mspire 0.7.18 → 0.8.0

data/lib/mspire/mzml.rb

@@ -1,25 +1,12 @@
+
+# TODO: trim down these require statements to only include upper level
 require 'mspire'
 require 'builder'
-require 'nokogiri'
-require 'io/bookmark'
-require 'zlib'
-require 'mspire/mzml/index_list'
-require 'mspire/mzml/spectrum'
-require 'mspire/mzml/file_description'
-require 'mspire/mzml/software'
-require 'mspire/mzml/scan_list'
-require 'mspire/mzml/selected_ion'
-require 'mspire/mzml/scan'
+require 'core_ext/enumerable'
+
+require 'mspire/mzml/reader'
+
 require 'mspire/mzml/scan_settings'
-require 'mspire/mzml/processing_method'
-require 'mspire/mzml/run'
-require 'mspire/mzml/spectrum_list'
-require 'mspire/mzml/chromatogram_list'
-require 'mspire/mzml/instrument_configuration'
-require 'mspire/mzml/data_processing'
-require 'mspire/mzml/referenceable_param_group'
-require 'mspire/mzml/cv'
-require 'mspire/mzml/sample'
 
 module Mspire
   # Reading an mzml file:
@@ -42,7 +29,8 @@ module Mspire
   #
   # Writing an mzml file from scratch:
   #
-  #     spec1 = Mspire::Mzml::Spectrum.new('scan=1', params: ['MS:1000127', ['MS:1000511', 1]]) do |spec|
+  #     spec1 = Mspire::Mzml::Spectrum.new('scan=1') do |spec|
+  #       spec.describe_many! ['MS:1000127', ['MS:1000511', 1]]
   #       spec.data_arrays = [[1,2,3], [4,5,6]]
   #       spec.scan_list = Mspire::Mzml::ScanList.new do |sl|
   #         scan = Mspire::Mzml::Scan.new do |scan|
@@ -60,7 +48,8 @@ module Mspire
   #         fd.file_content = Mspire::Mzml::FileContent.new
   #         fd.source_files << Mspire::Mzml::SourceFile.new
   #       end
-  #       default_instrument_config = Mspire::Mzml::InstrumentConfiguration.new("IC",[], params: ['MS:1000031'])
+  #       default_instrument_config = Mspire::Mzml::InstrumentConfiguration.new("IC",[])
+  #       default_instrument_config.describe! 'MS:1000031'
   #       mzml.instrument_configurations << default_instrument_config
   #       software = Mspire::Mzml::Software.new
   #       mzml.software_list << software
@@ -73,6 +62,23 @@ module Mspire
   #       end
   #     end
   class Mzml
+    include Enumerable  # each_spectrum
+
+    class << self
+      # read-only right now
+      def open(filename, &block)
+        File.open(filename) do |io|
+          block.call(self.new(io))
+        end
+      end
+
+      def foreach(filename, &block)
+        block or return enum_for(__method__, filename)
+        open(filename) do |mzml|
+          mzml.each(&block)
+        end
+      end
+    end
 
     module Default
       NAMESPACE = {
@@ -128,15 +134,17 @@ module Mspire
     # (required) an Mspire::Mzml::Run object
     attr_accessor :run
 
-    module Parser
-      NOBLANKS = ::Nokogiri::XML::ParseOptions::DEFAULT_XML | ::Nokogiri::XML::ParseOptions::NOBLANKS
-    end
-    include Enumerable
-
+    # the io object of the mzml file
     attr_accessor :io
+
+    # Mspire::Mzml::IndexList object associated with the file (only expected when reading
+    # mzml files at the moment)
     attr_accessor :index_list
+
+    # xml file encoding
     attr_accessor :encoding
 
+
     # arg must be an IO object for automatic index and header parsing to
     # occur.  If arg is a hash, then attributes are set.  In addition (or
     # alternatively) a block called that yields self to setup the object.
@@ -145,211 +153,65 @@ module Mspire
     # which allows seeking.  get_index_list is called to get or create the
     # index list.
     def initialize(arg=nil, &block)
-      %w(cvs software_list instrument_configurations data_processing_list).each {|guy| self.send( guy + '=', [] ) }
+      %w(cvs software_list instrument_configurations samples data_processing_list).each {|guy| self.send( guy + '=', [] ) }
 
       case arg
       when IO
-        @io = arg
-        begin
-          @encoding = @io.bookmark(true) {|io| io.readline.match(/encoding=["'](.*?)["']/)[1] }
-        rescue EOFError
-          raise RuntimeError, "no encoding present in XML!  (Is this even an xml file?)"
-        end
-        @index_list = get_index_list
-        read_header!
+        set_from_xml_io!(arg)
       when Hash
         arg.each {|k,v| self.send("#{k}=", v) }
       end
-      if block
-        block.call(self)
-      end
+      block.call(self) if block
     end
 
-    def read_header!
-      @io.rewind
-      chunk_size = 2**12
-      loc = 0
-      string = ''
-      while chunk = @io.read(chunk_size)
-        string << chunk
-        start_looking = ((loc-20) < 0) ? 0 : (loc-20)
-        break if string[start_looking..-1] =~ /<(spectrum|chromatogram)/
-        loc += chunk_size
+    module Convenience
+      def each_chromatogram(&block)
+        @run.chromatogram_list.each(&block)
       end
-      doc = Nokogiri::XML.parse(string, nil, @encoding, Parser::NOBLANKS)
-      mzml_n = doc.root
-      if mzml_n.name == 'indexedmzML'
-        mzml_n = mzml_n.child
-      end
-      cv_list_n = mzml_n.child
-      file_description_n = cv_list_n.next
-      self.cvs = cv_list_n.children.map do |cv_n|
-        Mspire::Mzml::CV.from_xml(cv_n)
-      end
-      self.file_description = Mspire::Mzml::FileDescription.from_xml(file_description_n)
-      next_n = file_description_n.next
-      loop do
-        case next_n.name
-        when 'referenceableParamGroupList'
-          # get a hash ready
-        when 'sampleList'
-          # set objects
-        when 'softwareList'  # required
-          # set objects
-        when 'instrumentConfigurationList'
-          # set objects
-        when 'dataProcessingList'
-          # set objects
-        when 'run'
-          # get defaults ready
-          break
-        end
-        next_n = next_n.next
-      end
-    end
-
-    class << self
 
-      # read-only right now
-      def open(filename, &block)
-        File.open(filename) do |io|
-          block.call(self.new(io))
-        end
+      def each_spectrum(&block)
+        @run.spectrum_list.each(&block)
       end
 
-      def foreach(filename, &block)
-        block or return enum_for(__method__, filename)
-        open(filename) do |mzml|
-          mzml.each(&block)
-        end
-      end
-    end
+      alias_method :each, :each_spectrum
 
-    # name can be :spectrum or :chromatogram
-    def get_xml_string(start_byte, name=:spectrum)
-      io.seek(start_byte)
-      data = []
-      regexp = %r{</#{name}>}
-      io.each_line do |line|
-        data << line 
-        #unless (line.index('<binary') && line[-12..-1].include?('</binary>'))
-          break if regexp.match(line)
-        #end
+      # @param [Object] arg an index number (Integer) or id string (String)
+      # @return [Mspire::Mzml::Spectrum] a spectrum object
+      def spectrum(arg)
+        run.spectrum_list[arg]
       end
-      data.join
-    end
+      alias_method :'[]', :spectrum
 
-    def each_spectrum(&block)
-      block or return enum_for(__method__)
-      (0...@index_list[:spectrum].size).each do |int|
-        block.call(spectrum(int))
+      # @param [Object] arg an index number (Integer) or id string (String)
+      # @return [Mspire::Mzml::Chromatogram] a spectrum object
+      def chromatogram(arg)
+        run.chromatogram_list[arg]
       end
-      #block_given? or return enum_for(__method__)
-      #(0...@index_list[:spectrum].size).each do |int|
-      #  yield spectrum(int)
-      #end
-    end
 
-    # returns the Nokogiri::XML::Node object associated with each spectrum
-    def each_spectrum_node(&block)
-      @index_list[:spectrum].each do |start_byte|
-        block.call spectrum_node_from_start_byte(start_byte)
+      def num_chromatograms
+        run.chromatogram_list.size
       end
-    end
-
-    alias_method :each, :each_spectrum
-
-    # returns the nokogiri xml node for the spectrum at that index
-    def spectrum_node(index)
-      spectrum_node_from_start_byte(@index_list[:spectrum][index])
-    end
 
-    def spectrum_node_from_start_byte(start_byte)
-      xml = get_xml_string(start_byte, :spectrum)
-      doc = Nokogiri::XML.parse(xml, nil, @encoding, Parser::NOBLANKS)
-      doc.root
-    end
-
-    # @param [Object] arg an index number (Integer) or id string (String)
-    # @return [Mspire::Spectrum] a spectrum object
-    def spectrum(arg)
-      start_byte = index_list[0].start_byte(arg)
-      spec_n = spectrum_node_from_start_byte(start_byte)
-      Mspire::Mzml::Spectrum.from_xml(spec_n)
-    end
-
-    # returns the number of spectra
-    def size
-      @index_list[:spectrum].size
-    end
-
-    alias_method :'[]', :spectrum
-
-    # @param [Integer] scan_num the scan number 
-    # @return [Mspire::Spectrum] a spectrum object, or nil if not found
-    # @raise [ScanNumbersNotUnique] if scan numbers are not unique
-    # @raise [ScanNumbersNotFound] if spectra exist but scan numbers were not
-    #   found
-    def spectrum_from_scan_num(scan_num)
-      @scan_to_index ||= @index_list[0].create_scan_index
-      raise ScanNumbersNotUnique if @scan_to_index == false
-      raise ScanNumbersNotFound if @scan_to_index == nil
-      spectrum(@scan_to_index[scan_num])
-    end
-
-    # @return [Mspire::Mzml::IndexList] or nil if there is no indexList in the
-    # mzML
-    def read_index_list
-      if offset=Mspire::Mzml::Index.index_offset(@io)
-        @io.seek(offset)
-        xml = Nokogiri::XML.parse(@io.read, nil, @encoding, Parser::NOBLANKS)
-        index_list = xml.root
-        num_indices = index_list['count'].to_i
-        array = index_list.children.map do |index_n|
-          #index = Index.new(index_n['name'])
-          index = Index.new
-          index.name = index_n['name'].to_sym
-          ids = []
-          index_n.children.map do |offset_n| 
-            index << offset_n.text.to_i 
-            ids << offset_n['idRef']
-          end
-          index.ids = ids
-          index
-        end
-        IndexList.new(array)
-      end
-    end
-    # Reads through and captures start bytes
-    # @return [Mspire::Mzml::IndexList] 
-    def create_index_list
-      indices_hash = @io.bookmark(true) do |inner_io|   # sets to beginning of file
-        indices = {:spectrum => {}, :chromatogram => {}}
-        byte_total = 0
-        @io.each do |line|
-          if md=%r{<(spectrum|chromatogram).*?id=['"](.*?)['"][ >]}.match(line)
-            indices[md[1].to_sym][md[2]] = byte_total + md.pre_match.bytesize
-          end
-          byte_total += line.bytesize
-        end
-        indices
+      # returns the number of spectra
+      def length
+        run.spectrum_list.size
       end
-
-      indices = indices_hash.map do |sym, hash|
-        indices = Index.new ; ids = []
-        hash.each {|id, startbyte| ids << id ; indices << startbyte }
-        indices.ids = ids ; indices.name = sym
-        indices
+      alias_method :size, :length
+
+      # @param [Integer] scan_num the scan number 
+      # @return [Mspire::Spectrum] a spectrum object, or nil if not found
+      # @raise [ScanNumbersNotUnique] if scan numbers are not unique
+      # @raise [ScanNumbersNotFound] if spectra exist but scan numbers were not
+      #   found
+      def spectrum_from_scan_num(scan_num)
+        @scan_to_index ||= @index_list[0].create_scan_index
+        raise ScanNumbersNotUnique if @scan_to_index == false
+        raise ScanNumbersNotFound if @scan_to_index == nil
+        spectrum(@scan_to_index[scan_num])
       end
-      IndexList.new(indices)
-    end
-
-    # reads or creates an index list
-    # @return [Array] an array of indices
-    def get_index_list
-      read_index_list || create_index_list
     end
-
+    include Convenience
+    
     # Because mzml files are often very large, we try to avoid storing the
     # entire object tree in memory before writing.
     # 
@@ -374,7 +236,7 @@ module Mspire
         if @referenceable_param_groups
           Mspire::Mzml::ReferenceableParamGroup.list_xml(@referenceable_param_groups, mzml_n)
         end
-        if @samples
+        if @samples && @samples.size > 0
           Mspire::Mzml::Sample.list_xml(@samples, mzml_n)
         end
         Mspire::Mzml::Software.list_xml(@software_list, mzml_n)

data/lib/mspire/plms1.rb

@@ -118,6 +118,9 @@ module Mspire
         out.puts scan_numbers.join(' ')
         out.puts times.join(' ')
         spectra.each do |spectrum|
+          puts "HIAYDSFA DSF"
+          puts spectrum.class
+          p spectrum
           out.puts spectrum.size
           if spectrum.size > 0
             out.puts spectrum.mzs.size

data/spec/mspire/cv/paramable_spec.rb

@@ -5,16 +5,16 @@ require 'mspire/cv/param'
 require 'mspire/user_param'
 require 'mspire/mzml/referenceable_param_group'
 
-class MockObject
+class ParamableObject
   include Mspire::CV::Paramable
 end
 
 describe 'Mspire::CV::Paramable' do
 
   subject do
-    paramable = MockObject.new :params => ['MS:1000007', ['MS:1000511', 2]]
+    paramable = ParamableObject.new.describe_many!(['MS:1000007', ['MS:1000511', 2]])
     paramable.user_params << Mspire::UserParam.new('hello', 477)
-    paramable.ref_param_groups << Mspire::Mzml::ReferenceableParamGroup.new('id1', :params => [['MS:1000512', 'filter string']])
+    paramable.ref_param_groups << Mspire::Mzml::ReferenceableParamGroup.new('id1').describe!('MS:1000512', 'filter string')
     paramable
   end
 

data/spec/mspire/mzml/data_array_spec.rb

@@ -1,16 +1,29 @@
 require 'spec_helper'
 
+require 'nokogiri'
+require 'mspire/mzml/parser'
+
 require 'mspire/mzml/data_array'
 
 describe Mspire::Mzml::DataArray do
 
-  it 'can be created from base64 binary data' do
-    d_ar = Mspire::Mzml::DataArray.from_binary('eJxjYACBD/YMEOAAoTgcABe3Abg=', :float64, zlib=true)
-    d_ar.is_a?(Array)
-    d_ar.should == [1.0, 2.0, 3.0]
-    d_ar = Mspire::Mzml::DataArray.from_binary('eJxjYACBD/YMEOAAoTgcABe3Abg=', ['MS:1000523', 'MS:1000574'])
+  let(:xml_node) do
+    string = %Q{<binaryDataArray encodedLength="1588">
+      <cvParam cvRef="MS" accession="MS:1000523" name="64-bit float" value=""/>
+      <cvParam cvRef="MS" accession="MS:1000574" name="zlib compression" value=""/>
+      <cvParam cvRef="MS" accession="MS:1000514" name="m/z array" value="" unitCvRef="MS" unitAccession="MS:1000040" unitName="m/z"/>
+      <binary>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</binary>
+    </binaryDataArray>}
+    Nokogiri::XML.parse(string, nil, 'utf-8', Mspire::Mzml::Parser::NOBLANKS).root
+  end
+
+  it 'can be created from base64 binary xml' do
+    d_ar = Mspire::Mzml::DataArray.from_xml(xml_node, {})
     d_ar.is_a?(Array)
-    d_ar.should == [1.0, 2.0, 3.0]
+    # these are just frozen
+    d_ar.size.should == 315
+    d_ar.first.round(3).should == 151.962
+    d_ar.last.round(3).should == 938.548
   end
 
   it "can be initialized like any ol' array" do

data/spec/mspire/mzml/file_content_spec.rb

@@ -6,7 +6,7 @@ require 'mspire/mzml/file_content'
 describe Mspire::Mzml::FileContent do 
 
   it 'can be initialized with params' do
-    filecontent = Mspire::Mzml::FileContent.new(:params => ['MS:1000579', ['IMS:1000080', "{9D501BDC-5344-4916-B7E9-7E795B02C856}"]])
+    filecontent = Mspire::Mzml::FileContent.new.describe_many!(['MS:1000579', ['IMS:1000080', "{9D501BDC-5344-4916-B7E9-7E795B02C856}"]])
 
     desc = filecontent.params
     desc.size.should == 2
@@ -18,9 +18,6 @@ describe Mspire::Mzml::FileContent do
       xml.should match(regexp)
     end
   end
-
-  it 'can be created from xml'
-
 end
 
 

data/spec/mspire/mzml/index_list_spec.rb

@@ -1,7 +1,6 @@
 require 'spec_helper'
 
-require 'mspire/mzml'
-require 'mspire/mzml/index_list'
+require 'mspire/mzml' # require index and index_list
 
 describe 'non-indexed uncompressed peaks, mzML file' do
   subject { TESTFILES + "/mspire/mzml/openms.noidx_nocomp.12.mzML" }
@@ -26,12 +25,7 @@ describe 'non-indexed uncompressed peaks, mzML file' do
         "scan=10935", "scan=10936", "scan=10937", 
         "scan=10938", "scan=10939", "scan=10940"
       ]
-      # right now, the behavior is to expect a chromatogram index, even if
-      # there are no chromatograms... is that the right behavior???
-      chromatogram_idx = index_list[:chromatogram]
-      chromatogram_idx.name.should == :chromatogram
-      chromatogram_idx.should == []
-      chromatogram_idx.ids.should == []
+      index_list[:chromatogram].should == nil
     end
   end
 end
@@ -52,7 +46,7 @@ describe 'indexed, compressed peaks, mzML file' do
     correct_index_list = lambda do |index_list|
       spectrum_idx = index_list[:spectrum]
       spectrum_idx.name.should == :spectrum
-      spectrum_idx.should == [4398, 219667, 227895]
+      spectrum_idx.should == [4397, 219666, 227894]
       spectrum_idx.ids.should == [
         "controllerType=0 controllerNumber=1 scan=1", 
         "controllerType=0 controllerNumber=1 scan=2", 
@@ -60,7 +54,7 @@ describe 'indexed, compressed peaks, mzML file' do
       ]
       chromatogram_idx = index_list[:chromatogram]
       chromatogram_idx.name.should == :chromatogram
-      chromatogram_idx.should == [239184]
+      chromatogram_idx.should == [239183]
       chromatogram_idx.ids.should == ["TIC"]
     end
 
@@ -71,8 +65,7 @@ describe 'indexed, compressed peaks, mzML file' do
     end
 
     it 'can create the index manually, if requested' do
-      mzml = Mspire::Mzml.new(@io)
-      index_list =  mzml.create_index_list
+      index_list = Mspire::Mzml::IndexList.create_index_list(@io)
       correct_index_list.call(index_list)
     end
 

data/spec/mspire/mzml/plms1_spec.rb

@@ -15,14 +15,13 @@ describe 'converting mzml to plms1' do
     end
 
     it 'can be converted into a plms1 object' do
-      scan_nums = (10929..10940).to_a
-      times =[6604.58, 6605.5, 6605.91, 6606.48, 6606.98, 6607.53, 6607.93, 6608.49, 6608.92, 6609.49, 6609.94, 6610.53]
+      scan_nums = [10929, 10931, 10933, 10935, 10937, 10939, 10940]
+      times =[ 6604.58, 6605.91, 6606.98, 6607.93, 6608.92, 6609.94, 6610.53]
       plms1 = @mzml.to_plms1
       plms1.spectra.respond_to?(:each).should be_true
       plms1.times.should == times
       plms1.scan_numbers.should == scan_nums
       plms1.spectra.each do |spec|
-        spec.size.should == 2
         spec.should be_a_kind_of(Mspire::SpectrumLike)
         spec.mzs.should == []
         spec.intensities.should == []
@@ -43,20 +42,17 @@ describe 'converting mzml to plms1' do
     end
 
     it 'can be converted into a plms1 object' do
-      #scan_nums = ###
-      #times =[6604.58, 6605.5, 6605.91, 6606.48, 6606.98, 6607.53, 6607.93, 6608.49, 6608.92, 6609.49, 6609.94, 6610.53]
       plms1 = @mzml.to_plms1
       plms1.spectra.respond_to?(:each).should be_true
-      plms1.times.should == [1981.5726, 1982.1077, 1982.4020999999998]
-      plms1.scan_numbers.should == [1, 2, 3] 
-      sizes = [20168, 315, 634]
+      plms1.times.should == [1981.5726]
+      plms1.scan_numbers.should == [1]
+      sizes = [20168]
       plms1.spectra.zip(sizes).each do |spec,exp_size|
         spec.should be_a_kind_of(Mspire::SpectrumLike)
         spec.size.should == 2
         spec.mzs.size.should == exp_size
         spec.intensities.size.should == exp_size
       end
-      #plms1.write("tmp.tmp.bin")
     end
 
   end

data/spec/mspire/mzml/referenceable_param_group_spec.rb

@@ -8,8 +8,8 @@ describe Mspire::Mzml::ReferenceableParamGroup do
   it 'is created with an id and params' do
     # the id is required for these objects
     # no compression
-    rfgroup1 = Mspire::Mzml::ReferenceableParamGroup.new("mzArray", params: ['MS:1000576', 'MS:1000514'])
-    rfgroup2 = Mspire::Mzml::ReferenceableParamGroup.new("intensityArray", params: ['MS:1000576', 'MS:1000515'])
+    rfgroup1 = Mspire::Mzml::ReferenceableParamGroup.new("mzArray").describe_many!(['MS:1000576', 'MS:1000514'])
+    rfgroup2 = Mspire::Mzml::ReferenceableParamGroup.new("intensityArray").describe_many!(['MS:1000576', 'MS:1000515'])
 
     b = Builder::XmlMarkup.new(:indent => 2)
     z = Mspire::Mzml::ReferenceableParamGroup.list_xml([rfgroup1, rfgroup2], b)
@@ -20,7 +20,7 @@ describe Mspire::Mzml::ReferenceableParamGroup do
   end
 
   it '#to_xml gives a ReferenceableParamGroupRef' do
-    rfgroup1 = Mspire::Mzml::ReferenceableParamGroup.new("mzArray", params: ['MS:1000576', 'MS:1000514'])
+    rfgroup1 = Mspire::Mzml::ReferenceableParamGroup.new("mzArray").describe_many!(['MS:1000576', 'MS:1000514'])
     builder = Builder::XmlMarkup.new(:indent => 2)
     rfgroup1.to_xml(builder)
     xml = builder.to_xml

data/spec/mspire/mzml/source_file_spec.rb

@@ -5,7 +5,7 @@ require 'builder'
 
 describe 'making a SourceFile' do
   it 'can be generated with params and a block' do
-    source_file = Mspire::Mzml::SourceFile.new("someFileID", "filename.mzML", "/home/jtprince/tmp", params: ['MS:1000584'])
+    source_file = Mspire::Mzml::SourceFile.new("someFileID", "filename.mzML", "/home/jtprince/tmp").describe!('MS:1000584')
 
     params = source_file.params
     params.size.should == 1
@@ -18,7 +18,6 @@ describe 'making a SourceFile' do
     end
   end
 
-  it 'can be created from xml'
 end
 
 

data/spec/mspire/mzml/spectrum_list_spec.rb

@@ -0,0 +1,54 @@
+require 'spec_helper'
+
+require 'mspire/mzml/spectrum_list'
+require 'builder'
+
+class MockSpectrum
+  attr_accessor :index
+  attr_accessor :id
+  attr_accessor :source_file
+  attr_accessor :data_processing
+  def initialize(id)
+    @id = id
+  end
+  def to_xml(builder, default_ids)
+    builder.mockSpectrum {}
+    builder
+  end
+end
+
+MockObject = Struct.new(:id)
+
+describe Mspire::Mzml::SpectrumList do
+
+  let :speclist do
+    Mspire::Mzml::SpectrumList.new(MockObject.new(:default_data_processing), [MockSpectrum.new('spec1')], { 'spec1' => 0 })
+  end
+
+  specify '#[Integer]' do
+    speclist[0].id.should == 'spec1'
+  end
+
+  specify '#[id]' do
+    speclist['spec1'].id.should == 'spec1'
+  end
+
+  specify '#create_id_to_index!' do
+    orig_index = speclist.id_to_index
+    speclist.create_id_to_index!
+    new_index = speclist.id_to_index
+    new_index.should == orig_index
+    new_index.equal?(orig_index).should be_false
+  end
+
+  specify '#to_xml' do
+    require 'stringio' 
+    st = StringIO.new
+    builder = Builder::XmlMarkup.new(:target => st)
+    speclist.to_xml(builder, {})
+    st.string.should == "<spectrumList count=\"1\" defaultDataProcessingRef=\"default_data_processing\"><mockSpectrum></mockSpectrum></spectrumList>"
+  end
+
+end
+
+  

data/spec/mspire/mzml/spectrum_spec.rb

@@ -16,8 +16,7 @@ describe Mspire::Mzml::Spectrum do
     end
 
     it 'gathers key data for ms1 spectrum' do
-      xml_node = @mzml.spectrum_node(0)
-      spec = Mspire::Mzml::Spectrum.from_xml(xml_node)
+      spec = @mzml.run.spectrum_list[0]
 
       # convenient access to common attributes 
       spec.retention_time.should == 1981.5726
@@ -36,8 +35,7 @@ describe Mspire::Mzml::Spectrum do
     end
 
     it 'gathers key data for ms2 spectrum' do
-      xml_node = @mzml.spectrum_node(1)
-      spec = Mspire::Mzml::Spectrum.from_xml(xml_node)
+      spec = @mzml.run.spectrum_list[1]
 
       # convenient access to common attributes 
       spec.retention_time.should == 1982.1077