patt = re.compile('^[A-Za-z \'\(\)]+ +\\([0-9A-F]+,[0-9A-F]+\\) +(.*)$')
if( patt.match(s) ):
return True
+ # After page 39, lines are like:
+ patt = re.compile('^[0-9x]+ [0-9xA-F]+ .*$')
+ if( patt.match(s) ):
+ #print "PAge 39", s
+ return True
return False
def IsAFullLine(self,s):
patt = re.compile('^[A-Za-z \'\(\)]+ +\\([0-9A-F]+,[0-9A-F]+\\) +(.*)$')
if( patt.match(s) ):
return True
+ # After page 39, lines are like:
+ patt = re.compile('^[0-9x]+ [0-9xA-F]+ .* [A-Z][A-Z] [0-9].*$')
+ if( patt.match(s) ):
+ #print "PAge 39", s
+ return True
return False
def IsAComment(self,s):
# dummy case:
if s == 'Attribute Name Tag Type Attribute Description':
- print "Dummy", s
+ #print "Dummy", s
+ return True
+ patt = re.compile('^.*ANNEXE.*$')
+ if patt.match(s):
return True
# Indicate page #, spaces ending with only one number
# Sometime there is a line with only one number, we need to
# make sure that page # is strictly increasing
patt = re.compile('^[1-9][0-9]+$')
if( patt.match(s) ):
- if( eval(s) > self._PreviousPage):
- print "Page #", eval(s)
+ p = eval(s)
+ if( p > self._PreviousPage):
+ #print "Page #", p
self._PreviousNumber = 0
- self._PreviousPage = eval(s)
+ self._PreviousPage = p
return True
+# else:
+# print "PAGE ERROR:", s
# Now within each page there is a comment that start with a #
# let's do the page approach wich reset at each page
patt = re.compile('^[0-9]+$')
if( patt.match(s) ):
- print "Number #", eval(s)
- self._PreviousNumber = eval(s)
- return True
+ if( eval(s) > self._PreviousNumber):
+ #print "Number #", eval(s)
+ self._PreviousNumber = eval(s)
+ return True
+ #else:
+ # print "ERROR:", s
return False
def AddOutputLine(self,s):
m = patt.match(s)
if m:
ss = m.group(2) + ' 0 ' + m.group(1)
+ else:
+ ss = s
+ # There is two case one that end with all capital letter
+ # explaining the 'DEFINED TERMS'
+ patt = re.compile('^[0-9x]+ [0-9xA-F]+ .* [A-Z][A-Z] [0-9] [A-Z, ]$')
+ #patt = re.compile('^[0-9x]+ [0-9xA-F]+ .* [A-Z][A-Z] [0-9]|1\\-n [A-Z, |3.0]+$')
+ #patt = re.compile('^[0-9x]+ [0-9xA-F]+ .* [A-Z][A-Z] [01n-] [A-Z, |3.0]+$')
+ if patt.match(s):
+ print "Match", s
+ ss = ''
self._OutLines.append(ss + '\n')
def Open(self):
self._PreviousBuffers = []
self.Write()
+"""
+Parser for:
+GE Medical Systems HISPEED ADVANTAGE CT/i CONFORMANCE STATEMENT
+pdftotext -f 81 -l 90 -raw -nopgbrk 2162114_100r5.pdf 2162114_100r5.txt
+"""
+class GEMSParser(PdfTextParser):
+# def __init__(self):
+# PdfTextParser.__init__(self)
+
+ def IsAStartingLine(self,s):
+ #patt = re.compile('^[A-Za-z \'\(\)]+ +\\([0-9A-F]+,[0-9A-F]+\\) +(.*)$')
+ patt = re.compile('^[A-Za-z0-9 .#(),_/-]+ +\\([0-9A-F]+, ?[0-9A-F]+\\) +(.*)$')
+ if( patt.match(s) ):
+ return True
+ return False
+
+ def IsAFullLine(self,s):
+ #patt = re.compile('^[A-Za-z \'\(\)]+ +\\([0-9A-F]+,[0-9A-F]+\\) +(.*)$')
+ patt = re.compile('^[A-Za-z0-9 .#(),_/-]+ +\\([0-9A-F]+, ?[0-9A-F]+\\) [A-Z][A-Z] [0-9]+$')
+ if( patt.match(s) ):
+ return True
+ print "Not full:", s
+ return False
+
+ def IsAComment(self,s):
+ if PdfTextParser.IsAComment(self,s):
+ return True
+ #patt = re.compile('^.*GE Medical Systems LightSpeed QX/i CONFORMANCE STATEMENT REV 2.2 sm 2288567-100.*$')
+ #if patt.match(s):
+ # return True
+ patt = re.compile('^.*GE Medical Systems HISPEED ADVANTAGE CT/i CONFORMANCE STATEMENT.*$')
+ if patt.match(s):
+ return True
+ patt = re.compile('^GE Medical Systems LightSpeed QX/i CONFORMANCE STATEMENT.*$')
+ if patt.match(s):
+ return True
+ patt = re.compile('^Attribute Name Tag VR VM$')
+ if patt.match(s):
+ return True
+ 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]+)$')
+ m = patt.match(s)
+ if m:
+ ss = m.group(2).lower() + ' ' + m.group(3).lower() + ' ' + m.group(4) + ' ' + m.group(5) + ' ' + m.group(1)
+ self._OutLines.append(ss + '\n')
+ else:
+ print 'OOOPs', s
+
+
"""
This class is meant to expand line like:
- (xxxx,xxxx to xxxx) xxxxxxxxxxxx
s2 = m.group(2)
return s1.lower() + s2
else:
- print "Impossible case:", s
- os.sys.exit(1)
+ patt = re.compile('^[0-9a-fA-F]+ [0-9a-fA-F]+ [A-Z][A-Z] [0-9n-] .*$')
+ if patt.match(s):
+ return s
+ else:
+ print "Impossible case:", s
+ os.sys.exit(1)
def AddOutputLine(self,s):
if s.__class__ == list:
list = []
if self.NeedToExpansion(s, list):
self.AddOutputLine(list) # list != []
- elif self.NeedXXExpansion(s, 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:
# (50xx,1200) Number of Patient Related Studies IS 1
- def NeedXXExpansion(self,s,list):
+ def NeedGroupXXExpansion(self,s,list):
patt = re.compile('^\\(([0-9a-fA-F]+)xx,([0-9a-fA-F]+)\\)(.*)$')
m = patt.match(s)
if m:
return True
return False
+ # If line is like:
+ # (2001,xx00) Number of Patient Related Studies IS 1
+ def NeedElemXXExpansion(self,s,list):
+ patt = re.compile('^([0-9a-fA-F]+) ([0-9a-fA-F]+)xx(.*)$')
+ 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]+)(.*)$')
+ m = patt.match(s)
+ if m:
+ #print m.groups()
+ gr = m.group(1)
+ el_start = m.group(2)
+ start = '0x00'
+ end = '0xFF'
+ for i in range(eval(start), eval(end)):
+ el = '%02x'% i
+ l = '('+gr+','+el+el_start+')'+m.group(3)
+ print l
+ list.append(l)
+ return True
+ return False
+
def Write(self):
outfile = file(self._OutputFilename, 'w')
outfile.writelines( self._OutLines )
self.Write()
infile.close()
+"""
+Parse line from a philips document, line are like this:
+
+Syncra Scan Type 2005,10A1 VR = CS, VM = 1
+"""
+class InteraParser:
+ def __init__(self):
+ self._InputFilename = ''
+ self._OutputFilename = ''
+
+ def Reformat(self,s):
+ assert self.IsGood(s)
+ patt = re.compile("^([A-Za-z0-9 -]+) ([0-9A-Z]+),([0-9A-Z]+) VR = ([A-Z][A-Z]), VM = (.*)$")
+ 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 ):
#dp.SetOutputFileName( outputfilename )
dp.SetOutputFileName( tempfile )
dp.Parse()
-
exp = DicomV3Expander()
- exp.SetInputFileName( tempfile )
+ #exp.SetInputFileName( tempfile )
+ exp.SetInputFileName( inputfilename )
exp.SetOutputFileName( outputfilename )
exp.Expand()
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" )
git://git.creatis.insa-lyon.fr / gdcm.git / blobdiff