dbernheisel · February 21, 2015 05:07
diff --git a/limit-onix3-sales-rights.py b/limit-onix3-sales-rights.py
 #!/usr/local/bin/python3
 from lxml import etree
 import sys
 import os
 import logging
 import shutil
 import argparse

 # This is designed to take an ONIX 3.0 file, analyze the Sales Rights, enforce the contract limitations, and then give pass it on for ingestion.
 # USAGE: python3 limit-sales-rights.py -f $FILE -c US CA 
 # outputs a log file

 ALL_COUNTRIES = ["AD", "AE", "AF", "AG", "AI", "AL", "AM", "AO", "AQ", "AR", "AS", "AT", "AU", "AW", "AX", "AZ", "BA", "BB", "BD", "BE", "BF", "BG", "BH", "BI", "BJ", "BL", "BM", "BN", "BO", "BQ", "BR", "BS", "BT", "BV", "BW", "BY", "BZ", "CA", "CC", "CD", "CF", "CG", "CH", "CI", "CK", "CL", "CM", "CN", "CO", "CR", "CS", "CU", "CV", "CW", "CX", "CY", "CZ", "DE", "DJ", "DK", "DM", "DO", "DZ", "EC", "EE", "EG", "EH", "ER", "ES", "ET", "FI", "FJ", "FK", "FM", "FO", "FR", "GA", "GB", "GD", "GE", "GF", "GG", "GH", "GI", "GL", "GM", "GN", "GP", "GQ", "GR", "GS", "GT", "GU", "GW", "GY", "HK", "HM", "HN", "HR", "HT", "HU", "ID", "IE", "IL", "IM", "IN", "IO", "IQ", "IR", "IS", "IT", "JE", "JM", "JO", "JP", "KE", "KG", "KH", "KI", "KM", "KN", "KP", "KR", "KW", "KY", "KZ", "LA", "LB", "LC", "LI", "LK", "LR", "LS", "LT", "LU", "LV", "LY", "MA", "MC", "MD", "ME", "MF", "MG", "MH", "MK", "ML", "MM", "MN", "MO", "MP", "MQ", "MR", "MS", "MT", "MU", "MV", "MW", "MX", "MY", "MZ", "NA", "NC", "NE", "NF", "NG", "NI", "NL", "NO", "NP", "NR", "NU", "NZ", "OM", "PA", "PE", "PF", "PG", "PH", "PK", "PL", "PM", "PN", "PR", "PS", "PT", "PW", "PY", "QA", "RE", "RO", "RS", "RU", "RW", "SA", "SB", "SC", "SD", "SE", "SG", "SH", "SI", "SJ", "SK", "SL", "SM", "SN", "SO", "SR", "SS", "ST", "SV", "SX", "SY", "SZ", "TC", "TD", "TF", "TG", "TH", "TJ", "TK", "TL", "TM", "TN", "TO", "TR", "TT", "TV", "TW", "TZ", "UA", "UG", "UM", "US", "UY", "UZ", "VA", "VC", "VE", "VG", "VI", "VN", "VU", "WF", "WS", "YE", "YT", "YU", "ZA", "ZM", "ZW"]

 def intersect(a, b):
    return list(set(a) & set(b))

 def main(onixfile, limit):
 	print("Limiting the file to " + " ".join(sorted(limit)))
 	onixfile = onixfile[0]
 	print(onixfile)
 	logging.basicConfig(filename=sys.argv[0]+'.log', level=logging.DEBUG, format='%(asctime)s %(message)s', datefmt='%Y/%m/%d %H:%M:%S')
 	logging.debug("======================================")
 	outputfile = os.path.join(os.path.split(os.path.abspath(onixfile))[0], "Adjusted", "Adjusted_" + os.path.split(os.path.abspath(onixfile))[1])
 	movedfile = os.path.join(os.path.split(os.path.abspath(onixfile))[0], "Originals", os.path.split(os.path.abspath(onixfile))[1])

 	
 	# test that we can open the file
 	try:
 		with open(onixfile, 'r') as f: logging.debug("Tested file existence %s", onixfile)
 	except IOError as e:
 		logging.critical("Can't open the file: %s" % os.path.abspath(onixfile))
 		logging.critical(e)
 		sys.exit(1)
 	
 	try:
 		logging.debug("Parsing ONIX file.")
 		root = etree.parse(onixfile, etree.XMLParser(encoding='utf-8', recover=True, dtd_validation=False, strip_cdata=False)).getroot()
 	except etree.XMLSyntaxError as e:
 		logging.critical("Could not parse %s", onixfile)
 		logging.critical(e.error_log.filter_from_level(etree.ErrorLevels.FATAL))
 		sys.exit(1)
 		
 	productsadjusted1 = root.xpath('/ONIXmessage/product[publishingdetail/salesrights[b089[text()="01"] or b089[text()="02"] or b089[text()="07"] or b089[text()="08"]]]')
 	productsadjusted2 = root.xpath('/ONIXmessage/product[publishingdetail[x456[text()="01"] or x456[text()="02"] or x456[text()="07"] or x456[text()="08"]]]')
 	productsadjusted = productsadjusted1 + productsadjusted2
 	print(len(productsadjusted))
 	for product in productsadjusted:
 		isbn = product.xpath('.//productidentifier[b221/text()="15"]/b244')[0].text
 		print("================================")
 		print(isbn)
 		forsaleterritories = []
 		notforsaleterritories = []
 		hasForSaleROW = False
 		hasNotForSaleROW = False
 		try: salesrights01 = product.xpath('.//publishingdetail/salesrights[b089[text()="01"]]/territory'); forsaleterritories.append(salesrights01[0])
 		except: pass
 		try: salesrights02 = product.xpath('.//publishingdetail/salesrights[b089[text()="02"]]/territory'); forsaleterritories.append(salesrights02[0])
 		except: pass
 		try: salesrights03 = product.xpath('.//publishingdetail/salesrights[b089[text()="03"]]/territory'); notforsaleterritories.append(salesrights03[0])
 		except: pass
 		try: salesrights04 = product.xpath('.//publishingdetail/salesrights[b089[text()="04"]]/territory'); notforsaleterritories.append(salesrights04[0])
 		except: pass
 		try: salesrights05 = product.xpath('.//publishingdetail/salesrights[b089[text()="05"]]/territory'); notforsaleterritories.append(salesrights05[0])
 		except: pass
 		try: salesrights06 = product.xpath('.//publishingdetail/salesrights[b089[text()="06"]]/territory'); notforsaleterritories.append(salesrights06[0])
 		except: pass
 		try: salesrights07 = product.xpath('.//publishingdetail/salesrights[b089[text()="07"]]/territory'); forsaleterritories.append(salesrights07[0])
 		except: pass
 		try: salesrights08 = product.xpath('.//publishingdetail/salesrights[b089[text()="08"]]/territory'); forsaleterritories.append(salesrights08[0])
 		except: pass
 		
 		# Remove NOT For Sale ROW tag. One day I can remove this useless section.
 		try:
 			rownotforsalesrights = product.xpath('.//publishingdetail/x456[text()="03" or text()="04" or text()="05" or text()="06"]')
 			# Remove Not For Sale ROW tags, since they don't matter and introduce bad processing for some ingestions.
 			logging.debug(isbn + "Has NOT For Sale ROW")
 			publishingdetail = product.xpath('.//publishingdetail')[0]
 			logging.debug(isbn + " Saw:	     " + str(etree.tostring(publishingdetail)).strip('\r\n'))
 			publishingdetail.remove(rownotforsalesrights[0])
 			print("Removed the Not For Sale ROW tag")
 			logging.debug(isbn + " Corrected: Removed the Not For Sale ROW tag x456 since !!! doesn't support it")
 		except: pass
 		
 		# Interpret For Sale ROW tag into a <salesrights>
 		try:
 			rowsalesrights = product.xpath('.//publishingdetail/x456[text()="01" or text()="02" or text()="07" or text()="08"]')
 			rowsalesrightstype = rowsalesrights[0].text

 			# Set up the Sales Rights composite
 			logging.debug(isbn + "Has For Sale ROW")
 			print("processing ROW==============")
 			publishingdetail = product.xpath('.//publishingdetail')[0]
 			salesrights = etree.SubElement(publishingdetail, "salesrights")
 			salesrightstype = etree.SubElement(salesrights, "b089")
 			salesrightstype.text = rowsalesrightstype
 			rowterritory = etree.SubElement(salesrights, "territory")
 			rowCountriesIncluded = etree.SubElement(rowterritory, "x449")
 			
 			# Do the Country Code math on ROW means, depending on what's present
 			# CAUTION THIS DOES NOT ACCOUNT FOR ALL SCENARIOS YET (ECZ or sub-territories)
 			print("ROW starting with all countries")
 			rowCountriesIncludedlist = ALL_COUNTRIES
 			logging.debug(isbn + " Starting: " + " ".join(rowCountriesIncludedlist))
 			
 			# Iterate Not For Sale CountriesIncluded so we remove them from ROW
 			for territory in notforsaleterritories:
 				try: CountriesIncluded = territory.xpath('.//x449')[0]; hasCountriesIncluded = True; print("Found Not For Sale x449: " + CountriesIncluded.text)
 				except: pass
 				if hasCountriesIncluded == True:
 					CountriesIncludedlist = sorted(CountriesIncluded.text.split(" "))
 					adjustedCountriesIncluded = [x for x in rowCountriesIncludedlist if x not in CountriesIncludedlist]
 					rowCountriesIncludedlist = adjustedCountriesIncluded
 					print("rowCountriesIncludedlist is now: %s" % " ".join(adjustedCountriesIncluded))
 					logging.debug(isbn + " Removing: " + " ".join(CountriesIncludedlist))
 					logging.debug(isbn + " Adjusted: " + " ".join(adjustedCountriesIncluded))
 			
 			# Iterate For Sale CountriesIncluded so we remove them from ROW
 			for territory in forsaleterritories:
 				try: CountriesIncluded = territory.xpath('.//x449')[0]; hasCountriesIncluded = True; print("Found For Sale x449: " + CountriesIncluded.text)
 				except: pass
 				if hasCountriesIncluded == True:
 					CountriesIncludedlist = sorted(CountriesIncluded.text.split(" "))
 					adjustedCountriesIncluded = [x for x in rowCountriesIncludedlist if x not in CountriesIncludedlist]
 					rowCountriesIncludedlist = adjustedCountriesIncluded
 					print("rowCountriesIncludedlist is now: %s" % " ".join(adjustedCountriesIncluded))
 					logging.debug(isbn + " Removing: " + " ".join(CountriesIncludedlist))
 					logging.debug(isbn + " Adjusted: " + " ".join(adjustedCountriesIncluded))
 			
 			# So now we have a representation of ROW, but we need to ensure it's limited now
 			adjustedCountriesIncluded = " ".join(set(adjustedCountriesIncluded).intersection(limit))
 			print("rowCountriesIncludedlist is now: %s" % adjustedCountriesIncluded)
 			logging.debug(isbn + " The stated limit is: " + " ".join(limit))
 			logging.debug(isbn + " ROW has been interpreted to: " + adjustedCountriesIncluded)
 			rowCountriesIncluded.text = adjustedCountriesIncluded
 						
 			logging.debug(isbn + " Saw:       " + str(etree.tostring(rowsalesrights[0])).strip('\r\n'))
 			print(isbn + " Saw:       " + str(etree.tostring(rowsalesrights[0])).strip('\r\n'))
 			logging.debug(isbn + " Corrected: " + str(etree.tostring(rowterritory)).strip('\r\n'))

 			# Remove original ROW tag since now it's represented by a <salesrights> composite
 			print("Removed the original ROW tag")
 			logging.debug(isbn + " Removed the ROW tag x456 since it was converted to a <salesrights>")
 			publishingdetail.remove(rowsalesrights[0])
 		except: print("Something went wrong")
 		
 		# Remove Not For Sale composites. Hope to remove this useless section one day.
 		for territory in notforsaleterritories:
 			print("not for sale==============")
 			salesrights = territory.getparent()
 			salesrights.getparent().remove(salesrights)
 			print("To: Removed this SalesRights, since !!! doesn't read Not For Sale SalesRights: %s" % str(etree.tostring(salesrights)).strip('\r\n'))
 			logging.debug(isbn + " Corrected: " + "Removed this SalesRights, since !!! doesn't read Not For Sale SalesRights: %s" % str(etree.tostring(salesrights)).strip('\r\n'))
 			
 		for territory in forsaleterritories:
 			print("territory==============")
 			
 			print("From:\n" + str(etree.tostring(territory)))
 			hasCountriesIncluded = False
 			hasRegionsIncluded   = False
 			hasCountriesExcluded = False
 			hasRegionsExcluded   = False
 			CountriesIncluded	= False
 			RegionsIncluded	  = False
 			CountriesExcluded	= False
 			RegionsExcluded	  = False
 			try: CountriesIncluded = territory.xpath('.//x449')[0]; hasCountriesIncluded = True; print("Found x449: " + CountriesIncluded.text)
 			except: pass
 			try: RegionsIncluded = territory.xpath('.//x450')[0]; hasRegionsIncluded = True; print("Found x450: " + RegionsIncluded.text)
 			except: pass
 			try: CountriesExcluded = territory.xpath('.//x451')[0]; hasCountriesExcluded = True; print("Found x451: " + CountriesExcluded.text)
 			except: pass
 			try: RegionsExcluded = territory.xpath('.//x452')[0]; hasRegionsExcluded = True; print("Found x452: " + RegionsExcluded.text)
 			except: pass

 			print(hasCountriesIncluded, hasRegionsIncluded, hasCountriesExcluded, hasRegionsExcluded)
 			
 			# Regions Included WORLD only
 			
 			if hasCountriesIncluded == False and hasRegionsIncluded == True and hasCountriesExcluded == False and hasRegionsExcluded == False:
 				logging.debug(isbn + " Detected Regions Included ONLY")
 				logging.debug(isbn + " Saw:	     " + str(etree.tostring(territory)).strip('\r\n'))
 				if RegionsIncluded.text.upper() == "WORLD":
 					newCountriesIncluded = etree.Element("x449")
 					newCountriesIncluded.text = " ".join(set(ALL_COUNTRIES).intersection(limit))
 					territory.replace(RegionsIncluded, newCountriesIncluded)
 					print("To:\n" + str(etree.tostring(territory)))
 					logging.debug(isbn + " Corrected: " + str(etree.tostring(territory)).strip('\r\n'))
 					continue
 				else:
 					print("We have not accounted for this combination (RegionsIncluded only, but not WORLD) of Sales Rights")
 					logging.error("We have not accounted for this combination (RegionsIncluded only, but not WORLD) of Sales Rights")
 					sys.exit(1)
 					
 			# Countries Included only
 			if hasCountriesIncluded == True and hasRegionsIncluded == False and hasCountriesExcluded == False and hasRegionsExcluded == False:
 				logging.debug(isbn + " Detected Countries Included ONLY")
 				logging.debug(isbn + " Saw:	     " + str(etree.tostring(territory)).strip('\r\n'))
 				currentsalesrights = sorted(CountriesIncluded.text.split(" "))
 				adjustedsalesrights = set(currentsalesrights).intersection(limit)
 				if len(adjustedsalesrights) == 0: # The intersection left this salesrights empty, therefore we must remove it
 					salesrights = territory.getparent()
 					salesrights.getparent().remove(salesrights)
 					print("To:\nRemoved this SalesRights, since nothing remained")
 					logging.debug(isbn + " Corrected: " + "Removed this SalesRights")
 					continue
 				CountriesIncluded.text = " ".join(sorted(adjustedsalesrights))
 				print("To:\n" + str(etree.tostring(territory)))
 				logging.debug(isbn + " Corrected: " + str(etree.tostring(territory)).strip('\r\n'))
 				continue
 			
 			# Regions Included WORLD with Countries Excluded
 			if hasCountriesIncluded == False and hasRegionsIncluded == True and hasCountriesExcluded == True and hasRegionsExcluded == False:
 				logging.debug(isbn + " Detected Regions Included with Countries Excluded")
 				logging.debug(isbn + " Saw:	     " + str(etree.tostring(territory)).strip('\r\n'))
 				if RegionsIncluded.text.upper() == "WORLD":
 					newCountriesIncluded = etree.Element("x449")
 					adjustedsalesrights = [x for x in ALL_COUNTRIES if x not in CountriesExcluded.text.split(" ")]
 					adjustedsalesrights = set(adjustedsalesrights).intersection(limit)
 					if len(adjustedsalesrights) == 0: # The intersection left this salesrights empty, therefore we must remove it
 						salesrights = territory.getparent()
 						salesrights.getparent().remove(salesrights)
 						print("To:\nRemoved this SalesRights, since nothing remained")
 						logging.debug(isbn + " Corrected: " + "Removed this SalesRights")
 						continue
 					newCountriesIncluded.text = " ".join(adjustedsalesrights)
 					territory.replace(RegionsIncluded, newCountriesIncluded)
 					territory.remove(CountriesExcluded)
 					print("To:\n" + str(etree.tostring(territory)))
 					logging.debug(isbn + " Corrected: " + str(etree.tostring(territory)).strip('\r\n'))
 					continue
 				else:
 					print("We have not accounted for this combination (RegionsIncluded that is NOT WORLD, and also has CountriesExcluded")
 					logging.error("We have not accounted for this combination (RegionsIncluded that is NOT WORLD, and also has CountriesExcluded")
 					sys.exit(1)

 	try:
 		with open(outputfile, 'wb') as f:
 			f.write(etree.tostring(root, xml_declaration=True, encoding='utf-8'))
 	except IOError as e:
 		logging.critical("Could not write adjusted ONIX file: %s" % os.path.abspath(movedfile))
 		logging.critical(e)
 		sys.exit(1)
 	
 	try:
 		logging.debug("Moving original file into /Originals")
 		shutil.copy2(onixfile, movedfile)
 		os.remove(onixfile)
 		sys.exit(0)
 	except IOError as e:
 		logging.error("Move failed")
 		logging.critical(e)
 		sys.exit(1)

 parser = argparse.ArgumentParser(description="Modify SalesRights of each product by intelligently removing countries")
 parser.add_argument('-f', '--file', nargs=1, required=True, help="The ONIX file that you'd like to modify")
 parser.add_argument('-c', '--country', nargs='*', required=True, help="A list of ISO country codes with which you'd like to limit the the Sales Rights. eg: US CA FR")
 args = parser.parse_args()
 main(args.file, args.country)
	#!/usr/local/bin/python3
	from lxml import etree
	import sys
	import os
	import logging
	import shutil
	import argparse

	# This is designed to take an ONIX 3.0 file, analyze the Sales Rights, enforce the contract limitations, and then give pass it on for ingestion.
	# USAGE: python3 limit-sales-rights.py -f $FILE -c US CA
	# outputs a log file

	ALL_COUNTRIES = ["AD", "AE", "AF", "AG", "AI", "AL", "AM", "AO", "AQ", "AR", "AS", "AT", "AU", "AW", "AX", "AZ", "BA", "BB", "BD", "BE", "BF", "BG", "BH", "BI", "BJ", "BL", "BM", "BN", "BO", "BQ", "BR", "BS", "BT", "BV", "BW", "BY", "BZ", "CA", "CC", "CD", "CF", "CG", "CH", "CI", "CK", "CL", "CM", "CN", "CO", "CR", "CS", "CU", "CV", "CW", "CX", "CY", "CZ", "DE", "DJ", "DK", "DM", "DO", "DZ", "EC", "EE", "EG", "EH", "ER", "ES", "ET", "FI", "FJ", "FK", "FM", "FO", "FR", "GA", "GB", "GD", "GE", "GF", "GG", "GH", "GI", "GL", "GM", "GN", "GP", "GQ", "GR", "GS", "GT", "GU", "GW", "GY", "HK", "HM", "HN", "HR", "HT", "HU", "ID", "IE", "IL", "IM", "IN", "IO", "IQ", "IR", "IS", "IT", "JE", "JM", "JO", "JP", "KE", "KG", "KH", "KI", "KM", "KN", "KP", "KR", "KW", "KY", "KZ", "LA", "LB", "LC", "LI", "LK", "LR", "LS", "LT", "LU", "LV", "LY", "MA", "MC", "MD", "ME", "MF", "MG", "MH", "MK", "ML", "MM", "MN", "MO", "MP", "MQ", "MR", "MS", "MT", "MU", "MV", "MW", "MX", "MY", "MZ", "NA", "NC", "NE", "NF", "NG", "NI", "NL", "NO", "NP", "NR", "NU", "NZ", "OM", "PA", "PE", "PF", "PG", "PH", "PK", "PL", "PM", "PN", "PR", "PS", "PT", "PW", "PY", "QA", "RE", "RO", "RS", "RU", "RW", "SA", "SB", "SC", "SD", "SE", "SG", "SH", "SI", "SJ", "SK", "SL", "SM", "SN", "SO", "SR", "SS", "ST", "SV", "SX", "SY", "SZ", "TC", "TD", "TF", "TG", "TH", "TJ", "TK", "TL", "TM", "TN", "TO", "TR", "TT", "TV", "TW", "TZ", "UA", "UG", "UM", "US", "UY", "UZ", "VA", "VC", "VE", "VG", "VI", "VN", "VU", "WF", "WS", "YE", "YT", "YU", "ZA", "ZM", "ZW"]

	def intersect(a, b):
	return list(set(a) & set(b))

	def main(onixfile, limit):
	print("Limiting the file to " + " ".join(sorted(limit)))
	onixfile = onixfile[0]
	print(onixfile)
	logging.basicConfig(filename=sys.argv[0]+'.log', level=logging.DEBUG, format='%(asctime)s %(message)s', datefmt='%Y/%m/%d %H:%M:%S')
	logging.debug("======================================")
	outputfile = os.path.join(os.path.split(os.path.abspath(onixfile))[0], "Adjusted", "Adjusted_" + os.path.split(os.path.abspath(onixfile))[1])
	movedfile = os.path.join(os.path.split(os.path.abspath(onixfile))[0], "Originals", os.path.split(os.path.abspath(onixfile))[1])


	# test that we can open the file
	try:
	with open(onixfile, 'r') as f: logging.debug("Tested file existence %s", onixfile)
	except IOError as e:
	logging.critical("Can't open the file: %s" % os.path.abspath(onixfile))
	logging.critical(e)
	sys.exit(1)

	try:
	logging.debug("Parsing ONIX file.")
	root = etree.parse(onixfile, etree.XMLParser(encoding='utf-8', recover=True, dtd_validation=False, strip_cdata=False)).getroot()
	except etree.XMLSyntaxError as e:
	logging.critical("Could not parse %s", onixfile)
	logging.critical(e.error_log.filter_from_level(etree.ErrorLevels.FATAL))
	sys.exit(1)

	productsadjusted1 = root.xpath('/ONIXmessage/product[publishingdetail/salesrights[b089[text()="01"] or b089[text()="02"] or b089[text()="07"] or b089[text()="08"]]]')
	productsadjusted2 = root.xpath('/ONIXmessage/product[publishingdetail[x456[text()="01"] or x456[text()="02"] or x456[text()="07"] or x456[text()="08"]]]')
	productsadjusted = productsadjusted1 + productsadjusted2
	print(len(productsadjusted))
	for product in productsadjusted:
	isbn = product.xpath('.//productidentifier[b221/text()="15"]/b244')[0].text
	print("================================")
	print(isbn)
	forsaleterritories = []
	notforsaleterritories = []
	hasForSaleROW = False
	hasNotForSaleROW = False
	try: salesrights01 = product.xpath('.//publishingdetail/salesrights[b089[text()="01"]]/territory'); forsaleterritories.append(salesrights01[0])
	except: pass
	try: salesrights02 = product.xpath('.//publishingdetail/salesrights[b089[text()="02"]]/territory'); forsaleterritories.append(salesrights02[0])
	except: pass
	try: salesrights03 = product.xpath('.//publishingdetail/salesrights[b089[text()="03"]]/territory'); notforsaleterritories.append(salesrights03[0])
	except: pass
	try: salesrights04 = product.xpath('.//publishingdetail/salesrights[b089[text()="04"]]/territory'); notforsaleterritories.append(salesrights04[0])
	except: pass
	try: salesrights05 = product.xpath('.//publishingdetail/salesrights[b089[text()="05"]]/territory'); notforsaleterritories.append(salesrights05[0])
	except: pass
	try: salesrights06 = product.xpath('.//publishingdetail/salesrights[b089[text()="06"]]/territory'); notforsaleterritories.append(salesrights06[0])
	except: pass
	try: salesrights07 = product.xpath('.//publishingdetail/salesrights[b089[text()="07"]]/territory'); forsaleterritories.append(salesrights07[0])
	except: pass
	try: salesrights08 = product.xpath('.//publishingdetail/salesrights[b089[text()="08"]]/territory'); forsaleterritories.append(salesrights08[0])
	except: pass

	# Remove NOT For Sale ROW tag. One day I can remove this useless section.
	try:
	rownotforsalesrights = product.xpath('.//publishingdetail/x456[text()="03" or text()="04" or text()="05" or text()="06"]')
	# Remove Not For Sale ROW tags, since they don't matter and introduce bad processing for some ingestions.
	logging.debug(isbn + "Has NOT For Sale ROW")
	publishingdetail = product.xpath('.//publishingdetail')[0]
	logging.debug(isbn + " Saw: " + str(etree.tostring(publishingdetail)).strip('\r\n'))
	publishingdetail.remove(rownotforsalesrights[0])
	print("Removed the Not For Sale ROW tag")
	logging.debug(isbn + " Corrected: Removed the Not For Sale ROW tag x456 since !!! doesn't support it")
	except: pass

	# Interpret For Sale ROW tag into a <salesrights>
	try:
	rowsalesrights = product.xpath('.//publishingdetail/x456[text()="01" or text()="02" or text()="07" or text()="08"]')
	rowsalesrightstype = rowsalesrights[0].text

	# Set up the Sales Rights composite
	logging.debug(isbn + "Has For Sale ROW")
	print("processing ROW==============")
	publishingdetail = product.xpath('.//publishingdetail')[0]
	salesrights = etree.SubElement(publishingdetail, "salesrights")
	salesrightstype = etree.SubElement(salesrights, "b089")
	salesrightstype.text = rowsalesrightstype
	rowterritory = etree.SubElement(salesrights, "territory")
	rowCountriesIncluded = etree.SubElement(rowterritory, "x449")

	# Do the Country Code math on ROW means, depending on what's present
	# CAUTION THIS DOES NOT ACCOUNT FOR ALL SCENARIOS YET (ECZ or sub-territories)
	print("ROW starting with all countries")
	rowCountriesIncludedlist = ALL_COUNTRIES
	logging.debug(isbn + " Starting: " + " ".join(rowCountriesIncludedlist))

	# Iterate Not For Sale CountriesIncluded so we remove them from ROW
	for territory in notforsaleterritories:
	try: CountriesIncluded = territory.xpath('.//x449')[0]; hasCountriesIncluded = True; print("Found Not For Sale x449: " + CountriesIncluded.text)
	except: pass
	if hasCountriesIncluded == True:
	CountriesIncludedlist = sorted(CountriesIncluded.text.split(" "))
	adjustedCountriesIncluded = [x for x in rowCountriesIncludedlist if x not in CountriesIncludedlist]
	rowCountriesIncludedlist = adjustedCountriesIncluded
	print("rowCountriesIncludedlist is now: %s" % " ".join(adjustedCountriesIncluded))
	logging.debug(isbn + " Removing: " + " ".join(CountriesIncludedlist))
	logging.debug(isbn + " Adjusted: " + " ".join(adjustedCountriesIncluded))

	# Iterate For Sale CountriesIncluded so we remove them from ROW
	for territory in forsaleterritories:
	try: CountriesIncluded = territory.xpath('.//x449')[0]; hasCountriesIncluded = True; print("Found For Sale x449: " + CountriesIncluded.text)
	except: pass
	if hasCountriesIncluded == True:
	CountriesIncludedlist = sorted(CountriesIncluded.text.split(" "))
	adjustedCountriesIncluded = [x for x in rowCountriesIncludedlist if x not in CountriesIncludedlist]
	rowCountriesIncludedlist = adjustedCountriesIncluded
	print("rowCountriesIncludedlist is now: %s" % " ".join(adjustedCountriesIncluded))
	logging.debug(isbn + " Removing: " + " ".join(CountriesIncludedlist))
	logging.debug(isbn + " Adjusted: " + " ".join(adjustedCountriesIncluded))

	# So now we have a representation of ROW, but we need to ensure it's limited now
	adjustedCountriesIncluded = " ".join(set(adjustedCountriesIncluded).intersection(limit))
	print("rowCountriesIncludedlist is now: %s" % adjustedCountriesIncluded)
	logging.debug(isbn + " The stated limit is: " + " ".join(limit))
	logging.debug(isbn + " ROW has been interpreted to: " + adjustedCountriesIncluded)
	rowCountriesIncluded.text = adjustedCountriesIncluded

	logging.debug(isbn + " Saw: " + str(etree.tostring(rowsalesrights[0])).strip('\r\n'))
	print(isbn + " Saw: " + str(etree.tostring(rowsalesrights[0])).strip('\r\n'))
	logging.debug(isbn + " Corrected: " + str(etree.tostring(rowterritory)).strip('\r\n'))

	# Remove original ROW tag since now it's represented by a <salesrights> composite
	print("Removed the original ROW tag")
	logging.debug(isbn + " Removed the ROW tag x456 since it was converted to a <salesrights>")
	publishingdetail.remove(rowsalesrights[0])
	except: print("Something went wrong")

	# Remove Not For Sale composites. Hope to remove this useless section one day.
	for territory in notforsaleterritories:
	print("not for sale==============")
	salesrights = territory.getparent()
	salesrights.getparent().remove(salesrights)
	print("To: Removed this SalesRights, since !!! doesn't read Not For Sale SalesRights: %s" % str(etree.tostring(salesrights)).strip('\r\n'))
	logging.debug(isbn + " Corrected: " + "Removed this SalesRights, since !!! doesn't read Not For Sale SalesRights: %s" % str(etree.tostring(salesrights)).strip('\r\n'))

	for territory in forsaleterritories:
	print("territory==============")

	print("From:\n" + str(etree.tostring(territory)))
	hasCountriesIncluded = False
	hasRegionsIncluded = False
	hasCountriesExcluded = False
	hasRegionsExcluded = False
	CountriesIncluded = False
	RegionsIncluded = False
	CountriesExcluded = False
	RegionsExcluded = False
	try: CountriesIncluded = territory.xpath('.//x449')[0]; hasCountriesIncluded = True; print("Found x449: " + CountriesIncluded.text)
	except: pass
	try: RegionsIncluded = territory.xpath('.//x450')[0]; hasRegionsIncluded = True; print("Found x450: " + RegionsIncluded.text)
	except: pass
	try: CountriesExcluded = territory.xpath('.//x451')[0]; hasCountriesExcluded = True; print("Found x451: " + CountriesExcluded.text)
	except: pass
	try: RegionsExcluded = territory.xpath('.//x452')[0]; hasRegionsExcluded = True; print("Found x452: " + RegionsExcluded.text)
	except: pass

	print(hasCountriesIncluded, hasRegionsIncluded, hasCountriesExcluded, hasRegionsExcluded)

	# Regions Included WORLD only

	if hasCountriesIncluded == False and hasRegionsIncluded == True and hasCountriesExcluded == False and hasRegionsExcluded == False:
	logging.debug(isbn + " Detected Regions Included ONLY")
	logging.debug(isbn + " Saw: " + str(etree.tostring(territory)).strip('\r\n'))
	if RegionsIncluded.text.upper() == "WORLD":
	newCountriesIncluded = etree.Element("x449")
	newCountriesIncluded.text = " ".join(set(ALL_COUNTRIES).intersection(limit))
	territory.replace(RegionsIncluded, newCountriesIncluded)
	print("To:\n" + str(etree.tostring(territory)))
	logging.debug(isbn + " Corrected: " + str(etree.tostring(territory)).strip('\r\n'))
	continue
	else:
	print("We have not accounted for this combination (RegionsIncluded only, but not WORLD) of Sales Rights")
	logging.error("We have not accounted for this combination (RegionsIncluded only, but not WORLD) of Sales Rights")
	sys.exit(1)

	# Countries Included only
	if hasCountriesIncluded == True and hasRegionsIncluded == False and hasCountriesExcluded == False and hasRegionsExcluded == False:
	logging.debug(isbn + " Detected Countries Included ONLY")
	logging.debug(isbn + " Saw: " + str(etree.tostring(territory)).strip('\r\n'))
	currentsalesrights = sorted(CountriesIncluded.text.split(" "))
	adjustedsalesrights = set(currentsalesrights).intersection(limit)
	if len(adjustedsalesrights) == 0: # The intersection left this salesrights empty, therefore we must remove it
	salesrights = territory.getparent()
	salesrights.getparent().remove(salesrights)
	print("To:\nRemoved this SalesRights, since nothing remained")
	logging.debug(isbn + " Corrected: " + "Removed this SalesRights")
	continue
	CountriesIncluded.text = " ".join(sorted(adjustedsalesrights))
	print("To:\n" + str(etree.tostring(territory)))
	logging.debug(isbn + " Corrected: " + str(etree.tostring(territory)).strip('\r\n'))
	continue

	# Regions Included WORLD with Countries Excluded
	if hasCountriesIncluded == False and hasRegionsIncluded == True and hasCountriesExcluded == True and hasRegionsExcluded == False:
	logging.debug(isbn + " Detected Regions Included with Countries Excluded")
	logging.debug(isbn + " Saw: " + str(etree.tostring(territory)).strip('\r\n'))
	if RegionsIncluded.text.upper() == "WORLD":
	newCountriesIncluded = etree.Element("x449")
	adjustedsalesrights = [x for x in ALL_COUNTRIES if x not in CountriesExcluded.text.split(" ")]
	adjustedsalesrights = set(adjustedsalesrights).intersection(limit)
	if len(adjustedsalesrights) == 0: # The intersection left this salesrights empty, therefore we must remove it
	salesrights = territory.getparent()
	salesrights.getparent().remove(salesrights)
	print("To:\nRemoved this SalesRights, since nothing remained")
	logging.debug(isbn + " Corrected: " + "Removed this SalesRights")
	continue
	newCountriesIncluded.text = " ".join(adjustedsalesrights)
	territory.replace(RegionsIncluded, newCountriesIncluded)
	territory.remove(CountriesExcluded)
	print("To:\n" + str(etree.tostring(territory)))
	logging.debug(isbn + " Corrected: " + str(etree.tostring(territory)).strip('\r\n'))
	continue
	else:
	print("We have not accounted for this combination (RegionsIncluded that is NOT WORLD, and also has CountriesExcluded")
	logging.error("We have not accounted for this combination (RegionsIncluded that is NOT WORLD, and also has CountriesExcluded")
	sys.exit(1)

	try:
	with open(outputfile, 'wb') as f:
	f.write(etree.tostring(root, xml_declaration=True, encoding='utf-8'))
	except IOError as e:
	logging.critical("Could not write adjusted ONIX file: %s" % os.path.abspath(movedfile))
	logging.critical(e)
	sys.exit(1)

	try:
	logging.debug("Moving original file into /Originals")
	shutil.copy2(onixfile, movedfile)
	os.remove(onixfile)
	sys.exit(0)
	except IOError as e:
	logging.error("Move failed")
	logging.critical(e)
	sys.exit(1)

	parser = argparse.ArgumentParser(description="Modify SalesRights of each product by intelligently removing countries")
	parser.add_argument('-f', '--file', nargs=1, required=True, help="The ONIX file that you'd like to modify")
	parser.add_argument('-c', '--country', nargs='*', required=True, help="A list of ISO country codes with which you'd like to limit the the Sales Rights. eg: US CA FR")
	args = parser.parse_args()
	main(args.file, args.country)
No results found