMP_DIR,  "Copying job files to temp dir...")
-
-# Copy external libs into TEMP_DIR:
-for lib in options.libs
-  files = ::File.join(lib, "**", "*.jar")
-  copy(files, TEMP_DIR_LIB,  "Copying external libs to temp dir...")
-end
-
-files = ::File.join(CASCADING_JRUBY_HOME, "lib", "**")
-copy(files, TEMP_DIR, "Copying cascading.jruby files to temp dir...")
-
-# Copy cascading.jruby.runner classes:
-files = ::File.join(CASCADING_JRUBY_HOME, "classes", "**")
-copy(files, TEMP_DIR, "Copying cascading.jruby files to temp dir...")
-
-# Copy cascading jars in _temp_jars/lib
-files = ::File.join(CASCADING_HOME, "**", "*.jar")
-copy(files, TEMP_DIR_LIB, "Copying Cascading jars to temp dir...")
-
-# Jar the whole thing:
-puts "Building final jar file (#{options.output})..."
-system("jar cvf #{options.output} -C #{TEMP_DIR}/ .")
-
-# Clean-up things
-puts "Cleaning temp dir..."
-rm_rf(TEMP_DIR)
-
-puts "Finished. Have Fun!"

data/ivy.xml

@@ -1,25 +0,0 @@
-<?xml version="1.0" encoding="ISO-8859-1"?>
-<ivy-module version="2.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
-       xsi:noNamespaceSchemaLocation="http://ant.apache.org/ivy/schemas/ivy.xsd">
-  <info organisation="com.etsy" module="cascading.jruby" status="integration" />
- 
-  <configurations>
-    <conf name="default" visibility="public" description="runtime dependencies and master artifact can be used with this conf" extends="runtime,master" />
-    <conf name="master" visibility="public" description="contains only the artifact published by this module itself, with no transitive dependencies" />
-    <conf name="compile" visibility="public" description="this is the default scope, used if none is specified. Compile dependencies are available in all classpaths." />
-    <conf name="provided" visibility="public" description="this is much like compile, but indicates you expect the JDK or a container to provide it. It is only available on the compilation classpath, and is not transitive." />
-    <conf name="runtime" visibility="public" description="this scope indicates that the dependency is not required for compilation, but is for execution. It is in the runtime and test classpaths, but not the compile classpath." extends="compile" />
-    <conf name="test" visibility="private" description="this scope indicates that the dependency is not required for normal use of the application, and is only available for the test compilation and execution phases." extends="runtime" />
-    <conf name="system" visibility="public" description="this scope is similar to provided except that you have to provide the JAR which contains it explicitly. The artifact is always available and is not looked up in a repository." />
-    <conf name="sources" visibility="public" description="this configuration contains the source artifact of this module, if any." />
-    <conf name="javadoc" visibility="public" description="this configuration contains the javadoc artifact of this module, if any." />
-    <conf name="optional" visibility="public" description="contains all optional dependencies" />
-  </configurations>
-
-  <dependencies>
-    <dependency org="cascading" name="cascading-core" rev="2.0.0" conf="default" />
-    <dependency org="cascading" name="cascading-local" rev="2.0.0" conf="default" />
-    <dependency org="cascading" name="cascading-hadoop" rev="2.0.0" conf="default" />
-    <dependency org="org.jruby" name="jruby" rev="1.6.5" conf="default" />
-  </dependencies>
-</ivy-module>

data/ivysettings.xml

@@ -1,7 +0,0 @@
-<ivysettings>
-  <include url="http://conjars.org/repo/ivysettings.xml"/>
-
-  <resolvers>
-    <ibiblio name="public" m2compatible="true"/>
-  </resolvers>
-</ivysettings>

data/samples/branch.rb

@@ -1,30 +0,0 @@
-#! /usr/bin/env jruby
-
-$: << File.join(File.dirname(__FILE__), '..', 'lib')
-
-require 'cascading'
-
-cascade 'branch', :mode => :local do
-  flow 'branch' do
-    source 'input', tap('samples/data/data2.txt')
-
-    assembly 'input' do
-      split 'line', ['name', 'score1', 'score2', 'id'], :pattern => /[.,]*\s+/
-
-      branch 'branch1' do
-        group_by 'score1' do
-          count
-        end
-      end
-
-      branch 'branch2' do
-        group_by 'score2' do
-          count
-        end
-      end
-    end
-
-    sink 'branch1', tap('output/branch1', :sink_mode => :replace)
-    sink 'branch2', tap('output/branch2', :sink_mode => :replace)
-  end
-end.complete

data/samples/copy.rb

@@ -1,20 +0,0 @@
-#! /usr/bin/env jruby
-$: << File.join(File.dirname(__FILE__), '..', 'lib')
-
-require 'cascading'
-
-cascade 'copy', :mode => :local do
-  flow 'copy' do
-    # You don't have to curl and cache inputs: tap can fetch via HTTP
-    #source 'input', tap('http://www.census.gov/genealogy/names/dist.all.last')
-    source 'input', tap('samples/data/genealogy/names/dist.all.last')
-
-    assembly 'input' do
-      rename 'line' => 'value'
-      # We override validate_with because we know line will never be null
-      reject 'value:string.indexOf("R") == -1', :validate_with => { :value => 'nothinghere' }
-    end
-
-    sink 'input', tap('output/copy', :sink_mode => :replace)
-  end
-end.complete