humboldt 1.0.2-java → 1.0.3-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 37a2d3fc7a3bc35d2da684d3359c9299da39b155
-  data.tar.gz: abbfab2107a18d0f4fa5e5d6ef9934d2d2d81028
+  metadata.gz: ad7d9161131ab93f3ee98a2a22a730bf6af82d9a
+  data.tar.gz: ee3f4f283aa281be60b55ecc9b6c169743d87998
 SHA512:
-  metadata.gz: 759cd4c0de2cd31a22019b6358fcb36dd26636d40dcc6766b78cd21d68a2f8894382cd7dcc177d996a7fea6506fb2a88d39ebe5b79036c542519cbd5ed82c3e9
-  data.tar.gz: af8dea70e46df9fa5a8526ebe9d2b7db44c189b61e89c29bbd895d1190a42dbfa1ad92e024be7f9f2eb6dd93a81f2a1f7f9a44a5e50d5293270efae18c94f718
+  metadata.gz: 19ccf74a3524748dcea4b24b026f7870a4785d8e6ff18cc661cde2136ab3c955f8f2bd37fb5f4b85b292bbe1961d8464b07f679fc0c3ed263eba8cb5b3fd218b
+  data.tar.gz: 93bc3287a0859e02d380d66fb920fc3c48fd02697411c49468da63b86a5b94a381104408667a5cf18915928a3d7ee359e4a836ab9846c5520b30c9292a19b93c

data/lib/humboldt/type_converters.rb

@@ -5,31 +5,6 @@ module Humboldt
     class Binary
       HADOOP = ::Hadoop::Io::BytesWritable
       RUBY = ::String
-
-      attr_reader :hadoop
-
-      def hadoop=(value)
-        unless value.is_a?(HADOOP)
-          raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{HADOOP}"
-        end
-        @hadoop = value
-      end
-
-      def initialize
-        @hadoop = HADOOP.new
-      end
-
-      def ruby
-        String.from_java_bytes(@hadoop.bytes).byteslice(0, @hadoop.length)
-      end
-
-      def ruby=(value)
-        unless value.is_a?(RUBY)
-          raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{RUBY}"
-        end
-
-        @hadoop.set(value.to_java_bytes, 0, value.bytesize)
-      end
     end
 
     begin
@@ -40,13 +15,11 @@ module Humboldt
           unless value.is_a?(Hash) || value.is_a?(Array)
             raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected Hash or Array"
           end
-          packed = MessagePack.pack(value)
-          @hadoop.set(packed.to_java_bytes, 0, packed.bytesize)
+          super(MessagePack.pack(value))
         end
 
         def ruby
-          packed = String.from_java_bytes(@hadoop.bytes).byteslice(0, @hadoop.length)
-          MessagePack.unpack(packed, encoding: Encoding::UTF_8)
+          MessagePack.unpack(super(), encoding: Encoding::UTF_8)
         end
       end
     rescue LoadError
@@ -55,35 +28,6 @@ module Humboldt
     class Text
       HADOOP = ::Hadoop::Io::Text
       RUBY = ::String
-
-      attr_reader :hadoop
-
-      def hadoop=(value)
-        unless value.is_a?(HADOOP)
-          raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{HADOOP}"
-        end
-        @hadoop = value
-      end
-
-      def initialize
-        @hadoop = HADOOP.new
-      end
-
-      def ruby
-        String.from_java_bytes(@hadoop.bytes).byteslice(0, @hadoop.length).force_encoding(Encoding::UTF_8)
-      end
-
-      def ruby=(value)
-        unless value.is_a?(RUBY)
-          raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{RUBY}"
-        end
-
-        if value.encoding == Encoding::UTF_8
-          @hadoop.set(value.to_java_bytes, 0, value.bytesize)
-        else
-          @hadoop.set(value)
-        end
-      end
     end
 
     begin
@@ -94,11 +38,11 @@ module Humboldt
           unless value.is_a?(Hash) || value.is_a?(Array)
             raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected Hash or Array"
           end
-          @hadoop.set(JSON.generate(value))
+          super(JSON.generate(value))
         end
 
         def ruby
-          JSON.parse(hadoop.to_s)
+          JSON.parse(super())
         end
       end
     end
@@ -106,56 +50,11 @@ module Humboldt
     class Long
       HADOOP = ::Hadoop::Io::LongWritable
       RUBY = ::Integer
-
-      attr_reader :hadoop
-
-      def hadoop=(value)
-        unless value.is_a?(HADOOP)
-          raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{HADOOP}"
-        end
-        @hadoop = value
-      end
-
-      def initialize
-        @hadoop = HADOOP.new
-      end
-
-      def ruby
-        @hadoop.get
-      end
-
-      def ruby=(value)
-        unless value.is_a?(Integer)
-          raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{RUBY}"
-        end
-
-        @hadoop.set value
-      end
     end
 
     class None
       HADOOP = ::Hadoop::Io::NullWritable
       RUBY = ::NilClass
-
-      def hadoop
-        HADOOP.get
-      end
-
-      def hadoop=(value)
-        unless value.is_a?(HADOOP)
-          raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{HADOOP}"
-        end
-      end
-
-      def ruby
-        nil
-      end
-
-      def ruby=(value)
-        unless value.nil?
-          raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{RUBY}"
-        end
-      end
     end
 
     TYPE_CONVERTER_CLASS_CACHE = Hash.new { |h,k| h[k] = const_get(k.to_s.capitalize) }

data/lib/humboldt/version.rb

@@ -1,5 +1,5 @@
 # encoding: utf-8
 
 module Humboldt
-  VERSION = '1.0.2'.freeze
+  VERSION = '1.0.3'.freeze
 end

data/lib/humboldt.rb

@@ -4,6 +4,9 @@ require 'fileutils'
 require 'rubydoop'
 require 'hadoop'
 
+$CLASSPATH << File.expand_path('../humboldt.jar', __FILE__)
+Java::Humboldt::HumboldtLibrary.new.load(JRuby.runtime, false)
+
 require 'humboldt/java_lib'
 
 require 'ext/hadoop'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: humboldt
 version: !ruby/object:Gem::Version
-  version: 1.0.2
+  version: 1.0.3
 platform: java
 authors:
 - The Burt Platform Team
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2015-04-02 00:00:00.000000000 Z
+date: 2015-05-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
@@ -66,25 +66,25 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
-- lib/humboldt.rb
+- bin/humboldt
+- config/emr-bootstrap/remove_old_jruby.sh
+- config/hadoop-local.xml
 - lib/ext/hadoop.rb
 - lib/ext/rubydoop.rb
+- lib/humboldt.jar
+- lib/humboldt.rb
 - lib/humboldt/cli.rb
 - lib/humboldt/emr_flow.rb
 - lib/humboldt/hadoop_status_filter.rb
 - lib/humboldt/java_lib.rb
 - lib/humboldt/mapper.rb
+- lib/humboldt/patterns/sum_reducer.rb
 - lib/humboldt/prefix_grouping.rb
 - lib/humboldt/processor.rb
 - lib/humboldt/reducer.rb
 - lib/humboldt/rspec.rb
 - lib/humboldt/type_converters.rb
 - lib/humboldt/version.rb
-- lib/humboldt/patterns/sum_reducer.rb
-- lib/humboldt.jar
-- bin/humboldt
-- config/hadoop-local.xml
-- config/emr-bootstrap/remove_old_jruby.sh
 homepage: http://github.com/burtcorp/humboldt
 licenses:
 - BSD-3-Clause
@@ -105,7 +105,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project:
-rubygems_version: 2.1.9
+rubygems_version: 2.4.5
 signing_key:
 specification_version: 4
 summary: Tools and libraries for simplifying running Rubydoop jobs locally and on AWS Elastic MapReduce