bio-lazyblastxml 0.3.0 → 0.4.0

data/README.rdoc

@@ -1,6 +1,57 @@
 = bio-lazyblastxml
 
-Description goes here.
+Provides a libxml-based lazy parser for reading through large blast xml files with a small memory footprint.
+
+== Requirements
+
+* Ruby 1.9.x
+* libxml
+
+If you're on ubuntu, libxml is most easily installed with:
+
+  sudo apt-get install libxml-ruby
+
+And then install the gem with
+
+  gem install bio-lazyblastxml
+  # If you need to be root to install gems, try:
+  sudo gem install bio-lazyblastxml
+
+== Overview
+
+The parsers uses a LibXML::Reader instance to read the XML file one line at a time, keeping very little in memory. You can think of the parser as having a very short memory, only able to recall the object that it happens to be looking at right now. The parser only runs through the document once unless Bio::LazyBlast#rewind is called.
+
+== Example Usage
+
+Each report is an enumerable that yields iterations.
+Each iteration is an enumerable that yields hits (if there are any hits).
+
+  require 'bio-lazyblastxml'
+  
+  # Generate your new report object
+  report = Bio::LazyBlast::Report.new('my_huge_blastfile.xml')
+  
+  # How many hits does each query have?
+  report.each_iteration do |iteration|
+    puts [iteration.query_def, iteration.count].join("\t")
+  end
+
+Each hit is an enumerable that yields hsps:
+
+  require 'bio-lazyblastxml'
+  
+  # Generate your new report object
+  report = Bio::LazyBlast::Report.new('my_huge_blastfile.xml')
+  
+  report.each_iteration do |iteration|
+    iteration.each_hit do |hit|
+      # Sum up the lengths of all the hsps
+      hsp_length_sum = hit.inject(0){|count,hsp| count += hsp.align_len}
+      puts [iteration.query_def, hit.definition, hsp_length_sum].join("\t")
+    end
+  end
+
+
 
 == Contributing to bio-lazyblastxml
  

data/VERSION

@@ -1 +1 @@
-0.3.0
+0.4.0

data/bio-lazyblastxml.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{bio-lazyblastxml}
-  s.version = "0.3.0"
+  s.version = "0.4.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["robsyme"]
-  s.date = %q{2011-05-31}
+  s.date = %q{2011-06-01}
   s.description = %q{This is very scrappy at the moment, and will need to be seriously cleaned up. It does what I need it to do for now. I'll fix it up in the coming weeks. Promise :)}
   s.email = %q{rob.syme@gmail.com}
   s.extra_rdoc_files = [

data/lib/bio/appl/blast/lazyblastxml.rb

@@ -4,10 +4,11 @@ module Bio
   class LazyBlast
     class Report
       include Enumerable
-      attr_reader :reader, :program, :version, :db, :query_id, :query_def, :query_len, :parameters
+      attr_reader :program, :version, :db, :query_id, :query_def, :query_len, :statistics
 
       def initialize(filename)
-        @reader = LibXML::XML::Reader.file(filename)
+        @filename = filename
+        @reader = LibXML::XML::Reader.file(@filename)
         @nodes = Enumerator.new do |yielder|
           while @reader.read 
             yielder << @reader if @reader.node_type == LibXML::XML::Reader::TYPE_ELEMENT
@@ -17,9 +18,9 @@ module Bio
       end
 
       def setup_report_values
-        @parameters = Hash.new
+        @statistics = Hash.new
         @nodes.each do |node|
-          return node if node.name == "BlastOutput_iterations"
+          return if node.name == "BlastOutput_iterations"
           case node.name
           when 'BlastOutput_program'
             @program = node.read_inner_xml
@@ -34,15 +35,15 @@ module Bio
           when 'BlastOutput_query-len'
             @query_len = node.read_inner_xml.to_i
           when 'Parameters_matrix'
-            @parameters['matrix'] = node.read_inner_xml
+            @statistics['matrix'] = node.read_inner_xml
           when 'Parameters_expect'
-            @parameters['expect'] = node.read_inner_xml.to_i
+            @statistics['expect'] = node.read_inner_xml.to_i
           when 'Parameters_gap-open'
-            @parameters['gap-open'] = node.read_inner_xml.to_i
+            @statistics['gap-open'] = node.read_inner_xml.to_i
           when 'Parameters_gap-extend'
-            @parameters['gap-extend'] = node.read_inner_xml.to_i
+            @statistics['gap-extend'] = node.read_inner_xml.to_i
           when 'Parameters_filter'
-            @parameters['filter'] = node.read_inner_xml
+            @statistics['filter'] = node.read_inner_xml
           end
         end
       end
@@ -52,6 +53,16 @@ module Bio
       end
       alias :each_iteration :each
 
+      def rewind
+        @reader.close
+        @reader = LibXML::XML::Reader.file(@filename)
+        @nodes = Enumerator.new do |yielder|
+          while @reader.read 
+            yielder << @reader if @reader.node_type == LibXML::XML::Reader::TYPE_ELEMENT
+          end
+        end
+      end
+
       class Iteration
         include Enumerable
         attr_reader :num, :query_id, :query_def, :query_len, :message, :parameters
@@ -67,7 +78,7 @@ module Bio
 
         def setup_iteration_values
           @nodes.each do |node|
-            return node if node.name == 'Iteration_hits'
+            return if node.name == 'Iteration_hits'
             case node.name
             when 'Iteration_iter-num'
               @num = node.read_inner_xml.to_i
@@ -103,7 +114,7 @@ module Bio
 
           def setup_hit_values
             @nodes.each do |node|
-              return node if node.name == 'Hit_hsps'
+              return if node.name == 'Hit_hsps'
               case node.name
               when 'Hit_num'
                 @num = node.read_inner_xml.to_i

data/test/test_bio-lazyblastxml.rb

@@ -35,17 +35,24 @@ class TestIteration < MiniTest::Unit::TestCase
     @report = Bio::LazyBlast::Report.new(@blast_filename)
   end
 
+  def test_rewind_ability
+    assert_equal 2, @report.count, "Test report should contain 2 iterations"
+    assert_equal 0, @report.count, "Report should contain no more iterations once the file has been read through"
+    @report.rewind
+    assert_equal 2, @report.count, "Test report should contain 2 iterations once the file has been rewound."
+  end
+
   def test_iteration_creation
     @iteration = @report.first
     assert_kind_of Bio::LazyBlast::Report::Iteration, @iteration
     assert_equal 'blastp', @report.program
     assert_equal 'blastp 2.2.21 [Jun-14-2009]', @report.version
     assert_equal 'db.fasta', @report.db
-    assert_equal 'BLOSUM62', @report.parameters['matrix']
-    assert_equal 10, @report.parameters['expect']
-    assert_equal 11, @report.parameters['gap-open']
-    assert_equal 1, @report.parameters['gap-extend']
-    assert_equal 'F', @report.parameters['filter']
+    assert_equal 'BLOSUM62', @report.statistics['matrix']
+    assert_equal 10, @report.statistics['expect']
+    assert_equal 11, @report.statistics['gap-open']
+    assert_equal 1, @report.statistics['gap-extend']
+    assert_equal 'F', @report.statistics['filter']
   end
 
   def test_example_usage

metadata

@@ -2,7 +2,7 @@
 name: bio-lazyblastxml
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors: 
 - robsyme
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-05-31 00:00:00 +08:00
+date: 2011-06-01 00:00:00 +08:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -116,7 +116,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: -3799468829096378627
+      hash: -1790620181502382914
       segments: 
       - 0
       version: "0"