parsedict.py

DTMK软件开发包,此为开源软件,是一款很好的医学图像开发资源.

    patt = re.compile('^B.[1-9].*Private .*$')
    if patt.match(s):
      return True
    patt = re.compile('^Table B.1.? .* Private .*$')
    if patt.match(s):
      return True
    patt = re.compile('^Note :.*$')
    if patt.match(s):
      return True
    patt = re.compile('^7.11.1$')
    if patt.match(s):
      return True
    return False

  def AddOutputLine(self,s):
    #print s
    assert not self.IsAComment(s)
    patt = re.compile('^([A-Za-z0-9 .#(),_/-]+) +\\(([0-9A-F]+), ?([0-9A-F]+)\\) ([A-Z][A-Z]) ([0-9]+)$') 
    m = patt.match(s)
    if m:
      ss = m.group(2).lower() + ' ' + m.group(3).lower() + ' ' + m.group(4) + ' ' + m.group(5) + ' ' + m.group(1)
      self._OutLines.append(ss + '\n')
    else:
      print 'OOOPs', s


"""
This class is meant to expand line like:
- (xxxx,xxxx to xxxx) xxxxxxxxxxxx
or
- (12xx, 3456) comment...

"""
class DicomV3Expander:
  def __init__(self):
    self._InputFilename = ''
    self._OutputFilename = ''
    self._OutLines = []

  def SetInputFileName(self,s):
    self._InputFilename = s

  def SetOutputFileName(self,s):
    self._OutputFilename = s
 
  # Function to turn into lower case a tag:
  # ex: (ABCD, EF01) -> (abcd, ef01)
  def LowerCaseTag(self,s):
    #print "Before:", s[:-1]
    patt = re.compile('^(\\([0-9a-fA-F]+,[0-9a-fA-F]+\\))(.*)$')
    m = patt.match(s)
    if m:
      s1 = m.group(1)
      s2 = m.group(2)
      return s1.lower() + s2
    else:
      patt = re.compile('^[0-9a-fA-F]+ [0-9a-fA-F]+ [A-Z][A-Z] [0-9n-] .*$')
      if patt.match(s):
        return s
      else:
        print "Impossible case:", s
        os.sys.exit(1)

  def AddOutputLine(self,s):
    if s.__class__ == list:
      for i in s:
        self._OutLines.append(i + '\n')
    else:
      self._OutLines.append(s + '\n')

  # Expand the line approriaetkly and also add it to the
  # _OutLines list
  def ExpandLine(self, s):
    assert s[-1] == '\n'
    s = s[:-1]  # remove \n
    list = []
    if self.NeedToExpansion(s, list):
      self.AddOutputLine(list) # list != []
    elif self.NeedGroupXXExpansion(s, list):
      self.AddOutputLine(list) # list != []
    elif self.NeedElemXXExpansion(s, list):
      self.AddOutputLine(list) # list != []
    else:
      self.AddOutputLine(self.LowerCaseTag(s))

  # If line is like:
  # (0020,3100 to 31FF) Source Image Ids RET
  def NeedToExpansion(self,s, list):
    patt = re.compile('^\\(([0-9a-fA-F]+),([0-9a-fA-F]+) to ([0-9a-fA-F]+)\\)(.*)$')
    m = patt.match(s)
    if m:
      #print m.groups()
      gr = m.group(1)
      el_start = '0x'+m.group(2)
      el_end = '0x'+m.group(3)
      for i in range(eval(el_start), eval(el_end)):
        el = hex(i)[2:]
        l = '('+gr+','+el+')'+m.group(4)
        list.append(l)
      return True
    return False

  # If line is like:
  # (50xx,1200) Number of Patient Related Studies IS 1
  def NeedGroupXXExpansion(self,s,list):
    patt = re.compile('^\\(([0-9a-fA-F]+)xx,([0-9a-fA-F]+)\\)(.*)$')
    m = patt.match(s)
    if m:
      #print m.groups()
      gr_start = m.group(1)
      el = m.group(2)
      #el_start = '0x'+m.group(2)
      #el_end = '0x'+m.group(3)
      start = '0x'+gr_start+'00'
      end   = '0x'+gr_start+'FF'
      for i in range(eval(start), eval(end)):
        gr = hex(i)[2:]
        l = '('+gr+','+el+')'+m.group(3)
        #print l
        list.append(l)
      return True
    return False

  # If line is like:
  # (2001,xx00) Number of Patient Related Studies IS 1
  def NeedElemXXExpansion(self,s,list):
    patt = re.compile('^([0-9a-fA-F]+) ([0-9a-fA-F]+)xx(.*)$')
    m = patt.match(s)
    if m:
      #print m.groups()
      gr = m.group(1)
      el_start = m.group(2)
      start = '0x00'
      end   = '0xFF'
      for i in range(eval(start), eval(end)):
        el = '%02x'% i
        l = '('+gr+','+el_start+el+')'+m.group(3)
        print l
        list.append(l)
      return True
    else:
      patt = re.compile('^([0-9a-fA-F]+) xx([0-9a-fA-F]+)(.*)$')
      m = patt.match(s)
      if m:
        #print m.groups()
        gr = m.group(1)
        el_start = m.group(2)
        start = '0x00'
        end   = '0xFF'
        for i in range(eval(start), eval(end)):
          el = '%02x'% i
          l = '('+gr+','+el+el_start+')'+m.group(3)
          print l
          list.append(l)
        return True
    return False

  def Write(self):
    outfile = file(self._OutputFilename, 'w')
    outfile.writelines( self._OutLines )
    outfile.close()

  def Expand(self):
    infile = file(self._InputFilename,'r')
    for line in infile.readlines():
      # ExpandLine also LowerCase the line
      self.ExpandLine(line) # l is [1,n] lines
    self.Write()
    infile.close()

"""
Parse line from a philips document, line are like this:

Syncra Scan Type 2005,10A1 VR = CS, VM = 1
"""
class InteraParser:
  def __init__(self):
    self._InputFilename = ''
    self._OutputFilename = ''

  def Reformat(self,s):
    assert self.IsGood(s)
    patt = re.compile("^([A-Za-z0-9 -]+) ([0-9A-Z]+),([0-9A-Z]+) VR = ([A-Z][A-Z]), VM = (.*)$")
    m = patt.match(s)
    if m:
      dicom = m.group(2) + ' ' + m.group(3) + ' ' + m.group(4) + ' ' + m.group(5) + ' ' + m.group(1)
      return dicom
    else:
      print "oops"

  def IsGood(self,s):
    patt = re.compile("^[A-Za-z0-9 -]+ [0-9A-Z]+,[0-9A-Z]+ VR = [A-Z][A-Z], VM = .*$")
    if patt.match(s):
      return True
    print "Not good:", s
    return False

  def SetInputFileName(self,s):
    self._InputFilename = s

  def SetOutputFileName(self,s):
    self._OutputFilename = s
  
  def Parse(self):
    infile = file(self._InputFilename, 'r')
    outLines = []
    for line in infile.readlines():
      print self.Reformat(line)
      outLines.append( self.Reformat(line) + '\n' )
    outfile = file(self._OutputFilename, 'w')
    outfile.writelines( outLines )
    outfile.close()
 
"""
Parse line from a dicom3tools document, line are like this:

(0003,0008) VERS="SSPI" VR="US"   VM="1"        Owner="SIEMENS ISI"             Keyword="ISICommandField"                       Name="ISI Command Field"
"""
class Dicom3ToolsParser:
  def __init__(self):
    self._InputFilename = ''
    self._OutputFilename = ''

  def Reformat(self,s):
    assert self.IsGood(s)
    patt = re.compile("^\(([0-9a-f]+),([0-9a-f]+)\)\s+VERS=\".*\"\s+VR=\"([A-Z][A-Z])\"\s+VM=\"(.*)\"\s+Owner=\".*\"\s+Keyword=\".*\"\s+Name=\"(.*)\"$")
    m = patt.match(s)
    dicom = ''
    if m:
      # Apparently some have Name == '?', skip those
      name = m.group(5)
      if name != '?' and name != '? ':
        dicom = m.group(1) + ' ' + m.group(2) + ' ' + m.group(3) + ' ' + m.group(4) + ' ' + m.group(5)
      else:
        print "oops"
    else:
      print "oops"
    return dicom

  def IsGood(self,s):
    #patt = re.compile("^\([0-9a-f]+,[0-9a-f]+\) VERS=\".*\" VR=\"[A-Z][A-Z]\" VM=\".*\" Owner=\".*\" Keyword=\".*\" Name=\".*\"$")
    patt = re.compile("^\([0-9a-f]+,[0-9a-f]+\)\s+VERS=\".*\"\s+VR=\"[A-Z][A-Z]\"\s+VM=\".*\"\s+Owner=\".*\"\s+Keyword=\".*\"\s+Name=\".*\".*$")
    if patt.match(s):
      return True
    print "Not good:", s
    return False

  def SetInputFileName(self,s):
    self._InputFilename = s

  def SetOutputFileName(self,s):
    self._OutputFilename = s
  
  def Parse(self):
    infile = file(self._InputFilename, 'r')
    outLines = []
    for line in infile.readlines():
      newline = self.Reformat(line)
      print newline
      if newline:
        outLines.append( newline + '\n' )
    outfile = file(self._OutputFilename, 'w')
    outfile.writelines( outLines )
    outfile.close()
 
"""
Parse line from a PhilipsAdvance document, line are like this:

GE Advance Implementation Version Name (0009,1001) 3 LO 2 n/a
"""
class GEAdvanceParser:
  def __init__(self):
    self._InputFilename = ''
    self._OutputFilename = ''

  def Reformat(self,s):
    assert self.IsGood(s)
    #patt = re.compile("^\(([0-9a-f]+),([0-9a-f]+)\)\s+VERS=\".*\"\s+VR=\"([A-Z][A-Z])\"\s+VM=\"(.*)\"\s+Owner=\".*\"\s+Keyword=\".*\"\s+Name=\"(.*)\"$")
    patt = re.compile("^([A-Za-z0-9 ._>]+) \\(([0-9A-F]+),([0-9A-F]+)\\) [0-9] ([A-Z][A-Z]) ([0-9]) .*$")
    m = patt.match(s)
    dicom = ''
    if m:
      dicom = m.group(2) + ' ' + m.group(3).lower() + ' ' + m.group(4) + ' ' + m.group(5) + ' ' + m.group(1)
    else:
      print "oops"
    return dicom

  def IsGood(self,s):
    #patt = re.compile("^\([0-9a-f]+,[0-9a-f]+\)\s+VERS=\".*\"\s+VR=\"[A-Z][A-Z]\"\s+VM=\".*\"\s+Owner=\".*\"\s+Keyword=\".*\"\s+Name=\".*\".*$")
    patt = re.compile("^[A-Za-z0-9 ._>]+ \\([0-9A-F]+,[0-9A-F]+\\) [0-9] [A-Z][A-Z] [0-9] .*$")
    if patt.match(s):
      return True
    print "Not good:", s
    return False

  def SetInputFileName(self,s):
    self._InputFilename = s

  def SetOutputFileName(self,s):
    self._OutputFilename = s
  
  def Parse(self):
    infile = file(self._InputFilename, 'r')
    outLines = []
    for line in infile.readlines():
      newline = self.Reformat(line)
      #print newline
      if newline:
        outLines.append( newline + '\n' )
    outfile = file(self._OutputFilename, 'w')
    outfile.writelines( outLines )
    outfile.close()
 
if __name__ == "__main__":
  argc = len(os.sys.argv )
  if ( argc < 3 ):
    print "Sorry, wrong list of args"
    os.sys.exit(1) #error

  inputfilename = os.sys.argv[1]
  outputfilename = os.sys.argv[2]
  tempfile = "/tmp/mytemp"
  """
  dp = PdfTextParser()
  dp.SetInputFileName( inputfilename )
  #dp.SetOutputFileName( outputfilename )
  dp.SetOutputFileName( tempfile )
  dp.Parse()
  exp = DicomV3Expander()
  #exp.SetInputFileName( tempfile )
  exp.SetInputFileName( inputfilename )
  exp.SetOutputFileName( outputfilename )
  exp.Expand()

  dp = TransferSyntaxParser()
  dp.SetInputFileName( inputfilename )
  dp.SetOutputFileName( outputfilename )
  dp.Parse()

  dp = PapyrusParser()
  dp.SetInputFileName( inputfilename )
  dp.SetOutputFileName( outputfilename )
  dp.Parse()

  dp = InteraParser()
  dp.SetInputFileName( inputfilename )
  dp.SetOutputFileName( outputfilename )
  dp.Parse()
  dp = GEMSParser()
  dp.SetInputFileName( inputfilename )
  dp.SetOutputFileName( outputfilename )
  dp.Parse()

  """
  dp = Dicom3ToolsParser()
  dp.SetInputFileName( inputfilename )
  dp.SetOutputFileName( outputfilename )
  dp.Parse()

  """
  dp = GEAdvanceParser()
  dp.SetInputFileName( inputfilename )
  dp.SetOutputFileName( outputfilename )
  dp.Parse()
  """

  #print dp.IsAStartingLine( "(0004,1212) File-set Consistency Flag US 1\n" )