parse_fasta 1.2.0 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b140f0d7d54cdb4f0938bbcd5aa2484f069fcb50
-  data.tar.gz: 9ff3a6ace4f834da41b298075aa470cb730bd4f6
+  metadata.gz: ae03847d56379d572d6118a176876a1e11a21a49
+  data.tar.gz: ffb84a464f8f7057f3a363b2b872f4b60fcca9c2
 SHA512:
-  metadata.gz: f9b9dd477b595a28970f2f299503f360c7fb353a62013b2e848f353a296ddebf1def65f5f6a5f02ea046d20041f28cfe0c32581cdc10793cd6ac75daec0576ec
-  data.tar.gz: aa1e8e8aff902c6a16315fa6513f755f92887ae79c0c4cc8f42d7ae7c530e8885250885c7397cf1861d47136ceb6012deed7fab9be3d98da0d3d4c4d11720f60
+  metadata.gz: 0b6b3694de307b868df3b1d5b38b08e539e545827d8d5f47a8b41a550f60d6354164b0e563b6eacf39ab63bd844c2ab68578fc0bfbc5fd5a1f3a63b31a09cfc9
+  data.tar.gz: 719f6fb5c112b06ecf969662617de3bdc02156a09fcb542ff0a9553de55f2d7d6400fc2d6384be27c780517b1ab95887991a8a22c9d05ab3070e7d0e2b05962f

data/README.md

@@ -1,5 +1,7 @@
 # parse_fasta #
 
+[![Gem Version](https://badge.fury.io/rb/parse_fasta.svg)](http://badge.fury.io/rb/parse_fasta)
+
 So you want to parse a fasta file...
 
 ## Installation ##
@@ -27,7 +29,7 @@ and over.
 ## Documentation ##
 
 Checkout
-[parse_fasta docs](http://rubydoc.info/gems/parse_fasta/1.1.0/frames)
+[parse_fasta docs](http://rubydoc.info/gems/parse_fasta/1.3.0/frames)
 to see the full documentation.
 
 ## Usage ##
@@ -56,6 +58,45 @@ Now we can parse fastq files as well!
 
 ## Versions ##
 
+### 1.3.0 ###
+
+Add additional functionality to `each_record` method.
+
+#### Info ####
+
+I often like to use the fasta format for other things like so
+
+	>fruits
+	pineapple
+	pear
+	peach
+	>veggies
+	peppers
+	parsnip
+	peas
+
+rather than having this in a two column file like this
+
+	fruit,pineapple
+	fruit,pear
+	fruit,peach
+	veggie,peppers
+	veggie,parsnip
+	veggie,peas
+
+So I added functionality to `each_record` to keep each line a record
+separate in an array. Here's an example using the above file.
+
+    info = []
+	FastaFile.open(f, 'r').each_record(1) do |header, lines|
+	  info << [header, lines]
+	end
+
+Then info will contain the following arrays
+
+	['fruits', ['pineapple', 'pear', 'peach']],
+	['veggies', ['peppers', 'parsnip', 'peas']]
+
 ### 1.2.0 ###
 
 Added `mean_qual` method to the `Quality` class.

data/lib/parse_fasta/fasta_file.rb

@@ -22,20 +22,42 @@ class FastaFile < File
   # Analagous to File#each_line, #each_record is used to go through a
   # fasta file record by record.
   #
-  # @example Parsing a fasta file
+  # @param separate_lines [Object] If truthy, separate lines of record
+  #   into an array, but if falsy, yield a Sequence object for the
+  #   sequence instead.
+  #
+  # @example Parsing a fasta file (default behavior)
   #   FastaFile.open('reads.fna', 'r').each_record do |header, sequence|
   #     puts [header, sequence.gc].join("\t")
   #   end
   # 
+  # @example Parsing a fasta file (with truthy value param)
+  #   FastaFile.open('reads.fna','r').each_record(1) do |header, sequence|
+  #     # header => 'sequence_1'
+  #     # sequence => ['AACTG', 'AGTCGT', ... ]
+  #   end
+  # 
   # @yield The header and sequence for each record in the fasta
   #   file to the block
+  #
   # @yieldparam header [String] The header of the fasta record without
   #   the leading '>'
-  # @yieldparam sequence [Sequence] The sequence of the fasta record
-  def each_record
-    self.each("\n>") do |line|
-      header, sequence = parse_line(line)
-      yield(header.strip, Sequence.new(sequence))
+  #
+  # @yieldparam sequence [Sequence, Array<String>] The sequence of the
+  #   fasta record. If `separate_lines` is falsy (the default
+  #   behavior), will be Sequence, but if truthy will be
+  #   Array<String>.
+  def each_record(separate_lines=nil)
+    if separate_lines
+      self.each("\n>") do |line|
+        header, sequence = parse_line_separately(line)
+        yield(header.strip, sequence)
+      end
+    else
+      self.each("\n>") do |line|
+        header, sequence = parse_line(line)
+        yield(header.strip, Sequence.new(sequence))
+      end
     end
   end
 
@@ -43,4 +65,13 @@ class FastaFile < File
   def parse_line(line)
     line.chomp.split("\n", 2).map { |s| s.gsub(/\n|>/, '') }
   end
+
+  def parse_line_separately(line)
+    #line.chomp.split("\n", 2).map { |s| s.gsub(/>/, '') }
+    header, sequence = 
+      line.chomp.split("\n", 2).map { |s| s.gsub(/>/, '') }
+    sequences = sequence.split("\n").reject { |s| s.empty? }
+
+    [header, sequences]
+  end
 end

data/lib/parse_fasta/version.rb

@@ -17,5 +17,5 @@
 # along with parse_fasta.  If not, see <http://www.gnu.org/licenses/>.
 
 module ParseFasta
-  VERSION = "1.2.0"
+  VERSION = "1.3.0"
 end

data/spec/lib/fasta_file_spec.rb

@@ -22,25 +22,39 @@ describe FastaFile do
   describe "#each_record" do
 
     let(:fname) { "#{File.dirname(__FILE__)}/../../test_files/test.fa" }
-    it "yields a block with header and sequence for each record in a fasta file" do
-      seqs = []
-      FastaFile.open(fname, 'r').each_record do |header, sequence|
-        seqs << [header, sequence]
+
+    context "with no arguments" do 
+      it "yields header and sequence for each record in a fasta file" do
+        seqs = []
+        FastaFile.open(fname, 'r').each_record do |header, sequence|
+          seqs << [header, sequence]
+        end
+        
+        expect(seqs).to eq([["seq1 is fun", "AACTGGNNN"],
+                            ["seq2", "AATCCTGNNN"],
+                            ["seq3", "yyyyyyyyyyyyyyyNNN"]])
+
       end
-      
-      expect(seqs).to eq([["seq1 is fun", "AACTGGend"],
-                          ["seq2", "AATCCTGend"],
-                          ["seq3", "yyyyyyyyyyyyyyyend"]])
 
+      it "yields sequence of type Sequence as second parameter" do
+        FastaFile.open(fname, 'r').each_record do |header, sequence|
+          expect(sequence).to be_an_instance_of Sequence
+          break
+        end
+      end      
     end
 
-    it "passes header of type string as first parameter" do
-      sequence_class = nil
-      FastaFile.open(fname, 'r').each_record do |header, sequence|
-        sequence_class = sequence.class
-        break
+    context "with a truthy argument" do
+      it "yields header and array of lines for each record" do
+        seqs = []
+        FastaFile.open(fname, 'r').each_record(1) do |header, sequence|
+          seqs << [header, sequence]
+        end
+
+        expect(seqs).to eq([["seq1 is fun", ["AACTGGNNN"]],
+                            ["seq2", ["AAT", "CCTGNNN"]],
+                            ["seq3", ["yyyyyyyyyy", "yyyyy", "NNN"]]])
       end
-      expect(sequence_class).to be Sequence
-    end      
+    end
   end
 end

data/spec/lib/sequence_spec.rb

@@ -20,8 +20,12 @@ require 'spec_helper'
 require 'bio'
 
 describe Sequence do
-  describe "#gc" do
 
+  it "inherits from String" do
+    expect(Sequence.new('ACTG')).to be_a String
+  end
+
+  describe "#gc" do
     it "gives the same answer as BioRuby" do
       s = 'ACtgcGAtcgCgAaTtGgCcnNuU'
       bioruby_gc = Bio::Sequence::NA.new(s).gc_content

data/test_files/test.fa

@@ -1,9 +1,10 @@
 >seq1 is fun
-AACTGGend
+AACTGGNNN
 >seq2
 AAT
-CCTGend
+CCTGNNN
 >seq3
 yyyyyyyyyy
+
 yyyyy
-end
+NNN

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: parse_fasta
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 1.3.0
 platform: ruby
 authors:
 - Ryan Moore
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-07-03 00:00:00.000000000 Z
+date: 2014-07-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler