gaworkflow/frontend/htsw_reports/libinfopar.py

   1 from xml.sax import make_parser
   2 from xml.sax.handler import ContentHandler
   3
   4
   5 '''
   6 Example library node from LibraryInfo.xml:
   7 <Library Name="SL14">
   8 <Track Flowcell="FC10135" Lane="4" Filename="071005_FC10135_s4_FoxP2_polyclonal_pfsk1_SL14.align_25.hg18.txt" Count=" 2438679" Complexity="4.51989e-06"/>
   9 <Track Flowcell="FC11977" Lane="6" Filename="070928_FC11977_s6_FoxP2_polyclonal_pfsk1_SL14.align_25.hg18.txt" Count=" 2007880" Complexity="0"/>
  10 <Track Flowcell="FC13593" Lane="5" Filename="071002_FC13593_s5_FoxP2_polyclonal_pfsk1_SL14.align_25.hg18.txt" Count=" 2533720" Complexity="1.97771e-06"/>
  11 </Library>
  12 '''
  13 class LibInfoHandler(ContentHandler):
  14
  15   def __init__ (self, searchTerm):
  16     self.searchTerm= searchTerm
  17     self.currlibid = ''
  18     self.LanesCount, self.ReadsCount = 0, 0
  19     self.Msg = ''
  20
  21   def startElement(self, name, attrs):
  22     if name == 'Library':
  23       self.currlibid = attrs.get('Name',"")
  24     elif name == 'Track' and self.searchTerm == self.currlibid:
  25       self.LanesCount += len(attrs.get('Lane',""))
  26       self.ReadsCount += int(attrs.get('Count',""))
  27     else:
  28       self.Msg += ' | name = '+name+', currlibid = '+ self.currlibid
  29     return
  30
  31   #def characters (self, ch):
  32     # return ..
  33
  34   #def endElement(self, name):
  35     # return ..
  36
  37
  38 ## TO DO: Change this to read the LibraryInfo.xml only ONCE per ReoprtRequest (do it in the models.py). + Read it directly from the analysis_server
  39
  40 def getLibReads(libid):
  41   searchTerm= libid
  42   parser = make_parser()
  43   curHandler = LibInfoHandler(searchTerm)
  44   parser.setContentHandler(curHandler)
  45   parser.parse(open('/gaworkflow/gaworkflow/frontend/htsw_reports/LibraryInfo.xml'))
  46   arRes = []
  47   arRes.append(curHandler.LanesCount)
  48   arRes.append(curHandler.ReadsCount)
  49   return arRes
  50