learn_mapreduce 0.1.0

data/lib/learn_mapreduce.rb

@@ -0,0 +1,72 @@
+# Small Framwork to learn MapReduce
+class MapReduce
+   def initialize
+      @mapper = nil
+      @reducer = nil
+   end
+   
+   # Call this function with a block to set the mapper function
+   # The mapper takes a record as argument
+   def map &mapper
+      @mapper = mapper
+   end
+   
+   # Call this function with a block to set the reducer function
+   # The reducer takes a key and a list of values as arguments
+   def reduce &reducer
+      @reducer = reducer
+   end
+   
+   # Run a MapReduce algorithm on the data provided
+   # Returns a hash containing the emitted tuples, the shuffled tuples and the output
+   def run data
+      throw "Mapper missing!" unless @mapper
+      throw "Reducer missing!" unless @reducer
+      
+      map_context = MapContext.new
+      data.each { |record|
+         map_context.instance_exec(record, &@mapper)
+      }
+
+      reduce_context = ReduceContext.new
+      map_context.shuffled.each { |key, list_of_values|
+         reduce_context.instance_exec(key, list_of_values, &@reducer)
+      }
+
+      return [
+         map_context.emitted,
+         map_context.shuffled,
+         reduce_context.output
+      ]
+   end
+end
+
+# The context within the mapper
+# Used to give a custom 'emit' function
+class MapContext
+   attr_accessor :emitted, :shuffled
+   
+   def initialize
+      @emitted = []
+      @shuffled = {}
+   end
+   
+   def emit key, value
+      @emitted.push([key, value])
+      (@shuffled[key] ||= []).push(value)
+   end
+end
+
+# The context within the reducer
+# Used to give a custom 'emit' function
+class ReduceContext
+   attr_accessor :output
+   
+   def initialize
+      @output = []
+   end
+   
+   def emit value
+      @output.push(value)
+   end
+end

metadata

@@ -0,0 +1,45 @@
+--- !ruby/object:Gem::Specification
+name: learn_mapreduce
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+  prerelease: 
+platform: ruby
+authors:
+- Aegis
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-05-28 00:00:00.000000000 Z
+dependencies: []
+description: A tiny implementation of the MapReduce Framework for learning purposes!
+email: 
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/learn_mapreduce.rb
+homepage: 
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: Tiny implementation of the MapReduce Framework.
+test_files: []