lederhosen 0.5.2 → 0.5.4

data/lederhosen.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "lederhosen"
-  s.version = "0.5.2"
+  s.version = "0.5.4"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Austin G. Davis-Richardson"]
-  s.date = "2012-08-27"
+  s.date = "2012-08-28"
   s.description = "Various tools for OTU clustering"
   s.email = "harekrishna@gmail.com"
   s.executables = ["lederhosen"]

data/lib/lederhosen/helpers.rb

@@ -99,7 +99,7 @@ module Lederhosen
       pbar = ProgressBar.new 'loading uc file', bytes
       File.open(input) do |handle|
         handle.each do |line|
-          pbar.inc handle.pos
+          pbar.set handle.pos
           next if line =~ /^#/ # skip comments
 
           line = line.strip.split

data/lib/lederhosen/tasks/k_filter.rb

@@ -28,7 +28,7 @@ module Lederhosen
         pbar = ProgressBar.new 'counting', File.size(input)
         records = Dna.new handle
         records.each do |r|
-          pbar.inc(handle.pos)
+          pbar.set handle.pos
           total_reads += 1
           kmers = r.sequence.to_kmers(k_len)
           kmers.each { |x| counting_table[x] += 1 }

data/lib/lederhosen/tasks/split_fasta.rb

@@ -2,6 +2,8 @@
 # Split a fasta file into many fasta files with n reads
 #
 
+require 'zlib'
+
 module Lederhosen
   class CLI
 
@@ -11,26 +13,49 @@ module Lederhosen
     method_option :input,   :type => :string,  :required => true
     method_option :out_dir, :type => :string,  :required => true
     method_option :n,       :type => :numeric, :required => true
+    method_option :gzip,    :type => :boolean, :default  => false
 
     def split_fasta
       input   = options[:input]
       out_dir = options[:out_dir]
       n       = options[:n].to_i
+      gzip    = options[:gzip]
 
       ohai "splitting #{input} into files with #{n} reads stored in #{out_dir}"
+      ohai "using gzip" if gzip
 
       `mkdir -p #{out_dir}`
 
       File.open input do |handle|
         pbar = ProgressBar.new 'splitting', File.size(handle)
         Dna.new(handle).each_with_index do |record, i|
-          pbar.inc handle.pos
-          @out = File.open(File.join(out_dir, "split_#{i/n}.fasta"), 'w') if i%n == 0
+          pbar.set handle.pos
+          # I have to use a class variable here because
+          # if I don't the variable gets set to nil after
+          # after each iteration.
+          @out =
+            if i%n == 0 # start a new file
+              # GzipWriter must be closed explicitly
+              # this raises an exception this first time
+              @out.close rescue nil
+
+              # create an IO object depending on whether or
+              # not the user wants to use gzip
+              if gzip
+                Zlib::GzipWriter.open(File.join(out_dir, "split_#{i/n}.fasta.gz"))
+              else
+                File.open(File.join(out_dir, "split_#{i/n}.fasta"), 'w')
+              end
+            else # keep using current handle
+              @out
+            end
           @out.puts record
         end
         pbar.finish
+        @out.close
       end
 
+      ohai "created #{Dir[File.join(out_dir, '*')].size} files"
     end
   end
 end

data/lib/lederhosen/tasks/uc_filter.rb

@@ -53,7 +53,7 @@ module Lederhosen
         pbar = ProgressBar.new 'saving', File.size(input)
         handle.each do |line|
 
-          pbar.inc handle.pos
+          pbar.set handle.pos
           if line =~ /^#/
             out.print line
             next

data/lib/lederhosen/version.rb

@@ -2,7 +2,7 @@ module Lederhosen
   module Version
     MAJOR = 0
     MINOR = 5
-    PATCH = 2
+    PATCH = 4
 
     STRING = [MAJOR, MINOR, PATCH].join('.')
   end

data/spec/cli_spec.rb

@@ -9,6 +9,7 @@ describe Lederhosen::CLI do
 
   it 'should have a version command' do
     `./bin/lederhosen version `.strip.should == "lederhosen-#{Lederhosen::Version::STRING}"
+    $?.success?.should be_true
   end
 
   it 'should trim reads' do
@@ -43,10 +44,17 @@ describe Lederhosen::CLI do
 
   it 'should filter OTU abundance matrices' do
     `./bin/lederhosen otu_filter --input=#{$test_dir}/otu_table.csv --output=#{$test_dir}/otu_table.filtered.csv --reads 1 --samples 1`
+    $?.success?.should be_true
+  end
+
+  it 'should split a fasta file into smaller fasta files (optionally gzipped)' do
+    `./bin/lederhosen split_fasta --input=#{$test_dir}/joined.fasta --out-dir=#{$test_dir}/split/ --gzip true -n 100`
+    $?.success?.should be_true
   end
 
   it 'should split joined.fasta into reads for each cluster' do
     `./bin/lederhosen split --reads=#{$test_dir}/joined.fasta --clusters=#{$test_dir}/clusters.uc --out-dir=#{$test_dir}/split --min-clst-size=1`
+    $?.success?.should be_true
   end
 
   it 'should create a fasta file containing representative reads for each cluster' do

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: lederhosen
 version: !ruby/object:Gem::Version 
-  hash: 15
+  hash: 3
   prerelease: 
   segments: 
   - 0
   - 5
-  - 2
-  version: 0.5.2
+  - 4
+  version: 0.5.4
 platform: ruby
 authors: 
 - Austin G. Davis-Richardson
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-08-27 00:00:00 Z
+date: 2012-08-28 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   type: :runtime