bioinform 0.1.6 → 0.1.7

data/spec/parsers/string_fantom_parser_spec.rb

@@ -1,30 +1,67 @@
 require 'spec_helper'
 require 'bioinform/parsers/string_fantom_parser'
 
-module Bioinform    
+module Bioinform
   describe StringFantomParser do
+    describe '#parse' do
+      it 'should be able to parse several motifs' do
+        input = <<-EOS
+//
+NA  motif_1
+P0	A	C	G	T
+P1	0	1	2	3
+P2	4	5	6	7
+//
+//
+NA  motif_2
+P0	A	C	G	T
+P1  1 2 3 4
+P2  5 6 7 8
+P3  9 10 11 12
+//
+NA  motif_3
+P0	A	C	G	T
+P1	2 3	4 5
+P2	6 7 8 9
+        EOS
+        StringFantomParser.split(input).should == [ {matrix: [[0,1,2,3],[4,5,6,7]], name: 'motif_1'},
+                                                    {matrix: [[1,2,3,4],[5,6,7,8],[9,10,11,12]], name: 'motif_2'},
+                                                    {matrix: [[2,3,4,5],[6,7,8,9]], name: 'motif_3'} ]
+      end
+
+      it 'should be able to parse motif with additional rows' do
+        input = <<-EOS
+NA  motif_1
+P0	A C G T S P
+P1	0 1 2 3 5 10
+P2	4 5 6 7 5 11
+        EOS
+        StringFantomParser.split(input).should == [ {matrix: [[0,1,2,3],[4,5,6,7]], name: 'motif_1'} ]
+      end
+    end
+
     good_cases = {
       'string in Fantom-format' => {input: "
         NA  motif_CTNCAG
-        P0	A	C	G	T	
-        P1	0	1878368	0	0	
-        P2	0	0	0	1878368	
-        P3	469592	469592	469592	469592	
-        P4	0	1878368	0	0	
-        P5	1878368	0	0	0	
+        P0	A	C	G	T
+        P1	0	1878368	0	0
+        P2	0	0	0	1878368
+        P3	469592	469592	469592	469592
+        P4	0	1878368	0	0
+        P5	1878368	0	0	0
         P6	0	0	1878368	0",
-        matrix: [ [0.0, 1878368.0, 0.0, 0.0], 
-                  [0.0, 0.0, 0.0, 1878368.0], 
-                  [469592.0, 469592.0, 469592.0, 469592.0], 
-                  [0.0, 1878368.0, 0.0, 0.0], 
-                  [1878368.0, 0.0, 0.0, 0.0], 
+        matrix: [ [0.0, 1878368.0, 0.0, 0.0],
+                  [0.0, 0.0, 0.0, 1878368.0],
+                  [469592.0, 469592.0, 469592.0, 469592.0],
+                  [0.0, 1878368.0, 0.0, 0.0],
+                  [1878368.0, 0.0, 0.0, 0.0],
                   [0.0, 0.0, 1878368.0, 0.0]],
-        name: 'motif_CTNCAG' 
+        name: 'motif_CTNCAG'
       }
     }
-    
+
     bad_cases = { }
-  
+
     parser_specs(StringFantomParser, good_cases, bad_cases)
   end
 end

data/spec/parsers/string_parser_spec.rb

@@ -16,23 +16,23 @@ module Bioinform
         end
       end
     end
-    
+
     context '::split' do
       it 'should be able to get a single PM' do
         StringParser.split("1 2 3 4 \n 5 6 7 8 \n 9 10 11 12").should == [ {matrix: [[1,2,3,4],[5,6,7,8],[9,10,11,12]], name:nil} ]
       end
-      
+
       it 'should be able to split several PMs separated with an empty line' do
         StringParser.split("1 2 3 4 \n 5 6 7 8 \n 9 10 11 12 \n\n 9 10 11 12 \n 1 2 3 4 \n 5 6 7 8").should == [ {matrix:[[1,2,3,4],[5,6,7,8],[9,10,11,12]],name:nil}, {matrix:[[9,10,11,12],[1,2,3,4],[5,6,7,8]],name:nil} ]
       end
-      
+
       it 'should be able to split several PMs separated with name' do
         StringParser.split("1 2 3 4 \n 5 6 7 8 \n 9 10 11 12 \nName\n 9 10 11 12 \n 1 2 3 4 \n 5 6 7 8").should == [ {matrix:[[1,2,3,4],[5,6,7,8],[9,10,11,12]],name:nil}, {matrix:[[9,10,11,12],[1,2,3,4],[5,6,7,8]],name:'Name'} ]
-        
+
         StringParser.split("1 2 3 4 \n 5 6 7 8 \n 9 10 11 12 \n\nName\n 9 10 11 12 \n 1 2 3 4 \n 5 6 7 8\n\n\n").should == [ {matrix:[[1,2,3,4],[5,6,7,8],[9,10,11,12]],name:nil}, {matrix:[[9,10,11,12],[1,2,3,4],[5,6,7,8]],name:'Name'} ]
       end
     end
-    
+
     context '::split_on_motifs' do
       it 'should be able to split string into PMs' do
         result = StringParser.split_on_motifs("1 2 3 4 \n 5 6 7 8 \n 9 10 11 12 \nName\n 9 10 11 12 \n 1 2 3 4 \n 5 6 7 8")
@@ -45,66 +45,66 @@ module Bioinform
       end
       it 'should create PM subclass when it\'s specified' do
         result = StringParser.split_on_motifs("1 2 3 4 \n 5 6 7 8 \n 9 10 11 12 \nName\n 9 10 11 12 \n 1 2 3 4 \n 5 6 7 8", PWM)
-        result.each{|pm| pm.class.should == PWM} 
+        result.each{|pm| pm.class.should == PWM}
       end
     end
-    
+
     good_cases = {
-      'Nx4 string' => {input: "1 2 3 4\n5 6 7 8", 
+      'Nx4 string' => {input: "1 2 3 4\n5 6 7 8",
                       matrix: [[1,2,3,4],[5,6,7,8]] },
-                      
-      '4xN string' => {input: "1 5\n2 6\n3 7\n 4 8", 
+
+      '4xN string' => {input: "1 5\n2 6\n3 7\n 4 8",
                       matrix: [[1,2,3,4],[5,6,7,8]] },
-                      
-      'string with name' => {input: "TestMatrix\n1 5\n2 6\n3 7\n 4 8", 
+
+      'string with name' => {input: "TestMatrix\n1 5\n2 6\n3 7\n 4 8",
                             matrix: [[1,2,3,4],[5,6,7,8]], name: 'TestMatrix' },
-                            
+
       'string with name (with introduction sign)' => {input: ">\t TestMatrix\n1 5\n2 6\n3 7\n 4 8",
                                                       matrix: [[1,2,3,4],[5,6,7,8]],
                                                       name: 'TestMatrix' },
-                                                      
-      'string with name (with special characters)' => {input: "Testmatrix_first:subname+sub-subname\n1 5\n2 6\n3 7\n 4 8", 
+
+      'string with name (with special characters)' => {input: "Testmatrix_first:subname+sub-subname\n1 5\n2 6\n3 7\n 4 8",
                             matrix: [[1,2,3,4],[5,6,7,8]], name: 'Testmatrix_first:subname+sub-subname' },
 
       'string with float numerics' => {input: "1.23 4.56 7.8 9.0\n9 -8.7 6.54 -3210",
                                       matrix: [[1.23, 4.56, 7.8, 9.0], [9, -8.7, 6.54, -3210]]},
-      
+
       'string with exponents' => {input: "123e-2 0.456e+1 7.8 9.0\n9 -87000000000E-10 6.54 -3.210e3",
                                   matrix: [[1.23, 4.56, 7.8, 9.0], [9, -8.7, 6.54, -3210]]},
 
-      'string with multiple spaces and tabs' => {input: "1 \t\t 2 3 4\n 5 6   7 8", 
+      'string with multiple spaces and tabs' => {input: "1 \t\t 2 3 4\n 5 6   7 8",
                                                 matrix: [[1,2,3,4],[5,6,7,8]] },
-      
-      'string with preceeding and terminating newlines' => {input: "\n\n\t 1 2 3 4\n5 6 7 8  \n\t\n", 
+
+      'string with preceeding and terminating newlines' => {input: "\n\n\t 1 2 3 4\n5 6 7 8  \n\t\n",
                       matrix: [[1,2,3,4],[5,6,7,8]] },
-      
+
       'string with windows crlf' => {input: "1 2 3 4\r\n5 6 7 8",
                       matrix: [[1,2,3,4],[5,6,7,8]] },
-                      
-      'Nx4 string with acgt-header' => {input: "A C G T\n1 2 3 4\n5 6 7 8", 
+
+      'Nx4 string with acgt-header' => {input: "A C G T\n1 2 3 4\n5 6 7 8",
                       matrix: [[1,2,3,4],[5,6,7,8]] },
-                      
-      'Nx4 string with name and acgt-header' => {input: "Name\nA C G T\n1 2 3 4\n5 6 7 8", 
+
+      'Nx4 string with name and acgt-header' => {input: "Name\nA C G T\n1 2 3 4\n5 6 7 8",
                       matrix: [[1,2,3,4],[5,6,7,8]], name: 'Name'},
-      
-      'Nx4 string with acgt-row-markers' => {input: "A 1 5\nC : 2 6\nG3 7\nT |4 8", 
+
+      'Nx4 string with acgt-row-markers' => {input: "A 1 5\nC : 2 6\nG3 7\nT |4 8",
                       matrix: [[1,2,3,4],[5,6,7,8]] },
-      
-      '4x4 string with acgt-header' => {input: "A C G T\n1 2 3 4\n5 6 7 8\n0 0 0 0\n2 2 2 2", 
+
+      '4x4 string with acgt-header' => {input: "A C G T\n1 2 3 4\n5 6 7 8\n0 0 0 0\n2 2 2 2",
                       matrix: [[1,2,3,4],[5,6,7,8],[0,0,0,0],[2,2,2,2]] },
-      
-      '4x4 string with acgt-row-markers' => {input: "A|1 2 3 4\nC|5 6 7 8\nG|0 0 0 0\nT|2 2 2 2", 
+
+      '4x4 string with acgt-row-markers' => {input: "A|1 2 3 4\nC|5 6 7 8\nG|0 0 0 0\nT|2 2 2 2",
                       matrix: [[1,5,0,2],[2,6,0,2],[3,7,0,2],[4,8,0,2]] },
-                      
-      '4x4 string with name and acgt-row-markers' => {input: "Name\nA:1 2 3 4\nC:5 6 7 8\nG:0 0 0 0\nT:2 2 2 2", 
+
+      '4x4 string with name and acgt-row-markers' => {input: "Name\nA:1 2 3 4\nC:5 6 7 8\nG:0 0 0 0\nT:2 2 2 2",
                       matrix: [[1,5,0,2],[2,6,0,2],[3,7,0,2],[4,8,0,2]], name: 'Name' }
     }
-    
+
     bad_cases = {
       'string with non-numeric input' =>  {input: "1.23 4.56 78aaa 9.0\n9 -8.7 6.54 -3210" },
       'string with empty exponent sign' => {input: "1.23 4.56 7.8 9.0\n 9e -8.7 6.54 3210" }
     }
-  
+
     parser_specs(StringParser, good_cases, bad_cases)
   end
 end

data/spec/spec_helper.rb

@@ -3,6 +3,37 @@ $LOAD_PATH.unshift File.dirname(__FILE__)
 
 require 'rspec'
 
+require 'fileutils'
+require 'stringio'
+
+# from minitest
+def capture_io(&block)
+  orig_stdout, orig_stderr = $stdout, $stderr
+  captured_stdout, captured_stderr = StringIO.new, StringIO.new
+  $stdout, $stderr = captured_stdout, captured_stderr
+  yield
+  return {stdout: captured_stdout.string, stderr: captured_stderr.string}
+ensure
+  $stdout = orig_stdout
+  $stderr = orig_stderr
+end
+
+# Method stubs $stdin not STDIN !
+def provide_stdin(input, &block)
+  orig_stdin = $stdin
+  $stdin = StringIO.new(input)
+  yield
+ensure
+  $stdin = orig_stdin
+end
+
+def capture_output(&block)
+  capture_io(&block)[:stdout]
+end
+def capture_stderr(&block)
+  capture_io(&block)[:stderr]
+end
+
 def parser_specs(parser_klass, good_cases, bad_cases)
   context '#parse!' do
     good_cases.each do |case_description, input_and_result|
@@ -11,7 +42,7 @@ def parser_specs(parser_klass, good_cases, bad_cases)
         result[:matrix].should == input_and_result[:matrix]
         if input_and_result.has_key?(:name)
           result[:name].should == input_and_result[:name]
-        else 
+        else
           result[:name].should be_nil
         end
       end

data/spec/support/delete_many_spec.rb

@@ -2,7 +2,7 @@ require 'spec_helper'
 require 'bioinform/support/delete_many'
 
 describe Array do
-  before :each do 
+  before :each do
     @arr = %w{a b c d e f g h i j b b}
   end
   describe '#delete_at_many' do
@@ -32,7 +32,7 @@ describe Array do
 end
 
 describe Hash do
-  before :each do 
+  before :each do
     @arr = {A: 3, T: 6, G: 4, C: 5}
   end
   describe '#delete_many' do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: bioinform
 version: !ruby/object:Gem::Version
-  version: 0.1.6
+  version: 0.1.7
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-09-03 00:00:00.000000000 Z
+date: 2012-09-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -89,8 +89,14 @@ files:
 - lib/bioinform/support/same_by.rb
 - lib/bioinform/version.rb
 - spec/cli/cli_spec.rb
+- spec/cli/data/KLF4 f2 spaced name.pcm
+- spec/cli/data/KLF4_f2.pcm
+- spec/cli/data/KLF4_f2.pwm.result
+- spec/cli/data/SP1_f1.pcm
+- spec/cli/data/SP1_f1.pwm.result
 - spec/cli/pcm2pwm_spec.rb
 - spec/cli/split_motifs_spec.rb
+- spec/data_models/collection_spec.rb
 - spec/data_models/pcm_spec.rb
 - spec/data_models/pm_spec.rb
 - spec/data_models/ppm_spec.rb
@@ -138,8 +144,14 @@ summary: Classes for work with different input formats of positional matrices an
   symbols
 test_files:
 - spec/cli/cli_spec.rb
+- spec/cli/data/KLF4 f2 spaced name.pcm
+- spec/cli/data/KLF4_f2.pcm
+- spec/cli/data/KLF4_f2.pwm.result
+- spec/cli/data/SP1_f1.pcm
+- spec/cli/data/SP1_f1.pwm.result
 - spec/cli/pcm2pwm_spec.rb
 - spec/cli/split_motifs_spec.rb
+- spec/data_models/collection_spec.rb
 - spec/data_models/pcm_spec.rb
 - spec/data_models/pm_spec.rb
 - spec/data_models/ppm_spec.rb