swineherd 0.0.4 → 0.0.6

data/VERSION

@@ -1 +1 @@
-0.0.4
+0.0.6

data/lib/swineherd/filesystem/hadoopfilesystem.rb

@@ -14,10 +14,12 @@ module Swineherd
     #
     # Initialize a new hadoop file system, needs path to hadoop configuration
     #
-    def initialize *args
+    def initialize params={}, *args
       check_and_set_environment
       @conf = Java::org.apache.hadoop.conf.Configuration.new
-      @hdfs = Java::org.apache.hadoop.fs.FileSystem.get(@conf)
+      uri = Java::java.net.URI.new params[:filesystem] if params[:filesystem]
+      fs_params = uri ? [ uri, @conf ] : [ @conf ]
+      @hdfs = Java::org.apache.hadoop.fs.FileSystem.get *fs_params
     end
 
     #

data/lib/swineherd/script.rb

@@ -56,17 +56,13 @@ module Swineherd
       # Default is to run with hadoop
       #
       def run mode=:hadoop
-        case mode
-        when :local then
-          sh local_cmd do |res, ok|
-            Log.info("Exit status was #{ok}")
-            raise "Local mode script failed with exit status #{ok}" if ok != 0
-          end
-        when :hadoop then
-          sh cmd do |res, ok|
-            Log.info("Exit status was #{ok}")
-            raise "Hadoop mode script failed with exit status #{ok}" if ok != 0
-          end
+        command = case mode
+        when :local then local_cmd
+        when :hadoop then cmd
+        end
+
+        sh command do |ok, status|
+          ok or raise "#{mode.to_s.capitalize} mode script failed with exit status #{status}"
         end
       end
 

data/swineherd.gemspec

@@ -5,13 +5,13 @@
 
 Gem::Specification.new do |s|
   s.name = %q{swineherd}
-  s.version = "0.0.4"
+  s.version = "0.0.6"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = ["Jacob Perkins"]
-  s.date = %q{2011-06-22}
+  s.authors = ["Jacob Perkins","Infochimps"]
+  s.date = %q{2011-10-05}
   s.description = %q{Swineherd is for running scripts and workflows on filesystems.}
-  s.email = %q{jacob.a.perkins@gmail.com}
+  s.email = ["jacob.a.perkins@gmail.com","coders@infochimps.com"]
   s.executables = ["hdp-tree", "hadoop-stream"]
   s.extra_rdoc_files = [
     "LICENSE",
@@ -60,7 +60,6 @@ Gem::Specification.new do |s|
   s.summary = %q{Flexible data workflow glue.}
 
   if s.respond_to? :specification_version then
-    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
     s.specification_version = 3
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then

data/tests/testcfg.yaml

@@ -3,5 +3,5 @@ filesystem_to_test: file
 s3_test_bucket: infochimps-test
 
 # :) you'll probably want to change these
-aws_access_key_id: myaccessid
-aws_secret_access_key: 1234mysecretaccesskey8q7fh
+aws_access_key_id: 02S6Y1EFA7ZZ7KCZH3G2
+aws_secret_access_key: mY13mL7/iXA+gjzNJ8O95LukPQgsWjyXqVizX6zB

metadata

@@ -1,21 +1,17 @@
 --- !ruby/object:Gem::Specification 
 name: swineherd
 version: !ruby/object:Gem::Version 
-  hash: 23
-  prerelease: false
-  segments: 
-  - 0
-  - 0
-  - 4
-  version: 0.0.4
+  prerelease: 
+  version: 0.0.6
 platform: ruby
 authors: 
 - Jacob Perkins
+- Infochimps
 autorequire: 
 bindir: bin
 cert_chain: []
 
-date: 2011-06-22 00:00:00 -05:00
+date: 2011-10-05 00:00:00 -05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -26,11 +22,6 @@ dependencies:
     requirements: 
     - - ~>
       - !ruby/object:Gem::Version 
-        hash: 7
-        segments: 
-        - 0
-        - 6
-        - 0
         version: 0.6.0
   type: :development
   version_requirements: *id001
@@ -42,11 +33,6 @@ dependencies:
     requirements: 
     - - ~>
       - !ruby/object:Gem::Version 
-        hash: 7
-        segments: 
-        - 1
-        - 5
-        - 2
         version: 1.5.2
   type: :development
   version_requirements: *id002
@@ -58,9 +44,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
         version: "0"
   type: :development
   version_requirements: *id003
@@ -72,9 +55,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
         version: "0"
   type: :runtime
   version_requirements: *id004
@@ -86,9 +66,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
         version: "0"
   type: :runtime
   version_requirements: *id005
@@ -100,9 +77,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
         version: "0"
   type: :runtime
   version_requirements: *id006
@@ -114,14 +88,13 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
         version: "0"
   type: :runtime
   version_requirements: *id007
 description: Swineherd is for running scripts and workflows on filesystems.
-email: jacob.a.perkins@gmail.com
+email: 
+- jacob.a.perkins@gmail.com
+- coders@infochimps.com
 executables: 
 - hdp-tree
 - hadoop-stream
@@ -179,23 +152,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
   none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
       version: "0"
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: Flexible data workflow glue.