elasticity 1.4 → 1.4.1

data/HISTORY.md

@@ -1,6 +1,14 @@
+### 1.4.1
+
++ Added Elasticity::EMR#describe_jobflow("jobflow_id") for describing a specific job.  If you happen to run hundreds of EMR jobs, this makes retrieving jobflow status much faster than using Elasticity::EMR#describe_jobflowS which pulls down and parses XML status for hundreds of jobs.
+
+### 1.4
+
++ Added Elasticity::CustomJarJob for launching "Custom Jar" jobs.
+
 ### 1.3.1
 
-+ Explicitly requiring 'time'.
++ Explicitly requiring 'time' (only a problem if you aren't running from within a Rails environment).
 + Elasticity::JobFlow now exposes last_state_change_reason.
 
 ### 1.3 (Contributions from Wouter Broekhof)

data/README.md

@@ -177,15 +177,28 @@ AddJobFlowSteps adds the specified steps to the specified job flow.
   })
 </pre>
 
+## describe_jobflow (Elasticity Convenience Method)
+
+This is a convenience methods that wraps DescribeJobFlow to return the status of a single job.
+
+<pre>
+  emr = Elasticity::EMR.new(ENV["AWS_ACCESS_KEY_ID"], ENV["AWS_SECRET_KEY"])
+  jobflow = emr.describe_jobflow("j-129V5AQFMKO1C")
+  p jobflow.jobflow_id
+  > "j-129V5AQFMKO1C"
+  p jobflow.name
+  > "Elasticity Test Job"
+</pre>
+
 ## DescribeJobFlows
 
-DescribeJobFlows returns detailed information as to the state of all jobs.  Currently this is wrapped in an <code>Elasticity::JobFlow</code> that contains the <code>name</code>, <code>jobflow_id</code> and <code>state</code>.  
+DescribeJobFlows returns detailed information as to the state of all jobs.  Currently this is wrapped in an <code>Elasticity::JobFlow</code> that contains the <code>name</code>, <code>jobflow_id</code> and <code>state</code>.
 
 <pre>
   emr = Elasticity::EMR.new(ENV["AWS_ACCESS_KEY_ID"], ENV["AWS_SECRET_KEY"])
   jobflows = emr.describe_jobflows
   p jobflows.map(&:name)
-  
+
   > ["Hive Test", "Pig Test", "Interactive Hadoop", "Interactive Hive"]
 </pre>
 
@@ -333,7 +346,7 @@ If you're chomping at the bit to initiate some EMR functionality that isn't wrap
 # License
 
 <pre>
-  Copyright 2011 Robert Slifka
+  Copyright 2011-2012 Robert Slifka
 
   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.

data/lib/elasticity/emr.rb

@@ -6,6 +6,26 @@ module Elasticity
       @aws_request = Elasticity::AwsRequest.new(aws_access_key_id, aws_secret_access_key, options)
     end
 
+    # Describe a specific jobflow.
+    #
+    #   describe_jobflow("j-3UN6WX5RRO2AG")
+    #
+    # Raises ArgumentError if the specified jobflow does not exist.
+    def describe_jobflow(jobflow_id)
+      begin
+        aws_result = @aws_request.aws_emr_request(EMR.convert_ruby_to_aws({
+          :operation => "DescribeJobFlows",
+          :job_flow_ids => [jobflow_id]
+        }))
+        xml_doc = Nokogiri::XML(aws_result)
+        xml_doc.remove_namespaces!
+        yield aws_result if block_given?
+        JobFlow.from_members_nodeset(xml_doc.xpath("/DescribeJobFlowsResponse/DescribeJobFlowsResult/JobFlows/member")).first
+      rescue RestClient::BadRequest => e
+        raise ArgumentError, EMR.parse_error_response(e.http_body)
+      end
+    end
+
     # Lists all jobflows in all states.
     #
     # To override this behaviour, pass additional filters as specified in the AWS

data/lib/elasticity/version.rb

@@ -1,3 +1,3 @@
 module Elasticity
-  VERSION = "1.4"
+  VERSION = "1.4.1"
 end

data/spec/lib/elasticity/emr_spec.rb

@@ -318,6 +318,89 @@ describe Elasticity::EMR do
 
   end
 
+  describe "#describe_jobflow" do
+    before do
+      @describe_jobflows_xml = <<-JOBFLOWS
+        <DescribeJobFlowsResponse xmlns="http://elasticmapreduce.amazonaws.com/doc/2009-03-31">
+          <DescribeJobFlowsResult>
+            <JobFlows>
+              <member>
+                <ExecutionStatusDetail>
+                  <State>TERMINATED</State>
+                </ExecutionStatusDetail>
+                <JobFlowId>j-3UN6WX5RRO2AG</JobFlowId>
+                <Name>The One Job Flow</Name>
+              </member>
+            </JobFlows>
+          </DescribeJobFlowsResult>
+        </DescribeJobFlowsResponse>
+      JOBFLOWS
+    end
+
+    it "should ask AWS about the specified job flow" do
+      aws_request = Elasticity::AwsRequest.new("","")
+      aws_request.should_receive(:aws_emr_request).with({
+        "Operation" => "DescribeJobFlows",
+        "JobFlowIds.member.1" => "j-3UN6WX5RRO2AG"
+      })
+      Elasticity::AwsRequest.stub(:new).and_return(aws_request)
+      emr = Elasticity::EMR.new("", "")
+      emr.describe_jobflow("j-3UN6WX5RRO2AG")
+    end
+
+    context "when the job flow ID exists" do
+      it "should return a JobFlow" do
+        aws_request = Elasticity::AwsRequest.new("","")
+        aws_request.stub(:aws_emr_request).with({
+          "Operation" => "DescribeJobFlows",
+          "JobFlowIds.member.1" => "j-3UN6WX5RRO2AG"
+        }).and_return(@describe_jobflows_xml)
+        Elasticity::AwsRequest.stub(:new).and_return(aws_request)
+        emr = Elasticity::EMR.new("", "")
+        jobflow = emr.describe_jobflow("j-3UN6WX5RRO2AG")
+        jobflow.jobflow_id.should == "j-3UN6WX5RRO2AG"
+      end
+    end
+
+    context "when there is an error" do
+      before do
+        @error_xml = <<-ERROR
+          <ErrorResponse xmlns="http://elasticmapreduce.amazonaws.com/doc/2009-03-31">
+            <Error>
+              <Message>Specified job flow ID not valid</Message>
+            </Error>
+          </ErrorResponse>
+        ERROR
+      end
+
+      it "should raise an ArgumentError with the error message" do
+        aws_request = Elasticity::AwsRequest.new("aws_access_key_id", "aws_secret_key")
+        @exception = RestClient::BadRequest.new
+        @exception.should_receive(:http_body).and_return(@error_xml)
+        aws_request.should_receive(:aws_emr_request).and_raise(@exception)
+        Elasticity::AwsRequest.should_receive(:new).and_return(aws_request)
+        emr = Elasticity::EMR.new("aws_access_key_id", "aws_secret_key")
+        lambda {
+          emr.describe_jobflow("bad_jobflow_id")
+        }.should raise_error(ArgumentError, "Specified job flow ID not valid")
+      end
+    end
+
+    context "when a block is provided" do
+      it "should yield to the block" do
+        aws_request = Elasticity::AwsRequest.new("aws_access_key_id", "aws_secret_key")
+        aws_request.should_receive(:aws_emr_request).and_return("describe!")
+        Elasticity::AwsRequest.should_receive(:new).and_return(aws_request)
+        emr = Elasticity::EMR.new("aws_access_key_id", "aws_secret_key")
+        xml_result = nil
+        emr.describe_jobflow("_") do |xml|
+          xml_result = xml
+        end
+        xml_result.should == "describe!"
+      end
+    end
+  end
+
   describe "#modify_instance_groups" do
 
     describe "integration happy path" do

metadata

@@ -1,12 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: elasticity
 version: !ruby/object:Gem::Version 
-  hash: 7
+  hash: 5
   prerelease: 
   segments: 
   - 1
   - 4
-  version: "1.4"
+  - 1
+  version: 1.4.1
 platform: ruby
 authors: 
 - Robert Slifka
@@ -14,7 +15,8 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-12-09 00:00:00 Z
+date: 2011-12-17 00:00:00 -08:00
+default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: rest-client
@@ -199,6 +201,7 @@ files:
 - spec/lib/elasticity/job_flow_step_spec.rb
 - spec/lib/elasticity/pig_job_spec.rb
 - spec/spec_helper.rb
+has_rdoc: true
 homepage: http://www.github.com/rslifka/elasticity
 licenses: []
 
@@ -228,7 +231,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.8.6
+rubygems_version: 1.4.1
 signing_key: 
 specification_version: 3
 summary: Programmatic access to Amazon's Elastic Map Reduce service.