swineherd 0.0.1

data/LICENSE

@@ -0,0 +1,201 @@
+                              Apache License
+                        Version 2.0, January 2004
+                     http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+   "License" shall mean the terms and conditions for use, reproduction,
+   and distribution as defined by Sections 1 through 9 of this document.
+
+   "Licensor" shall mean the copyright owner or entity authorized by
+   the copyright owner that is granting the License.
+
+   "Legal Entity" shall mean the union of the acting entity and all
+   other entities that control, are controlled by, or are under common
+   control with that entity. For the purposes of this definition,
+   "control" means (i) the power, direct or indirect, to cause the
+   direction or management of such entity, whether by contract or
+   otherwise, or (ii) ownership of fifty percent (50%) or more of the
+   outstanding shares, or (iii) beneficial ownership of such entity.
+
+   "You" (or "Your") shall mean an individual or Legal Entity
+   exercising permissions granted by this License.
+
+   "Source" form shall mean the preferred form for making modifications,
+   including but not limited to software source code, documentation
+   source, and configuration files.
+
+   "Object" form shall mean any form resulting from mechanical
+   transformation or translation of a Source form, including but
+   not limited to compiled object code, generated documentation,
+   and conversions to other media types.
+
+   "Work" shall mean the work of authorship, whether in Source or
+   Object form, made available under the License, as indicated by a
+   copyright notice that is included in or attached to the work
+   (an example is provided in the Appendix below).
+
+   "Derivative Works" shall mean any work, whether in Source or Object
+   form, that is based on (or derived from) the Work and for which the
+   editorial revisions, annotations, elaborations, or other modifications
+   represent, as a whole, an original work of authorship. For the purposes
+   of this License, Derivative Works shall not include works that remain
+   separable from, or merely link (or bind by name) to the interfaces of,
+   the Work and Derivative Works thereof.
+
+   "Contribution" shall mean any work of authorship, including
+   the original version of the Work and any modifications or additions
+   to that Work or Derivative Works thereof, that is intentionally
+   submitted to Licensor for inclusion in the Work by the copyright owner
+   or by an individual or Legal Entity authorized to submit on behalf of
+   the copyright owner. For the purposes of this definition, "submitted"
+   means any form of electronic, verbal, or written communication sent
+   to the Licensor or its representatives, including but not limited to
+   communication on electronic mailing lists, source code control systems,
+   and issue tracking systems that are managed by, or on behalf of, the
+   Licensor for the purpose of discussing and improving the Work, but
+   excluding communication that is conspicuously marked or otherwise
+   designated in writing by the copyright owner as "Not a Contribution."
+
+   "Contributor" shall mean Licensor and any individual or Legal Entity
+   on behalf of whom a Contribution has been received by Licensor and
+   subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   copyright license to reproduce, prepare Derivative Works of,
+   publicly display, publicly perform, sublicense, and distribute the
+   Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   (except as stated in this section) patent license to make, have made,
+   use, offer to sell, sell, import, and otherwise transfer the Work,
+   where such license applies only to those patent claims licensable
+   by such Contributor that are necessarily infringed by their
+   Contribution(s) alone or by combination of their Contribution(s)
+   with the Work to which such Contribution(s) was submitted. If You
+   institute patent litigation against any entity (including a
+   cross-claim or counterclaim in a lawsuit) alleging that the Work
+   or a Contribution incorporated within the Work constitutes direct
+   or contributory patent infringement, then any patent licenses
+   granted to You under this License for that Work shall terminate
+   as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+   Work or Derivative Works thereof in any medium, with or without
+   modifications, and in Source or Object form, provided that You
+   meet the following conditions:
+
+   (a) You must give any other recipients of the Work or
+       Derivative Works a copy of this License; and
+
+   (b) You must cause any modified files to carry prominent notices
+       stating that You changed the files; and
+
+   (c) You must retain, in the Source form of any Derivative Works
+       that You distribute, all copyright, patent, trademark, and
+       attribution notices from the Source form of the Work,
+       excluding those notices that do not pertain to any part of
+       the Derivative Works; and
+
+   (d) If the Work includes a "NOTICE" text file as part of its
+       distribution, then any Derivative Works that You distribute must
+       include a readable copy of the attribution notices contained
+       within such NOTICE file, excluding those notices that do not
+       pertain to any part of the Derivative Works, in at least one
+       of the following places: within a NOTICE text file distributed
+       as part of the Derivative Works; within the Source form or
+       documentation, if provided along with the Derivative Works; or,
+       within a display generated by the Derivative Works, if and
+       wherever such third-party notices normally appear. The contents
+       of the NOTICE file are for informational purposes only and
+       do not modify the License. You may add Your own attribution
+       notices within Derivative Works that You distribute, alongside
+       or as an addendum to the NOTICE text from the Work, provided
+       that such additional attribution notices cannot be construed
+       as modifying the License.
+
+   You may add Your own copyright statement to Your modifications and
+   may provide additional or different license terms and conditions
+   for use, reproduction, or distribution of Your modifications, or
+   for any such Derivative Works as a whole, provided Your use,
+   reproduction, and distribution of the Work otherwise complies with
+   the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+   any Contribution intentionally submitted for inclusion in the Work
+   by You to the Licensor shall be under the terms and conditions of
+   this License, without any additional terms or conditions.
+   Notwithstanding the above, nothing herein shall supersede or modify
+   the terms of any separate license agreement you may have executed
+   with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+   names, trademarks, service marks, or product names of the Licensor,
+   except as required for reasonable and customary use in describing the
+   origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+   agreed to in writing, Licensor provides the Work (and each
+   Contributor provides its Contributions) on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+   implied, including, without limitation, any warranties or conditions
+   of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+   PARTICULAR PURPOSE. You are solely responsible for determining the
+   appropriateness of using or redistributing the Work and assume any
+   risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+   whether in tort (including negligence), contract, or otherwise,
+   unless required by applicable law (such as deliberate and grossly
+   negligent acts) or agreed to in writing, shall any Contributor be
+   liable to You for damages, including any direct, indirect, special,
+   incidental, or consequential damages of any character arising as a
+   result of this License or out of the use or inability to use the
+   Work (including but not limited to damages for loss of goodwill,
+   work stoppage, computer failure or malfunction, or any and all
+   other commercial damages or losses), even if such Contributor
+   has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+   the Work or Derivative Works thereof, You may choose to offer,
+   and charge a fee for, acceptance of support, warranty, indemnity,
+   or other liability obligations and/or rights consistent with this
+   License. However, in accepting such obligations, You may act only
+   on Your own behalf and on Your sole responsibility, not on behalf
+   of any other Contributor, and only if You agree to indemnify,
+   defend, and hold each Contributor harmless for any liability
+   incurred by, or claims asserted against, such Contributor by reason
+   of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+   To apply the Apache License to your work, attach the following
+   boilerplate notice, with the fields enclosed by brackets "[]"
+   replaced with your own identifying information. (Don't include
+   the brackets!)  The text should be enclosed in the appropriate
+   comment syntax for the file format. We also recommend that a
+   file or class name and description of purpose be included on the
+   same "printed page" as the copyright notice for easier
+   identification within third-party archives.
+
+Copyright [yyyy] [name of copyright owner]
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

data/README.textile

@@ -0,0 +1,207 @@
+h1. SwineHerd
+
+Swineherd is for running scripts and workflows on filesystems.
+
+h3. Outline
+
+A @workflow@ is built with @script@ objects and ran on a @filesystem@.
+
+h4. Script:
+
+A script has the following
+
+* @source@ - The source file used. These can be "Apache Pig":http://pig.apache.org/ scripts, "Wukong":http://github.com/infochimps/wukong scripts, even "R":http://www.r-project.org/ scripts. You can add your own scripts by subclassing the @script@ class. 
+* @input@ - An array of input paths.
+* @output@ - An array of output paths.
+* @options@ - A ruby hash of options used as command line args. Eg. {:foo => 'bar'}. How these options are mapped to command line arguments is up to the particular script class.
+* @attributes@ - A ruby hash of parameters used for variable substitution. Every script is assumed to be (but not required to be) an eruby template.
+
+h4. Workflow:
+
+A workflow is built using rake @task@ objects that doing nothing more than run scripts. A workflow
+
+* can be described with a directed dependency graph
+* has an @id@ which is used to run its tasks idempotently. At the moment it is the responsibility of the running process (or human being) to choose a suitable id.
+* manages intermediate outputs by using the @next_output@ and @latest_output@ methods. See the examples dir for usage.
+* A workflow has a working directory in which all intermediate outputs go
+** These are named according to the rake task that created them
+
+h4. FileSystem
+
+Workflows are intended to run on filesystems. At the moment, implemented filesystems are
+
+* @file@ - Local file system. Only thoroughly tested on unbuntu linux.
+* @hdfs@ - Hadoop distributed file system. Uses jruby and the Apache Hadoop 0.20 api.
+* @s3@ - Uses the right_aws gem for interacting with Amazon Simple Storage System (s3).
+
+Using the filesystem:
+
+Paths should be absolute.
+
+<pre><code>
+# get a new instance of local filesystem and write to it
+localfs = FileSystem.get(:file)
+localfs.open("mylocalfile", 'w') do |f|
+  f.write("Writing a string to a local file")
+end
+
+# get a new instance of hadoop filesystem and write to it
+hadoopfs = FileSystem.get(:hdfs)
+hadoopfs.open("myhadoopfile", 'w') do |f|
+  f.write("Writing a string to an hdfs file")
+end
+
+# get a new instance of s3 filesystem and write to it
+access_key_id     = '1234abcd'
+secret_access_key = 'foobar1234'
+s3fs = FileSystem.get(:s3, accees_key_id, secret_access_key)
+s3fs.mkpath 'mys3bucket' # bucket must exist
+s3fs.open("mys3bucket/mys3file", 'w') do |f|
+  f.write("Writing a string to an s3 file")
+end
+</code></pre>
+
+h3. Working Example
+
+For the most up to date working example see the examples directory. Here's a simple example for running pagerank:
+
+<pre><code>
+#!/usr/bin/env ruby
+
+$LOAD_PATH << '../../lib'
+require 'swineherd'        ; include Swineherd
+require 'swineherd/script' ; include Swineherd::Script
+require 'swineherd/filesystem'
+
+Settings.define :flow_id,     :required => true,                     :description => "Flow id required to make run of workflow unique"
+Settings.define :iterations,  :type => Integer,  :default => 10,     :description => "Number of pagerank iterations to run"
+Settings.define :hadoop_home, :default => '/usr/local/share/hadoop', :description => "Path to hadoop config"
+Settings.resolve!
+
+flow = Workflow.new(Settings.flow_id) do
+
+  # The filesystems we're going to be working with
+  hdfs    = Swineherd::FileSystem.get(:hdfs)
+  localfs = Swineherd::FileSystem.get(:file)
+
+  # The scripts we're going to use
+  initializer = PigScript.new('scripts/pagerank_initialize.pig')
+  iterator    = PigScript.new('scripts/pagerank.pig')
+  finisher    = WukongScript.new('scripts/cut_off_list.rb')
+  plotter     = RScript.new('scripts/histogram.R')
+
+  #
+  # Runs simple pig script to initialize pagerank. We must specify the input
+  # here as this is the first step in the workflow. The output attribute is to
+  # ensure idempotency and the options attribute is the hash that will be
+  # converted into command-line args for the pig interpreter.
+  #
+  task :pagerank_initialize do
+    initializer.options = {:adjlist => "/tmp/pagerank_example/seinfeld_network.tsv", :initgrph => next_output(:pagerank_initialize)}
+    initializer.run(:hadoop) unless hdfs.exists? latest_output(:pagerank_initialize)
+  end
+
+  #
+  # Runs multiple iterations of pagerank with another pig script and manages all
+  # the intermediate outputs.
+  #
+  task :pagerank_iterate => [:pagerank_initialize] do
+    iterator.options[:damp]           = '0.85f'
+    iterator.options[:curr_iter_file] = latest_output(:pagerank_initialize)
+    Settings.iterations.times do
+      iterator.options[:next_iter_file] = next_output(:pagerank_iterate)
+      iterator.run(:hadoop) unless hdfs.exists? latest_output(:pagerank_iterate)
+      iterator.refresh!
+      iterator.options[:curr_iter_file] = latest_output(:pagerank_iterate)
+    end
+  end
+
+  #
+  # Here we use a wukong script to cut off the last field (a big pig bag of
+  # links). Notice how every wukong script MUST have an input but pig scripts do
+  # not.
+  #
+  task :cut_off_adjacency_list => [:pagerank_iterate] do
+    finisher.input  << latest_output(:pagerank_iterate)
+    finisher.output << next_output(:cut_off_adjacency_list)
+    finisher.run :hadoop unless hdfs.exists? latest_output(:cut_off_adjacency_list)
+  end
+
+  #
+  # We want to pull down one result file, merge the part-000.. files into one file
+  #
+  task :merge_results => [:cut_off_adjacency_list] do
+    merged_results = next_output(:merge_results)
+    hdfs.merge(latest_output(:cut_off_adjacency_list), merged_results) unless hdfs.exists? merged_results
+  end
+
+  #
+  # Cat results into a local directory with the same structure
+  # eg. #{work_dir}/#{flow_id}/pull_down_results-0.
+  #
+  # FIXME: Bridging filesystems is cludgey.
+  #
+  task :pull_down_results => [:merge_results] do
+    local_results = next_output(:pull_down_results)
+    hdfs.copy_to_local(latest_output(:merge_results), local_results) unless localfs.exists? local_results
+  end
+
+  #
+  # Plot 2nd column of the result as a histogram (requires R and
+  # ggplot2). Note that the output here is a png file but doesn't have that
+  # extension. Ensmarten me as to the right way to handle that?
+  #
+  task :plot_results =>  [:pull_down_results] do
+    plotter.attributes = {
+      :pagerank_data => latest_output(:pull_down_results),
+      :plot_file     => next_output(:plot_results), # <-- this will be a png...
+      :raw_rank      => "aes(x=d$V2)"
+    }
+    plotter.run(:local) unless localfs.exists? latest_output(:plot_results)
+  end
+
+end
+
+flow.workdir = "/tmp/pagerank_example"
+flow.describe
+flow.run(:plot_results)
+</code></pre>
+
+h3. Utils
+
+There's a fun little program to emphasize the ease of using the filesystem abstraction called 'hdp-tree':
+
+<pre><code>
+$: bin/hdp-tree /tmp/my_hdfs_directory
+--- 
+/tmp/my_hdfs_directory: 
+  - my_hdfs_directory: 
+      - sub_dir_a: leaf_file_1
+      - sub_dir_a: leaf_file_2
+      - sub_dir_a: leaf_file_3
+  - my_hdfs_directory: 
+      - sub_dir_b: leaf_file_1
+      - sub_dir_b: leaf_file_2
+      - sub_dir_b: leaf_file_3
+  - my_hdfs_directory: 
+      - sub_dir_c: leaf_file_1
+      - sub_dir_c: leaf_file_2
+      - sub_dir_c: leaf_file_3
+      - sub_dir_c: 
+          - sub_sub_dir_a: yet_another_leaf_file
+      - sub_dir_c: sub_sub_dir_b
+      - sub_dir_c: sub_sub_dir_c
+</code></pre>
+
+I know, it's not as pretty as unix tree, but this IS github...
+
+h3. TODO
+
+* next task in a workflow should NOT run if the previous step failed
+** this is made difficult by the fact that, sometimes?, when a pig script fails it still returns a 0 exit status
+** same for wukong scripts
+* add a @job@ object that implements a @not_if@ function. this way a @workflow@ will be constructed of @job@ objects
+** a @job@ will do nothing more than execute the ruby code in it's (run?) block, unless @not_if@ is true
+** this way we can put @script@ objects inside a @job@ and only run under certain conditions that the user specifies when
+   they create the @job@
+* implement ftp filesystem interfaces

data/Rakefile

@@ -0,0 +1,30 @@
+require 'rubygems'
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "swineherd"
+  gem.homepage = "http://github.com/Ganglion/swineherd"
+  gem.license = "MIT"
+  gem.summary = %Q{Flexible data workflow glue.}
+  gem.description = %Q{Swineherd is for running scripts and workflows on filesystems.}
+  gem.email = "jacob.a.perkins@gmail.com"
+  gem.authors = ["Jacob Perkins"]
+  # Include your dependencies below. Runtime dependencies are required when using your gem,
+  # and development dependencies are only needed for development (ie running rake tasks, tests, etc)
+  #  gem.add_runtime_dependency 'jabber4r', '> 0.1'
+  #  gem.add_development_dependency 'rspec', '> 1.2.3'
+  gem.add_development_dependency "yard", "~> 0.6.0"
+  gem.add_development_dependency "jeweler", "~> 1.5.2"
+  gem.add_development_dependency "rcov", ">= 0"
+  gem.add_dependency 'configliere'
+  gem.add_dependency 'gorillib'
+  gem.add_dependency 'erubis'
+  gem.add_dependency 'right_aws'
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+
+require 'yard'
+YARD::Rake::YardocTask.new

data/VERSION

@@ -0,0 +1 @@
+0.0.1

data/bin/hadoop-stream

@@ -0,0 +1,35 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'rake'
+require 'swineherd' ; include Swineherd
+
+#
+# Uses hadoop and rake's multitask capability to stream many source
+# files in parallel into a single destination directory.
+#
+
+Settings.define :input, :type => Array, :required => true, :description => "Comma spearated list of directories (hdfs paths, s3 paths, etc) to stream"
+Settings.define :output,                :required => true, :description => "Destination directory (s3 or hdfs)"
+Settings.resolve!
+
+#
+# Takes a hash of paths eg: {'filename' => 'full path'} and defines
+# a new streaming task for each one
+#
+def define_tasks list_of_tasks
+  list_of_tasks.each do |basename, source|
+    task basename do
+      destination = File.join(Settings.output, basename) # each file gets its own output
+      HDFS.stream(source, destination)
+    end
+  end
+end
+
+# Create a list of tasks, one per file
+list_of_tasks = Settings.input.inject({}){|list, path| list[File.basename(path)] = path; list}
+define_tasks list_of_tasks
+
+multitask :stream_all => list_of_tasks.keys
+
+Rake::MultiTask["stream_all"].invoke