A Simple extractor to parse a valid xml based CDL and convert it into a simplified ColorCorrectionCollection xml file.

cdl2ccc.py

#!/usr/bin/env python
#
# Author: Andrew Bunday
# Date: 19/08/11
#
# A Simple extractor to parse a valid xml based CDL and convert it into 
# a simplified ColorCorrectionCollection xml file.

import xml.etree.ElementTree 
from xml.etree.ElementTree import XMLParser, ElementTree, Element
import sys, re
from StringIO import StringIO as sio

def indent(elem, level=0):
    """Pretty prints the otherwise plain xml string output"""
    i = "\n" + level*"   "
    if len(elem):
        if not elem.text or not elem.text.strip():
            elem.text = i + "   "
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
        for elem in elem:
            indent(elem, level+1)
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
    else:
        if level and (not elem.tail or not elem.tail.strip()):
            elem.tail = i

try:
    if len(sys.argv) < 2: raise ValueError('No cdl file provided')
    p = open( sys.argv[-1], 'rU' )
    xml_raw = p.read()
    p.close()
    
except Exception as e : 
    print "Error: %s" % e
    sys.exit(1)

#Stripping out any unwarranted quotation from the xml stream.
xml_clean = re.sub( '"', '' , re.sub('""', "'", xml_raw ) )

try:
    tree = xml.etree.ElementTree.parse( sio(xml_clean) )
except Exception as e:
    print e
    
# Create the root for our new xml tree
collectionElem = Element("ColorCorrectionCollection")
collectionElem.set('xmlns', "urn:ASC:CDL:v1.2")
    
# Iterate through each of the color decisions within the cdl. 
# For each one we find we grab out the media reference string
# and filter it for information about the shot since the id's are
# often autogenerated sequential garbage.
#
# For each decision we find we extract the SOP and saturation data
# and build a new clean node which we add to our previously created root.
decisionNodes = tree.findall("{urn:ASC:CDL:v1.01}ColorDecision")
for decisionNode in decisionNodes:
    mediaRef = decisionNode.getiterator('{urn:ASC:CDL:v1.01}MediaRef')[0].get('ref')
    slateRef = re.findall( '.*/(.*)/\w+-\w+\.dpx', mediaRef )[0]
    
    colorCorrectionElem = Element("ColorCorrection")
    colorCorrectionElem.set( 'id', slateRef )
    
    colorCorrections = decisionNode.getiterator('{urn:ASC:CDL:v1.01}ColorCorrection')
    for colorCorrection in decisionNode.getiterator('{urn:ASC:CDL:v1.01}ColorCorrection') :
        
        slopeElem = Element('Slope')
        slopeElem.text = colorCorrection.find('{urn:ASC:CDL:v1.01}SOPNode/{urn:ASC:CDL:v1.01}Slope').text
        
        offsetElem = Element('Offset')
        offsetElem.text = colorCorrection.find('{urn:ASC:CDL:v1.01}SOPNode/{urn:ASC:CDL:v1.01}Offset').text
        
        powerElem = Element('Power')
        powerElem.text = colorCorrection.find('{urn:ASC:CDL:v1.01}SOPNode/{urn:ASC:CDL:v1.01}Power').text
        
        SOPElem = Element("SOPNode")
        SOPElem.append(slopeElem)
        SOPElem.append(offsetElem)
        SOPElem.append(powerElem)
        
        colorCorrectionElem.append(SOPElem)
        
        try:
            saturationElem = Element('Saturation')
            saturationElem.text = colorCorrection.find('{urn:ASC:CDL:v1.01}SatNode/{urn:ASC:CDL:v1.01}Saturation').text
            
            SATElem = Element('SatNode')
            SATElem.append(saturationElem)
            colorCorrectionElem.append(SATElem)
        except Exception as e:
            #the is no saturation on this node... stupid optional extras
            pass
            
    collectionElem.append( colorCorrectionElem )
        
indent(collectionElem)
collectionTree = ElementTree( collectionElem )

# A user may put 'monkey.ccc' or 'monkey' as the filename. We ensure we always have a single
# .ccc file extension.
filename = raw_input( "Save .ccc file as:" ).strip(".ccc")

collectionTree.write( "%s.ccc" % filename )