biodiversity19 1.0.6 → 1.0.7

data/.rvmrc

@@ -1 +1 @@
-rvm use ruby-1.9.2-p290@biodiversity--create
+rvm use ruby-1.9.2-p290@biodiversity --create

data/Gemfile

@@ -1,10 +1,12 @@
 source "http://rubygems.org"
 
-gem "jeweler"
 gem "treetop"
-gem "facter"
 gem "parallel"
 
+group :development do
+  gem "jeweler"
+end
+
 group :test do
   gem "ruby-debug19", :require => "ruby-debug"
   gem "rspec"

data/Gemfile.lock

@@ -4,7 +4,6 @@ GEM
     archive-tar-minitar (0.5.2)
     columnize (0.3.4)
     diff-lcs (1.1.3)
-    facter (1.6.3)
     git (1.2.5)
     jeweler (1.6.4)
       bundler (~> 1.0)
@@ -41,7 +40,6 @@ PLATFORMS
   ruby
 
 DEPENDENCIES
-  facter
   jeweler
   parallel
   rspec

data/README.rdoc

@@ -85,6 +85,11 @@ You can use it as a library
   # to get detailed information about elements of the name
   parser.parse("Pseudocercospora dendrobii (H.C. Burnett 1883) U. Braun & Crous 2003")[:scientificName][:details]
 
+  # to parse using several CPUs (4 seem to be optimal)
+  parser = ParallelParser.new # ParallelParser.new(4) will try to run 4 processes if hardware allows
+  array_of_names = ["Betula alba", "Homo sapiens"....]
+  parser.parse(array_of_names) # -> {"Betula alba" => "{scientificName...}", "Homo sapiens" => "{scientificName...}", ...}
+
   # to resolve lsid and get back RDF file
   LsidResolver.resolve("urn:lsid:ubio.org:classificationbank:2232671")
 

data/Rakefile

@@ -30,6 +30,7 @@ begin
     gem.bindir = 'bin'
     gem.executables = ['nnparse', 'parserver']
     gem.add_dependency('treetop')
+    gem.add_dependency('parallel')
     gem.add_dependency('json') if ruby_version < 19
     gem.add_development_dependency "rspec"
     # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings

data/VERSION

@@ -1 +1 @@
-1.0.6
+1.0.7

data/lib/biodiversity/parser.rb

@@ -25,11 +25,14 @@ end
 
 class ParallelParser
 
-  def initialize
-    require 'facter'
+  def initialize(processes_num = nil)
     require 'parallel'
     cpu_num
-    @processes_num = cpu_num > 1 ? cpu_num - 1 : 1
+    if processes_num.to_i > 0
+      @processes_num = [processes_num, cpu_num - 1].min
+    else
+      @processes_num = cpu_num > 3 ? cpu_num - 2 : 1
+    end
   end
 
   def parse(names_list)
@@ -38,7 +41,7 @@ class ParallelParser
   end
 
   def cpu_num
-    @cpu_num ||= Facter.processorcount.to_i
+    @cpu_num ||= Parallel.processor_count
   end
 
   private

data/spec/parser/scientific_name.spec.rb

@@ -61,4 +61,13 @@ describe ParallelParser do
     res.keys.size.should == names.size
   end
 
+  it "should parse several names in parallel with given num of processes" do
+    names = []
+    read_test_file { |n| names << (n[:name]) if n[:name] }
+    names.uniq!
+    pparser = ParallelParser.new(4)
+    res = pparser.parse(names)
+    names.size.should > 100
+    res.keys.size.should == names.size
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: biodiversity19
 version: !ruby/object:Gem::Version
-  version: 1.0.6
+  version: 1.0.7
   prerelease: 
 platform: ruby
 authors:
@@ -12,8 +12,8 @@ cert_chain: []
 date: 2011-11-17 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: jeweler
-  requirement: &70228377889480 !ruby/object:Gem::Requirement
+  name: treetop
+  requirement: &70293221558620 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70228377889480
+  version_requirements: *70293221558620
 - !ruby/object:Gem::Dependency
-  name: treetop
-  requirement: &70228377827560 !ruby/object:Gem::Requirement
+  name: parallel
+  requirement: &70293221558140 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,21 +32,21 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70228377827560
+  version_requirements: *70293221558140
 - !ruby/object:Gem::Dependency
-  name: facter
-  requirement: &70228377827080 !ruby/object:Gem::Requirement
+  name: jeweler
+  requirement: &70293221557660 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
+  type: :development
   prerelease: false
-  version_requirements: *70228377827080
+  version_requirements: *70293221557660
 - !ruby/object:Gem::Dependency
-  name: parallel
-  requirement: &70228377826600 !ruby/object:Gem::Requirement
+  name: treetop
+  requirement: &70293221557180 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,10 +54,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70228377826600
+  version_requirements: *70293221557180
 - !ruby/object:Gem::Dependency
-  name: treetop
-  requirement: &70228377826120 !ruby/object:Gem::Requirement
+  name: parallel
+  requirement: &70293221556700 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -65,10 +65,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70228377826120
+  version_requirements: *70293221556700
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &70228377825640 !ruby/object:Gem::Requirement
+  requirement: &70293221556220 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -76,7 +76,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70228377825640
+  version_requirements: *70293221556220
 description: Tools for biodiversity informatics
 email: dmozzherin@gmail.com
 executables: