parse_fasta 1.6.0 → 1.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2f6ccbf7f40297b5bc4604e15c7ef47ffb573d44
-  data.tar.gz: f95cffcff55c9789eabb563095319154ca21ec99
+  metadata.gz: 889ac551f3260a660a2035614b252f7ddd511551
+  data.tar.gz: 963cebe7b51e0caaf2327713acc5a0a6d7a34bb4
 SHA512:
-  metadata.gz: 1cdd0c880390a6666bafa57190eb37672188abfe64e24048277e759cdfd48eedca35c0e6a2251426bfe071aedc9c0bddb00b220ba140f87fdf1de1f8ae0b67b5
-  data.tar.gz: 92734f57cc2da98f1a705c5e60b568c67c47b152efd6a114e523c51fc982c55f1f8aa4edf6df6b143fc11a3a910ec0b448158f4010438a7b292c25bf0154fafa
+  metadata.gz: d5f26789225ebc0131680974502f54127240d2db1c9bffb3c577808bf75cf83e09eb7dc1b66fd86be18733b2ea49f4bffd8f51a8111cffeda37ba3e874bc72db
+  data.tar.gz: cad0979ede863a7e8205b684853533be11e85b8522429e93348eca20ad3c41895148ae42fc854dbd6d87f49f20dfbea5a95c346161790d5c038d1f0366e82a4b

data/README.md

@@ -71,6 +71,11 @@ want your scripts to accept either fastA or fastQ files.
 If you need the description and quality string, you should use
 FastqFile instead.
 
+#### 1.6.1 ####
+
+Better internal handling of empty sequences -- instead of raising
+errors, pass empty sequences.
+
 ### 1.5 ###
 
 Now accepts gzipped files. Huzzah!

data/lib/parse_fasta/fasta_file.rb

@@ -33,13 +33,13 @@ class FastaFile < File
   #   FastaFile.open('reads.fna.gz').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').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
   #
@@ -55,7 +55,7 @@ class FastaFile < File
       f = Zlib::GzipReader.open(self)
     rescue Zlib::GzipFile::Error => e
       f = self
-    end      
+    end
 
     if separate_lines
       f.each("\n>") do |line|
@@ -63,9 +63,9 @@ class FastaFile < File
         yield(header.strip, sequence)
       end
     else
-      f.each("\n>") do |line| 
+      f.each("\n>") do |line|
         header, sequence = parse_line(line)
-        yield(header.strip, Sequence.new(sequence))
+        yield(header.strip, Sequence.new(sequence || ""))
       end
     end
 
@@ -74,16 +74,22 @@ class FastaFile < File
   end
 
   private
+
   def parse_line(line)
-    line.chomp.split("\n", 2).map { |s| s.gsub(/\n|>/, '') }
+    line.split("\n", 2).map { |s| s.gsub(/\n|>/, '') }
   end
 
   def parse_line_separately(line)
-    header, sequence = 
-      line.chomp.split("\n", 2).map { |s| s.gsub(/>/, '') }
-    sequences = sequence.split("\n")
-      .reject { |s| s.empty? }
-      .map { |s| Sequence.new(s) }
+    header, sequence =
+      line.split("\n", 2).map { |s| s.gsub(/>/, '') }
+
+    if sequence.nil?
+      sequences = []
+    else
+      sequences = sequence.split("\n")
+        .reject { |s| s.empty? }
+        .map { |s| Sequence.new(s) }
+    end
 
     [header, sequences]
   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 = "1.6.0"
+  VERSION = "1.6.1"
 end

data/spec/lib/fasta_file_spec.rb

@@ -20,17 +20,9 @@ require 'spec_helper'
 
 describe FastaFile do
   describe "#each_record" do
-    let(:records) {
-      [["seq1 is fun", "AACTGGNNN"],
-       ["seq2", "AATCCTGNNN"],
-       ["seq3", "yyyyyyyyyyyyyyyNNN"]]
-    }
-
-    let(:truthy_records) {
-      [["seq1 is fun", ["AACTGGNNN"]],
-       ["seq2", ["AAT", "CCTGNNN"]],
-       ["seq3", ["yyyyyyyyyy", "yyyyy", "NNN"]]]
-    }
+    let(:records) { Helpers::RECORDS }
+
+    let(:truthy_records) { Helpers::TRUTHY_RECORDS }
     let(:f_handle) { FastaFile.open(@fname).each_record { |s| } }
 
     shared_examples_for "any FastaFile" do
@@ -61,7 +53,7 @@ describe FastaFile do
             expect(all_Sequences).to be true
           end
         end
-        
+
       end
     end
 
@@ -96,6 +88,5 @@ describe FastaFile do
         expect(f_handle).to be_an_instance_of FastaFile
       end
     end
-  end      
+  end
 end
-

data/spec/lib/seq_file_spec.rb

@@ -20,15 +20,12 @@ require 'spec_helper'
 
 describe SeqFile do
   describe "#each_record" do
-    let(:records) {
-      [["seq1 is fun", "AACTGGNNN"],
-       ["seq2", "AATCCTGNNN"],
-       ["seq3", "yyyyyyyyyyyyyyyNNN"]]
-    }
 
     context "when input is a fasta file" do
+      let(:records) { Helpers::RECORDS }
+
       let(:f_handle) { SeqFile.open(@fname).each_record { |s| } }
-      
+
       shared_examples_for "parsing a fasta file" do
         it "yields proper header and sequence for each record" do
           expect { |b|
@@ -96,7 +93,7 @@ describe SeqFile do
         end
       end
     end
-    
+
     context "with a 4 line per record fastq file" do
       describe "#each_record" do
         context "with a gzipped file" do

data/spec/spec_helper.rb

@@ -21,3 +21,22 @@ Coveralls.wear!
 
 require 'parse_fasta'
 
+module Helpers
+
+  RECORDS = [["empty seq at beginning", ""],
+             ["seq1 is fun", "AACTGGNNN"],
+             ["seq2", "AATCCTGNNN"],
+             ["empty seq 1", ""],
+             ["empty seq 2", ""],
+             ["seq3", "yyyyyyyyyyyyyyyNNN"],
+             ["empty seq at end", ""]]
+
+  TRUTHY_RECORDS = [["empty seq at beginning", []],
+                    ["seq1 is fun", ["AACTGGNNN"]],
+                    ["seq2", ["AAT", "CCTGNNN"]],
+                    ["empty seq 1", []],
+                    ["empty seq 2", []],
+                    ["seq3", ["yyyyyyyyyy", "yyyyy", "NNN"]],
+                    ["empty seq at end", []]]
+
+end

data/test_files/test.fa

@@ -1,12 +1,18 @@
+> empty seq at beginning
 >seq1 is fun
 AACTGGNNN
 
+
 >seq2
 AAT
 CCTGNNN
+> empty seq 1
+> empty seq 2
+
 
 >seq3
 yyyyyyyyyy
 
 yyyyy
 NNN
+>empty seq at end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: parse_fasta
 version: !ruby/object:Gem::Version
-  version: 1.6.0
+  version: 1.6.1
 platform: ruby
 authors:
 - Ryan Moore
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-22 00:00:00.000000000 Z
+date: 2015-05-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler