mspire 0.7.18 → 0.8.0

data/spec/mspire/mzml_spec.rb

@@ -1,13 +1,222 @@
 require 'spec_helper'
-require 'builder'
 
+require 'builder'
 require 'mspire/mzml'
 
+require 'mspire/mzml/file_description'
+require 'mspire/mzml/run'
+
 describe Mspire::Mzml do
 
+  describe 'reading a SIM file' do
+    before do
+      @file = TESTFILES + "/mspire/mzml/1_BB7_SIM_478.5.mzML"
+      @io = File.open(@file)
+      @mzml = Mspire::Mzml.new(@io)
+    end
+    after do
+      @io.close
+    end
+
+    specify '#chromatogram' do
+      tic = @mzml.chromatogram(0)
+      tic.id.should == 'TIC'
+
+      sim = @mzml.chromatogram(1)
+      sim.id.should == 'SIM SIC 478.5'
+    end
+
+    specify '#num_chromatograms' do
+      @mzml.num_chromatograms.should == 2
+    end
+
+    specify '#each_chromatogram' do
+      @mzml.each_chromatogram do |chrm|
+        chrm.should be_a(Mspire::Mzml::Chromatogram)
+        chrm.times.should be_an(Array)
+        chrm.intensities.should be_an(Array)
+        chrm.times.size.should == 72
+        chrm.intensities.size.should == 72
+      end
+    end
+  end
+
   describe 'reading an indexed, compressed peaks, mzML file' do
-    describe 'reading a spectrum' do
 
+    describe 'reading the header things' do
+      before do
+        @file = TESTFILES + "/mspire/mzml/j24z.idx_comp.3.mzML"
+        @io = File.open(@file)
+        @mzml = Mspire::Mzml.new(@io)
+      end
+      after do
+        @io.close
+      end
+
+      specify '#cvs - reads the cvList' do
+        cvs = @mzml.cvs
+        cvs.size.should == 2
+        cvs.first.id.should == 'MS'
+        cvs.last.id.should == 'UO'
+      end
+
+      specify '#file_description reads the fileDescription' do
+        @mzml.file_description.should be_a(Mspire::Mzml::FileDescription)
+      end
+
+      describe Mspire::Mzml::FileDescription do
+
+        let(:file_description) { @mzml.file_description }
+
+        specify '#file_content' do
+          fc = file_description.file_content
+          fc.fetch_by_acc("MS:1000579").should be_true
+          fc.fetch_by_acc("MS:1000580").should be_true
+          fc.fetch_by_acc("MS:1000550").should be_false
+          fc.params.size.should == 2
+        end
+
+        specify '#source_files' do
+          sfs = file_description.source_files
+          sfs.size.should == 1
+          sf = sfs.first
+          sf.id.should == 'RAW1'
+          sf.name.should == 'j24.raw'
+          sf.location.should == 'file://.'
+          sf.params.size.should == 3
+          sha1 = sf.param_by_acc('MS:1000569')
+          sha1.name.should == 'SHA-1'
+          sha1.accession.should == 'MS:1000569'
+          sha1.value.should == "6023d121fb6ca7f19fada3b6c5e4d5da09c95f12"
+        end
+      end
+
+      specify '#referenceable_param_groups (reads the referenceableParamGroupList)' do
+        rpgs = @mzml.referenceable_param_groups
+        rpgs.size.should == 1
+        rpg = rpgs.first
+        rpg.id.should == 'CommonInstrumentParams'
+        prms = rpg.params
+        prms.first.to_a.should == ["MS", "MS:1000449", "LTQ Orbitrap", nil, nil]
+        prms.last.to_a.should == ["MS", "MS:1000529", "instrument serial number", "SN1025B", nil]
+      end
+
+      it 'reads the softwareList' do
+        sl = @mzml.software_list
+        sl.size.should == 2
+        xcal = sl.first
+        xcal.id.should == 'Xcalibur'
+        xcal.version.should == '2.4 SP1'
+        xcal.params.first.to_a.should == ["MS", "MS:1000532", "Xcalibur", nil, nil]
+
+        pwiz = sl.last
+        pwiz.id.should == 'pwiz'
+        pwiz.version.should == "2.1.2086"
+        pwiz.params.first.to_a.should == ["MS", "MS:1000615", "ProteoWizard", nil, nil]
+      end
+
+      
+      def component_is_correct(component, klass, accs)
+        component.should be_a(Mspire::Mzml.const_get(klass))
+        accs.each do |acc|
+          component.fetch_by_acc(acc).should be_true
+        end
+      end
+
+      it 'reads the instrumentConfigurationList' do
+        ics = @mzml.instrument_configurations
+        ics.size.should == 2
+        ic1 = ics.first
+        ic1.id.should == 'IC1'
+
+        # grabbing a referenceable param!
+        ic1.fetch_by_acc('MS:1000449').should be_true
+        ic1.fetch_by_acc('MS:1000529').should be_true
+
+        %w{Source Analyzer Detector}.zip(
+          [["MS:1000398", "MS:1000485"], ["MS:1000484"], ["MS:1000624"]], 
+          ic1.components
+        ).each do |klass,accs,component|
+          component_is_correct(component, klass, accs)
+        end
+
+        ic2 = ics.last
+
+        %w{Source Analyzer Detector}.zip(
+          [["MS:1000398", "MS:1000485"], ["MS:1000083"], ["MS:1000253"]], 
+          ic2.components
+        ).each do |klass,accs,component|
+          component_is_correct(component, klass, accs)
+        end
+      end
+
+      it 'reads the dataProcessingList' do
+        dpl = @mzml.data_processing_list
+        dpl.size.should == 1
+        dp = dpl.first
+
+        dp.id.should == 'pwiz_Reader_Thermo_conversion'
+        pms = dp.processing_methods
+        pms.size.should == 1
+        pm = pms.first
+        pm.should be_a(Mspire::Mzml::ProcessingMethod)
+
+        # the order is not instrinsic to the object but to the container
+        # (i.e., it is an index)
+        dp.order(pm).should == 0
+        pm.software.should be_a(Mspire::Mzml::Software)
+        pm.params.first.to_a.should == ["MS", "MS:1000544", "Conversion to mzML", nil, nil]
+      end
+
+      it 'reads the run' do
+        run = @mzml.run
+        run.id.should == 'j24'
+
+        ic = run.default_instrument_configuration
+        ic.should be_a(Mspire::Mzml::InstrumentConfiguration)
+        ic.fetch_by_acc('MS:1000449').should be_true
+
+        run.start_time_stamp.should == "2010-07-08T11:34:52Z"
+        sf = run.default_source_file
+        sf.should be_a(Mspire::Mzml::SourceFile)
+        sf.id.should == 'RAW1'
+
+        run.sample.should be_nil # no sample
+      end
+
+      describe Mspire::Mzml::Run do
+
+        specify '#spectrum_list' do
+          sl = @mzml.run.spectrum_list
+          sl.should be_a(Mspire::Mzml::SpectrumList)
+          sl.default_data_processing.should be_a(Mspire::Mzml::DataProcessing)
+          sl.default_data_processing.id.should == 'pwiz_Reader_Thermo_conversion'
+          sl.size.should == 3
+
+          sl.each do |spec|
+            spec.should be_a(Mspire::Mzml::Spectrum)
+            spec.params.size.should == 9
+            scan_list = spec.scan_list
+            scan_list.size.should == 1
+            scan_list.params.size.should == 1
+          end
+        end
+
+        specify '#chromatogram_list' do
+          cl = @mzml.run.chromatogram_list
+          cl.should be_a(Mspire::Mzml::ChromatogramList)
+          cl.size.should == 1
+          cl.default_data_processing.should be_a(Mspire::Mzml::DataProcessing)
+          cl.default_data_processing.id.should == 'pwiz_Reader_Thermo_conversion'
+
+          cl.each do |chrom|
+            chrom.should be_a(Mspire::Mzml::Chromatogram)
+          end
+        end
+      end
+    end
+
+    describe 'reading a spectrum' do
       before do
         @file = TESTFILES + "/mspire/mzml/j24z.idx_comp.3.mzML"
         @io = File.open(@file)
@@ -17,7 +226,7 @@ describe Mspire::Mzml do
         @io.close
       end
 
-      it '#spectrum (or #[]) returns a spectrum when queried by index (Integer)' do
+      specify '#spectrum (or #[]) returns a spectrum when queried by index (Integer)' do
         spectrum = @mzml.spectrum(1) # getting the second spectrum
         spectrum1 = @mzml[1] # can get with brackets
         spectrum.ms_level.should == 2
@@ -25,12 +234,19 @@ describe Mspire::Mzml do
         spectrum.should be_a(Mspire::Mzml::Spectrum)
         spectrum.should respond_to(:mzs)
         spectrum.should respond_to(:intensities)
+
+        spectrum.params.size.should == 9
+
         spectrum.mzs.size.should == 315
         spectrum.intensities.size.should == 315
         spectrum.mzs[2].should be_within(1e-10).of(164.32693481445312)
       end
 
-      it '#spectrum (or #[]) returns a spectrum when queried by id (String)' do
+      specify '#spectrum always returns spectrum with data_processing object (uses default if none given)' do
+        @mzml.spectrum(1).data_processing.should be_a(Mspire::Mzml::DataProcessing)
+      end
+
+      specify '#spectrum (or #[]) returns a spectrum when queried by id (String)' do
         spectrum = @mzml.spectrum("controllerType=0 controllerNumber=1 scan=2")
         spectrum1 = @mzml["controllerType=0 controllerNumber=1 scan=2"]
         spectrum.ms_level.should == 2
@@ -38,7 +254,7 @@ describe Mspire::Mzml do
         spectrum.should be_a(Mspire::Mzml::Spectrum)
       end
 
-      it 'goes through spectrum with #each or #each_spectrum' do
+      specify '#each or #each_spectrum goes through each spectrum' do
         mz_sizes = [20168, 315, 634]
         centroided_list = [false, true, true]
         @mzml.each do |spec|
@@ -62,19 +278,24 @@ describe Mspire::Mzml do
         lambda {iter.next}.should raise_error
       end
 
-      # not quite ready for this one yet
-      xit 'contains scans linked to their instrument config objects' do
-        instr_config_first = @mzml.file_description.instrument_configurations[0]
-        instr_config_last = @mzml.file_description.instrument_configurations[1]
+      it 'contains scans linked to their instrument config objects' do
+        # this is tricky because we need to use the default instrument config
+        # from the run for the first scan and an element ref for the second...
+        [0,1].each do |i| 
+          @mzml[i].scan_list.first.instrument_configuration.should be_a(Mspire::Mzml::InstrumentConfiguration)
+        end
+        instr_config_first = @mzml.instrument_configurations[0]
+        instr_config_last = @mzml.instrument_configurations[1]
+
         @mzml[0].scan_list.first.instrument_configuration.should == instr_config_first 
         @mzml[1].scan_list.first.instrument_configuration.should == instr_config_last
       end
 
       it 'can gracefully determine the m/z with highest peak in select scans' do
         highest_mzs = Mspire::Mzml.foreach(@file).select {|v| v.ms_level > 1 }.map do |spec|
-          spec.peaks.sort_by(&:last).first.first
+          spec.peaks.max_by(&:last)[0]
         end
-        highest_mzs.map(&:round).should == [453, 866]
+        highest_mzs.map(&:round).should == [746, 644]
       end
     end
   end
@@ -86,8 +307,9 @@ describe Mspire::Mzml do
     end
 
     it 'writes MS1 and MS2 spectra' do
-      # params: profile and ms_level 1
-      spec1 = Mspire::Mzml::Spectrum.new('scan=1', params: ['MS:1000128', ['MS:1000511', 1]]) do |spec|
+      spec1 = Mspire::Mzml::Spectrum.new('scan=1') do |spec|
+        # profile and ms_level 1
+        spec.describe_many!(['MS:1000128', ['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|
@@ -98,10 +320,9 @@ describe Mspire::Mzml do
         end
       end
 
-      # centroid,  ms_level 2, MSn spectrum, 
-      spec_params = ['MS:1000127', ['MS:1000511', 2], "MS:1000580"]
-
-      spec2 = Mspire::Mzml::Spectrum.new('scan=2', params: spec_params) do |spec| 
+      spec2 = Mspire::Mzml::Spectrum.new('scan=2') do |spec| 
+        # centroid,  ms_level 2, MSn spectrum, 
+        spec.describe_many!(['MS:1000127', ['MS:1000511', 2], "MS:1000580"])
         spec.data_arrays = [[1,2,3.5], [5,6,5]]
         spec.scan_list = Mspire::Mzml::ScanList.new do |sl|
           scan = Mspire::Mzml::Scan.new do |scan|
@@ -110,7 +331,7 @@ describe Mspire::Mzml do
           end
           sl << scan
         end
-        precursor = Mspire::Mzml::Precursor.new( spec1 )
+        precursor = Mspire::Mzml::Precursor.new( spec1.id )
         si = Mspire::Mzml::SelectedIon.new
         # the selected ion m/z:
         si.describe! "MS:1000744", 2.0
@@ -129,15 +350,14 @@ describe Mspire::Mzml do
           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").describe!('MS:1000031')
         mzml.instrument_configurations << default_instrument_config
         software = Mspire::Mzml::Software.new
         mzml.software_list << software
         default_data_processing = Mspire::Mzml::DataProcessing.new("did_nothing")
         mzml.data_processing_list << default_data_processing
         mzml.run = Mspire::Mzml::Run.new("little_run", default_instrument_config) do |run|
-          spectrum_list = Mspire::Mzml::SpectrumList.new(default_data_processing)
-          spectrum_list.push(spec1, spec2)
+          spectrum_list = Mspire::Mzml::SpectrumList.new(default_data_processing, [spec1, spec2])
           run.spectrum_list = spectrum_list
         end
       end

data/spec/spec_helper.rb

@@ -11,6 +11,7 @@ TESTFILES = File.dirname(__FILE__) + '/testfiles'
 Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
 
 RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
   config.color_enabled = true
   config.tty = true
   config.formatter = :documentation  # :progress, :html, :textmate

data/spec/testfiles/mspire/mzml/1_BB7_SIM_478.5.mzML

@@ -0,0 +1,103 @@
+<?xml version="1.0" encoding="ISO-8859-1"?>
+<indexedmzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://psi.hupo.org/ms/mzml http://psidev.info/files/ms/mzML/xsd/mzML1.1.1_idx.xsd">
+  <mzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://psi.hupo.org/ms/mzml http://psidev.info/files/ms/mzML/xsd/mzML1.1.0.xsd" id="1 BB7 SIM 478.5" version="1.1.0">
+    <cvList count="2">
+      <cv id="MS" fullName="Proteomics Standards Initiative Mass Spectrometry Ontology" version="3.7.3" URI="http://psidev.cvs.sourceforge.net/*checkout*/psidev/psi/psi-ms/mzML/controlledVocabulary/psi-ms.obo"/>
+      <cv id="UO" fullName="Unit Ontology" version="18:03:2011" URI="http://obo.cvs.sourceforge.net/*checkout*/obo/obo/ontology/phenotype/unit.obo"/>
+    </cvList>
+    <fileDescription>
+      <fileContent>
+        <cvParam cvRef="MS" accession="MS:1001472" name="selected ion monitoring chromatogram" value=""/>
+      </fileContent>
+      <sourceFileList count="1">
+        <sourceFile id="RAW1" name="1 BB7 SIM 478.5.RAW" location="file://D:/Manan Data/25 MARCH/25 MARCH 80 20 M W">
+          <cvParam cvRef="MS" accession="MS:1000768" name="Thermo nativeID format" value=""/>
+          <cvParam cvRef="MS" accession="MS:1000563" name="Thermo RAW file" value=""/>
+          <cvParam cvRef="MS" accession="MS:1000569" name="SHA-1" value="eeaed7c644ebec89cbf80582e0829dcf40632b6f"/>
+        </sourceFile>
+      </sourceFileList>
+    </fileDescription>
+    <referenceableParamGroupList count="1">
+      <referenceableParamGroup id="CommonInstrumentParams">
+        <cvParam cvRef="MS" accession="MS:1000492" name="Thermo Electron instrument model" value=""/>
+        <cvParam cvRef="MS" accession="MS:1000529" name="instrument serial number" value="LC000249"/>
+        <userParam name="instrument model" value="LCQ"/>
+      </referenceableParamGroup>
+    </referenceableParamGroupList>
+    <softwareList count="2">
+      <software id="Xcalibur" version="2.0">
+        <cvParam cvRef="MS" accession="MS:1000532" name="Xcalibur" value=""/>
+      </software>
+      <software id="pwiz" version="2.2.2954">
+        <cvParam cvRef="MS" accession="MS:1000615" name="ProteoWizard" value=""/>
+      </software>
+    </softwareList>
+    <instrumentConfigurationList count="1">
+      <instrumentConfiguration id="IC">
+        <cvParam cvRef="MS" accession="MS:1000031" name="instrument model" value=""/>
+      </instrumentConfiguration>
+    </instrumentConfigurationList>
+    <dataProcessingList count="1">
+      <dataProcessing id="pwiz_Reader_Thermo_conversion">
+        <processingMethod order="0" softwareRef="pwiz">
+          <cvParam cvRef="MS" accession="MS:1000544" name="Conversion to mzML" value=""/>
+        </processingMethod>
+      </dataProcessing>
+    </dataProcessingList>
+    <run id="_x0031__x0020_BB7_x0020_SIM_x0020_478.5" defaultInstrumentConfigurationRef="IC" startTimeStamp="2012-03-26T17:07:56Z" defaultSourceFileRef="RAW1">
+      <chromatogramList count="2" defaultDataProcessingRef="pwiz_Reader_Thermo_conversion">
+        <chromatogram index="0" id="TIC" defaultArrayLength="72">
+          <cvParam cvRef="MS" accession="MS:1000235" name="total ion current chromatogram" value=""/>
+          <binaryDataArrayList count="2">
+            <binaryDataArray encodedLength="728">
+              <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:1000595" name="time array" value="" unitCvRef="UO" unitAccession="UO:0000031" unitName="minute"/>
+              <binary>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</binary>
+            </binaryDataArray>
+            <binaryDataArray encodedLength="288">
+              <cvParam cvRef="MS" accession="MS:1000521" name="32-bit float" value=""/>
+              <cvParam cvRef="MS" accession="MS:1000574" name="zlib compression" value=""/>
+              <cvParam cvRef="MS" accession="MS:1000515" name="intensity array" value="" unitCvRef="MS" unitAccession="MS:1000131" unitName="number of counts"/>
+              <binary>eJxjYMABHIxdGVoc3RhmcLkzXKlxZ1gu4c5w7KwbQ4WWG8OH6a4MDS9cGComuTGIlrkzpFx1YxB0cGeQfOPOUMDt0bD8qHvDpknuDD+uuTE4THBlqHjiCjc3JdWNweSoW0NUlzvDqiJ3hjMX3Bgsdrgx1Fi6MRz47YJwwBwXhoYpLgw1rUC5aW4MpRbuDN/+uTEU/HFlEOhwY2goRJj5ocGVQUHXlaFE343BSce9ganXncExxJ1hylc3hgxvN4YFvG4MChNdGAzYIHoebEGyBz8AACv9PyU=</binary>
+            </binaryDataArray>
+          </binaryDataArrayList>
+        </chromatogram>
+        <chromatogram index="1" id="SIM SIC 478.5" defaultArrayLength="72">
+          <cvParam cvRef="MS" accession="MS:1001472" name="selected ion monitoring chromatogram" value=""/>
+          <precursor>
+            <isolationWindow>
+              <cvParam cvRef="MS" accession="MS:1000827" name="isolation window target m/z" value="478.5" unitCvRef="MS" unitAccession="MS:1000040" unitName="m/z"/>
+              <cvParam cvRef="MS" accession="MS:1000828" name="isolation window lower offset" value="0.5" unitCvRef="MS" unitAccession="MS:1000040" unitName="m/z"/>
+              <cvParam cvRef="MS" accession="MS:1000829" name="isolation window upper offset" value="0.5" unitCvRef="MS" unitAccession="MS:1000040" unitName="m/z"/>
+            </isolationWindow>
+            <activation>
+            </activation>
+          </precursor>
+          <binaryDataArrayList count="2">
+            <binaryDataArray encodedLength="728">
+              <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:1000595" name="time array" value="" unitCvRef="UO" unitAccession="UO:0000031" unitName="minute"/>
+              <binary>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</binary>
+            </binaryDataArray>
+            <binaryDataArray encodedLength="288">
+              <cvParam cvRef="MS" accession="MS:1000521" name="32-bit float" value=""/>
+              <cvParam cvRef="MS" accession="MS:1000574" name="zlib compression" value=""/>
+              <cvParam cvRef="MS" accession="MS:1000515" name="intensity array" value="" unitCvRef="MS" unitAccession="MS:1000131" unitName="number of counts"/>
+              <binary>eJxjYMABHIxdGVoc3RhmcLkzXKlxZ1gu4c5w7KwbQ4WWG8OH6a4MDS9cGComuTGIlrkzpFx1YxB0cGeQfOPOUMDt0bD8qHvDpknuDD+uuTE4THBlqHjiCjc3JdWNweSoW0NUlzvDqiJ3hjMX3Bgsdrgx1Fi6MRz47YJwwBwXhoYpLgw1rUC5aW4MpRbuDN/+uTEU/HFlEOhwY2goRJj5ocGVQUHXlaFE343BSce9ganXncExxJ1hylc3hgxvN4YFvG4MChNdGAzYIHoebEGyBz8AACv9PyU=</binary>
+            </binaryDataArray>
+          </binaryDataArrayList>
+        </chromatogram>
+      </chromatogramList>
+    </run>
+  </mzML>
+  <indexList count="2">
+    <index name="chromatogram">
+      <offset idRef="TIC">3158</offset>
+      <offset idRef="SIM SIC 478.5">5334</offset>
+    </index>
+  </indexList>
+  <indexListOffset>8219</indexListOffset>
+  <fileChecksum>80aaa01cefde0abbd6178089a0187e7ae742ae95</fileChecksum>
+</indexedmzML>

data/spec/testfiles/mspire/mzml/j24z.idx_comp.3.mzML

@@ -74,7 +74,7 @@
       </dataProcessing>
     </dataProcessingList>
     <run id="j24" defaultInstrumentConfigurationRef="IC1" startTimeStamp="2010-07-08T11:34:52Z" defaultSourceFileRef="RAW1">
-      <spectrumList count="24" defaultDataProcessingRef="pwiz_Reader_Thermo_conversion">
+      <spectrumList count="3" defaultDataProcessingRef="pwiz_Reader_Thermo_conversion">
         <spectrum index="0" id="controllerType=0 controllerNumber=1 scan=1" defaultArrayLength="20168">
           <cvParam cvRef="MS" accession="MS:1000511" name="ms level" value="1"/>
           <cvParam cvRef="MS" accession="MS:1000579" name="MS1 spectrum" value=""/>
@@ -258,14 +258,14 @@
   </mzML>
   <indexList count="2">
     <index name="spectrum">
-      <offset idRef="controllerType=0 controllerNumber=1 scan=1">4398</offset>
-      <offset idRef="controllerType=0 controllerNumber=1 scan=2">219667</offset>
-      <offset idRef="controllerType=0 controllerNumber=1 scan=3">227895</offset>
+      <offset idRef="controllerType=0 controllerNumber=1 scan=1">4397</offset>
+      <offset idRef="controllerType=0 controllerNumber=1 scan=2">219666</offset>
+      <offset idRef="controllerType=0 controllerNumber=1 scan=3">227894</offset>
     </index>
     <index name="chromatogram">
-      <offset idRef="TIC">239184</offset>
+      <offset idRef="TIC">239183</offset>
     </index>
   </indexList>
-  <indexListOffset>240801</indexListOffset>
+  <indexListOffset>240800</indexListOffset>
   <fileChecksum>4204d7e91808d1976df85df5c97f239ff085090d</fileChecksum>
 </indexedmzML>

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mspire
 version: !ruby/object:Gem::Version
-  version: 0.7.18
+  version: 0.8.0
   prerelease: 
 platform: ruby
 authors:
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-07-17 00:00:00.000000000 Z
+date: 2012-07-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -192,7 +192,7 @@ description: mass spectrometry proteomics, lipidomics, and tools, a rewrite of m
   merging of ms-* gems
 email: jtprince@gmail.com
 executables:
-- mzml_to_imzml
+- mspire
 extensions: []
 extra_rdoc_files:
 - LICENSE
@@ -202,8 +202,9 @@ files:
 - README.rdoc
 - Rakefile
 - VERSION
-- bin/mzml_to_imzml
+- bin/mspire
 - lib/core_ext/array/in_groups.rb
+- lib/core_ext/enumerable.rb
 - lib/cv.rb
 - lib/cv/param.rb
 - lib/cv/referenceable_param_group_ref.rb
@@ -211,6 +212,7 @@ files:
 - lib/merge.rb
 - lib/mspire.rb
 - lib/mspire/bin.rb
+- lib/mspire/commandline.rb
 - lib/mspire/cv/obo.rb
 - lib/mspire/cv/param.rb
 - lib/mspire/cv/paramable.rb
@@ -260,14 +262,19 @@ files:
 - lib/mspire/mzml/data_processing.rb
 - lib/mspire/mzml/file_content.rb
 - lib/mspire/mzml/file_description.rb
+- lib/mspire/mzml/index.rb
 - lib/mspire/mzml/index_list.rb
 - lib/mspire/mzml/instrument_configuration.rb
+- lib/mspire/mzml/io_index.rb
+- lib/mspire/mzml/io_indexable_list.rb
 - lib/mspire/mzml/isolation_window.rb
 - lib/mspire/mzml/list.rb
+- lib/mspire/mzml/parser.rb
 - lib/mspire/mzml/plms1.rb
 - lib/mspire/mzml/precursor.rb
 - lib/mspire/mzml/processing_method.rb
 - lib/mspire/mzml/product.rb
+- lib/mspire/mzml/reader.rb
 - lib/mspire/mzml/referenceable_param_group.rb
 - lib/mspire/mzml/run.rb
 - lib/mspire/mzml/sample.rb
@@ -325,11 +332,11 @@ files:
 - spec/mspire/mzml/cv_spec.rb
 - spec/mspire/mzml/data_array_spec.rb
 - spec/mspire/mzml/file_content_spec.rb
-- spec/mspire/mzml/file_description_spec.rb
 - spec/mspire/mzml/index_list_spec.rb
 - spec/mspire/mzml/plms1_spec.rb
 - spec/mspire/mzml/referenceable_param_group_spec.rb
 - spec/mspire/mzml/source_file_spec.rb
+- spec/mspire/mzml/spectrum_list_spec.rb
 - spec/mspire/mzml/spectrum_spec.rb
 - spec/mspire/mzml_spec.rb
 - spec/mspire/peaklist_spec.rb
@@ -345,6 +352,7 @@ files:
 - spec/testfiles/mspire/ident/peptide/db/uni_11_sp_tr.msd_clvg2.min_aaseq4.yml
 - spec/testfiles/mspire/imzml/continuous_binary_check.ibd
 - spec/testfiles/mspire/imzml/processed_binary_check.ibd
+- spec/testfiles/mspire/mzml/1_BB7_SIM_478.5.mzML
 - spec/testfiles/mspire/mzml/j24z.idx_comp.3.mzML
 - spec/testfiles/mspire/mzml/mspire_simulated.MSn.check.mzML
 - spec/testfiles/mspire/mzml/openms.noidx_nocomp.12.mzML
@@ -390,7 +398,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.18
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: mass spectrometry proteomics, lipidomics, and tools

data/bin/mzml_to_imzml

@@ -1,9 +0,0 @@
-#!/usr/bin/env ruby
-# encoding: UTF-8
-
-require 'mspire/imzml/writer/commandline'
-
-argv = ARGV.dup
-ARGV.clear
-Mspire::Imzml::Writer::Commandline.run(argv)
-

data/spec/mspire/mzml/file_description_spec.rb

@@ -1,12 +0,0 @@
-require 'spec_helper'
-require 'mspire/mzml/file_description'
-require 'builder'
-
-describe 'creating mzml xml' do
-  describe Mspire::Mzml::FileDescription do
-
-    it 'creates valid xml'
-
-    it 'can be set from xml'
-  end
-end