bio-gff3 0.8.7 → 0.9.0

data/.travis.yml

@@ -0,0 +1,12 @@
+language: ruby
+rvm:
+  - 1.8.7
+  - 1.9.2
+  - 1.9.3
+#   - jruby-19mode # JRuby in 1.9 mode
+  - rbx-19mode
+#  - jruby-18mode # JRuby in 1.8 mode
+#  - rbx-18mode
+
+# uncomment this line if your project needs to run something other than `rake`:
+# script: bundle exec rspec spec

data/Gemfile

@@ -9,8 +9,8 @@ gem "bio-logger", "> 0.8.0"
 # Include everything needed to run rake, tests, features, etc.
 group :development do
   gem "shoulda", ">= 0"
-  gem "bundler", "~> 1.0.0"
-  gem "jeweler", "~> 1.5.2"
-  gem "rcov", ">= 0"
-  gem "rspec", ">= 2.3.0"
+  gem "bundler", "~> 1.1.5"
+  gem "jeweler", "~> 1.8.3"
+  gem "rspec", ">= 2.10.0"
+  gem "regressiontest"
 end

data/Gemfile.lock

@@ -1,27 +1,41 @@
 GEM
   remote: http://rubygems.org/
   specs:
-    bio (1.4.1)
+    activesupport (3.2.7)
+      i18n (~> 0.6)
+      multi_json (~> 1.0)
+    bio (1.4.2)
     bio-logger (1.0.0)
       log4r (>= 1.1.9)
-    diff-lcs (1.1.2)
+    diff-lcs (1.1.3)
     git (1.2.5)
-    jeweler (1.5.2)
-      bundler (~> 1.0.0)
+    i18n (0.6.0)
+    jeweler (1.8.4)
+      bundler (~> 1.0)
       git (>= 1.2.5)
       rake
-    log4r (1.1.9)
-    rake (0.9.2)
-    rcov (0.9.9)
-    rspec (2.6.0)
-      rspec-core (~> 2.6.0)
-      rspec-expectations (~> 2.6.0)
-      rspec-mocks (~> 2.6.0)
-    rspec-core (2.6.4)
-    rspec-expectations (2.6.0)
-      diff-lcs (~> 1.1.2)
-    rspec-mocks (2.6.0)
-    shoulda (2.11.3)
+      rdoc
+    json (1.7.4)
+    log4r (1.1.10)
+    multi_json (1.3.6)
+    rake (0.9.2.2)
+    rdoc (3.12)
+      json (~> 1.4)
+    regressiontest (0.0.1)
+    rspec (2.10.0)
+      rspec-core (~> 2.10.0)
+      rspec-expectations (~> 2.10.0)
+      rspec-mocks (~> 2.10.0)
+    rspec-core (2.10.1)
+    rspec-expectations (2.10.0)
+      diff-lcs (~> 1.1.3)
+    rspec-mocks (2.10.1)
+    shoulda (3.1.1)
+      shoulda-context (~> 1.0)
+      shoulda-matchers (~> 1.2)
+    shoulda-context (1.0.0)
+    shoulda-matchers (1.2.0)
+      activesupport (>= 3.0.0)
 
 PLATFORMS
   ruby
@@ -29,9 +43,9 @@ PLATFORMS
 DEPENDENCIES
   bio (>= 1.3.1)
   bio-logger (> 0.8.0)
-  bundler (~> 1.0.0)
-  jeweler (~> 1.5.2)
+  bundler (~> 1.1.5)
+  jeweler (~> 1.8.3)
   log4r (> 1.1.6)
-  rcov
-  rspec (>= 2.3.0)
+  regressiontest
+  rspec (>= 2.10.0)
   shoulda

data/README.rdoc

@@ -1,3 +1,9 @@
+{<img
+src="https://secure.travis-ci.org/pjotrp/bioruby-gff3-plugin.png"
+/>}[http://travis-ci.org/#!/pjotrp/bioruby-gff3-plugin]
+
+bio-gff3 is listed at http://biogems.info
+
 = bio-gff3
 
 GFF3 parser, aimed at parsing big data GFF3 to return sequences of any type, 
@@ -15,7 +21,8 @@ Currently the output is a FASTA file.
 You can use this plugin in two ways. First as a standalone program,
 second as a plugin library to BioRuby.
 
-Note: a really fast GFF3 parser is in the works at https://github.com/pjotrp/biolib_hpc/tree/master/modules/gff3
+Note: a really fast GFF3 parser, and way more flexible, is in the
+works. See https://github.com/mamarjan/gff3-pltools.
 
 == Install and run gff3-fetch
 
@@ -55,13 +62,9 @@ For a write-up see http://thebird.nl/bioruby/BioRuby_GFF3.html
 
 -------------------------------------------------------------------------------
 
-== Copyright
-
-Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl> 
-
+= Command line usage (CLI)
 
-
-  Fetch and assemble GFF3 types (e.g. ORF, mRNA, CDS) + print in FASTA format. 
+  Fetch and assemble GFF3 types (ORF, mRNA, CDS) + print in FASTA format. 
 
     gff3-fetch [options] type [filename.fa] filename.gff3
 
@@ -94,10 +97,10 @@ Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>
   Where (NYI == Not Yet Implemented):
 
   Multiple GFF3 files can be used. With external FASTA files, always the last
-  one before the GFF3 filename is matched.
+  one before the GFF3 filename is matched. Make sure the FASTA file
+  comes before the GFF3 file on the command line.
 
-  Note that above switches are only partially implemented at this stage. Full
-  feature support is projected Feb. 2011.
+  Note that above switches are only partially implemented at this stage.
 
   Examples:
 
@@ -164,8 +167,7 @@ time gff3-fetch cds m_hapla.WS217.dna.fa m_hapla.WS217.gff3 2> /dev/null > test.
 
   Cache              real     user     sys  gff3 version
   ------------------------------------------------------------
-  in preparation see also biolib/HPC:
-    https://github.com/pjotrp/biolib_hpc/tree/master/modules/gff3
+  in preparation
   ------------------------------------------------------------
 
 where
@@ -176,13 +178,20 @@ where
 ruby 1.9.2p136 (2010-12-25 revision 30365) [x86_64-linux]
 on an 8 CPU, 2.6 GHz (6MB cache), 16 GB RAM machine. 
 
+Note: the new parser by Marjan is magnitudes faster, and way more
+flexible. See https://github.com/mamarjan/gff3-pltools
+
 == Cite
 
   If you use this software, please cite 
   
+    http://dx.doi.org/10.1093/bioinformatics/bts080
+
+  or
+
     http://dx.doi.org/10.1093/bioinformatics/btq475
 
 == Copyright
 
-Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl> 
+Copyright (C) 2010-2012 Pjotr Prins <pjotr.prins@thebird.nl>
 

data/Rakefile

@@ -1,12 +1,12 @@
 require 'rubygems'
-# require 'bundler'
-# begin
-#   Bundler.setup(:default, :development)
-# rescue Bundler::BundlerError => e
-#   $stderr.puts e.message
-#   $stderr.puts "Run `bundle install` to install missing gems"
-#   exit e.status_code
-# end
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
 require 'rake'
 
 require 'jeweler'
@@ -33,7 +33,8 @@ Jeweler::RubygemsDotOrgTasks.new
 require 'rake/testtask'
 Rake::TestTask.new(:test) do |test|
   test.libs << 'lib' << 'test'
-  test.pattern = 'test/**/test_*.rb'
+  # test.pattern = 'test/**/test_*.rb'  # breaks in 1.9.3
+  test.test_files = Dir.glob("test/**/test_*.rb")
   test.verbose = true
   Kernel.system('rspec spec/*.rb')
 end
@@ -47,21 +48,21 @@ end
 #end
 
 
-require 'rcov/rcovtask'
-Rcov::RcovTask.new do |test|
-  test.libs << 'test'
-  test.pattern = 'test/**/test_*.rb'
-  test.verbose = true
-end
+# require 'rcov/rcovtask'
+# Rcov::RcovTask.new do |test|
+#   test.libs << 'test'
+#   test.pattern = 'test/**/test_*.rb'
+#   test.verbose = true
+# end
 
 task :default => :test
 
-require 'rake/rdoctask'
-Rake::RDocTask.new do |rdoc|
-  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+# require 'rake/rdoctask'
+# Rake::RDocTask.new do |rdoc|
+#   version = File.exist?('VERSION') ? File.read('VERSION') : ""
 
-  rdoc.rdoc_dir = 'rdoc'
-  rdoc.title = "bio-gff3 #{version}"
-  rdoc.rdoc_files.include('README*')
-  rdoc.rdoc_files.include('lib/**/*.rb')
-end
+#  rdoc.rdoc_dir = 'rdoc'
+#   rdoc.title = "bio-gff3 #{version}"
+#  rdoc.rdoc_files.include('README*')
+#  rdoc.rdoc_files.include('lib/**/*.rb')
+# end

data/VERSION

@@ -1 +1 @@
-0.8.7
+0.9.0

data/bin/gff3-fetch

@@ -1,14 +1,13 @@
-#! /usr/bin/ruby
+#! /usr/bin/env ruby
 #
 # Author:: Pjotr Prins
-# Copyright:: August 2010
 # License:: Ruby License
-#
-# Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>
+
+COPYRIGHT = "Copyright (C) 2010-2012 Pjotr Prins <pjotr.prins@thebird.nl>"
 
 USAGE = <<EOM
 
-  Fetch and assemble GFF3 types (e.g. ORF, mRNA, CDS) + print in FASTA format. 
+  Fetch and assemble GFF3 types (ORF, mRNA, CDS) + print in FASTA format. 
 
     gff3-fetch [options] type [filename.fa] filename.gff3
 
@@ -41,10 +40,10 @@ USAGE = <<EOM
   Where (NYI == Not Yet Implemented):
 
   Multiple GFF3 files can be used. With external FASTA files, always the last
-  one before the GFF3 filename is matched.
+  one before the GFF3 filename is matched. Make sure the FASTA file
+  comes before the GFF3 file on the command line.
 
-  Note that above switches are only partially implemented at this stage. Full
-  feature support is projected Feb. 2011.
+  Note that above switches are only partially implemented at this stage.
 
   Examples:
 
@@ -126,11 +125,15 @@ on an 8 CPU, 2.6 GHz (6MB cache), 16 GB RAM machine.
 
   If you use this software, please cite 
   
+    http://dx.doi.org/10.1093/bioinformatics/bts080
+
+  or
+
     http://dx.doi.org/10.1093/bioinformatics/btq475
 
 == Copyright
 
-Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl> 
+#{COPYRIGHT}
 
 EOM
 
@@ -144,7 +147,7 @@ require 'optparse'
 require 'ostruct'
 require 'bio/output/gfffastawriter'
 
-$stderr.print "BioRuby GFF3 Plugin "+GFF3_VERSION+" Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>\n\n"
+$stderr.print "gff3-fetch (biogem Ruby #{RUBY_VERSION}) "+GFF3_VERSION+" "+COPYRIGHT+"\n\n"
 
 if ARGV.size == 0
   print USAGE
@@ -158,7 +161,7 @@ options = OpenStruct.new()
 # ---- Default options
 options.parser = :line
 
-opts = OptionParser.new() { |opts|
+opts2 = OptionParser.new() { |opts|
   opts.on_tail("-h", "--help", "Show help and examples") {
     print(opts)
     print USAGE
@@ -239,6 +242,7 @@ opts = OptionParser.new() { |opts|
   end
 
  }
+opts = opts2
 opts.parse!(ARGV)
 
 Bio::Log::CLI.configure('bio-gff3')

data/bio-gff3.gemspec

@@ -4,23 +4,21 @@
 # -*- encoding: utf-8 -*-
 
 Gem::Specification.new do |s|
-  s.name = %q{bio-gff3}
-  s.version = "0.8.7"
+  s.name = "bio-gff3"
+  s.version = "0.9.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = [%q{Pjotr Prins}]
-  s.date = %q{2011-07-31}
-  s.description = %q{GFF3 (genome browser) information and digest mRNA and CDS sequences.
-Options for low memory use and caching of records.
-Support for external FASTA files.
-}
-  s.email = %q{pjotr.prins@thebird.nl}
-  s.executables = [%q{gff3-fetch}]
+  s.authors = ["Pjotr Prins"]
+  s.date = "2012-08-20"
+  s.description = "GFF3 (genome browser) information and digest mRNA and CDS sequences.\nOptions for low memory use and caching of records.\nSupport for external FASTA files.\n"
+  s.email = "pjotr.prins@thebird.nl"
+  s.executables = ["gff3-fetch"]
   s.extra_rdoc_files = [
     "LICENSE.txt",
     "README.rdoc"
   ]
   s.files = [
+    ".travis.yml",
     "Gemfile",
     "Gemfile.lock",
     "LICENSE.txt",
@@ -59,6 +57,8 @@ Support for external FASTA files.
     "test/data/gff/MhA1_Contig1133.gff3",
     "test/data/gff/MhA1_Contig125.fa",
     "test/data/gff/MhA1_Contig125.gff3",
+    "test/data/gff/m_hapla.WS232.annotations.part.gff3",
+    "test/data/gff/m_hapla.WS232.genomic.part.fa",
     "test/data/gff/standard.gff3",
     "test/data/gff/test-cds.gff3",
     "test/data/gff/test-ext-fasta.fa",
@@ -66,30 +66,21 @@ Support for external FASTA files.
     "test/data/gff/test.gff3",
     "test/data/regression/test_ext_gff3.rtest",
     "test/data/regression/test_gff3.rtest",
+    "test/data/regression/test_latest_wormbase_ext_gff3.ref",
+    "test/data/regression/test_latest_wormbase_ext_gff3.rtest",
     "test/data/regression/test_lrucache_ext_gff3.rtest",
     "test/data/regression/test_lrucache_gff3.rtest",
     "test/data/regression/test_nocache_ext_gff3.rtest",
     "test/data/regression/test_nocache_gff3.rtest",
     "test/helper.rb",
-    "test/regressiontest.rb",
-    "test/test_bio-gff3.rb"
-  ]
-  s.homepage = %q{https://github.com/pjotrp/bioruby-gff3-plugin}
-  s.licenses = [%q{MIT}]
-  s.require_paths = [%q{lib}]
-  s.rubygems_version = %q{1.8.6}
-  s.summary = %q{GFF3 parser for big data}
-  s.test_files = [
-    "spec/gff3_assemble2_spec.rb",
-    "spec/gff3_assemble3_spec.rb",
-    "spec/gff3_assemble_spec.rb",
-    "spec/gff3_fileiterator_spec.rb",
-    "spec/gffdb_spec.rb",
-    "spec/gffparserec.rb",
-    "test/helper.rb",
-    "test/regressiontest.rb",
+    "test/regressiontest2.rb",
     "test/test_bio-gff3.rb"
   ]
+  s.homepage = "https://github.com/pjotrp/bioruby-gff3-plugin"
+  s.licenses = ["MIT"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = "1.8.10"
+  s.summary = "GFF3 parser for big data"
 
   if s.respond_to? :specification_version then
     s.specification_version = 3
@@ -99,29 +90,29 @@ Support for external FASTA files.
       s.add_runtime_dependency(%q<log4r>, ["> 1.1.6"])
       s.add_runtime_dependency(%q<bio-logger>, ["> 0.8.0"])
       s.add_development_dependency(%q<shoulda>, [">= 0"])
-      s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
-      s.add_development_dependency(%q<jeweler>, ["~> 1.5.2"])
-      s.add_development_dependency(%q<rcov>, [">= 0"])
-      s.add_development_dependency(%q<rspec>, [">= 2.3.0"])
+      s.add_development_dependency(%q<bundler>, ["~> 1.1.5"])
+      s.add_development_dependency(%q<jeweler>, ["~> 1.8.3"])
+      s.add_development_dependency(%q<rspec>, [">= 2.10.0"])
+      s.add_development_dependency(%q<regressiontest>, [">= 0"])
     else
       s.add_dependency(%q<bio>, [">= 1.3.1"])
       s.add_dependency(%q<log4r>, ["> 1.1.6"])
       s.add_dependency(%q<bio-logger>, ["> 0.8.0"])
       s.add_dependency(%q<shoulda>, [">= 0"])
-      s.add_dependency(%q<bundler>, ["~> 1.0.0"])
-      s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
-      s.add_dependency(%q<rcov>, [">= 0"])
-      s.add_dependency(%q<rspec>, [">= 2.3.0"])
+      s.add_dependency(%q<bundler>, ["~> 1.1.5"])
+      s.add_dependency(%q<jeweler>, ["~> 1.8.3"])
+      s.add_dependency(%q<rspec>, [">= 2.10.0"])
+      s.add_dependency(%q<regressiontest>, [">= 0"])
     end
   else
     s.add_dependency(%q<bio>, [">= 1.3.1"])
     s.add_dependency(%q<log4r>, ["> 1.1.6"])
     s.add_dependency(%q<bio-logger>, ["> 0.8.0"])
     s.add_dependency(%q<shoulda>, [">= 0"])
-    s.add_dependency(%q<bundler>, ["~> 1.0.0"])
-    s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
-    s.add_dependency(%q<rcov>, [">= 0"])
-    s.add_dependency(%q<rspec>, [">= 2.3.0"])
+    s.add_dependency(%q<bundler>, ["~> 1.1.5"])
+    s.add_dependency(%q<jeweler>, ["~> 1.8.3"])
+    s.add_dependency(%q<rspec>, [">= 2.10.0"])
+    s.add_dependency(%q<regressiontest>, [">= 0"])
   end
 end
 

data/lib/bio/db/gff/block/gffblockparser.rb

@@ -69,23 +69,22 @@ module Bio
    
         def each_seq(gfftype) 
           parse(gfftype) { | id, seq | yield id,seq }
-
         end
 
         def each_gene_seq
           each_seq('gene') { | id, seq | yield id,seq }
         end
+
         def each_mRNA_seq
           each_seq('mrna') { | id, seq | yield id,seq }
-
         end
+
         def each_exon_seq
           each_seq('exon') { | id, seq | yield id,seq }
-
         end
+
         def each_CDS_seq
           each_seq('cds') { | id, seq | yield id,seq }
-
         end
       end
     end