Use PropertyValueAliases for the script mapping.

The mapping of the script labels in the UCD data to ISO 15924
script tags is now done using the sc property map in the
PropertyValueAliases data.

This has the following benefits:

    1.  It removes the dependency on the IANA subtag registry.

    2.  It ensures the scripts are correct as specified in the
        UCD data files.

.gitignore

 
 # build output:
 
-data/language-subtag-registry
 data/ucd
 
 src/libucd.la

Makefile.am

 UCD_VERSION=@UCD_VERSION@
 UCD_ROOTDIR=data/ucd
 
-data/language-subtag-registry:
-	wget -O $@ http://www.iana.org/assignments/language-subtag-registry
-
 data/ucd/PropList.txt:
 	mkdir -pv data/ucd
 	wget -O $@ http://www.unicode.org/Public/${UCD_VERSION}/ucd/PropList.txt
 
+data/ucd/PropertyValueAliases.txt:
+	mkdir -pv data/ucd
+	wget -O $@ http://www.unicode.org/Public/${UCD_VERSION}/ucd/PropertyValueAliases.txt
+
 data/ucd/Scripts.txt:
 	mkdir -pv data/ucd
 	wget -O $@ http://www.unicode.org/Public/${UCD_VERSION}/ucd/Scripts.txt
 
 ############################# libucd ##########################################
 
-tools/ucd.py: data/language-subtag-registry
+tools/ucd.py: data/ucd/PropertyValueAliases.txt
 
 tools/case.py: tools/ucd.py \
 	data/ucd/UnicodeData.txt

tools/ucd.py

 import sys
 import iana
 
-script_map = {
-	# UCD script names not derivable from IANA script tags:
-	'Canadian_Aboriginal': 'Cans',
-	'Common': 'Zyyy',
-	'Egyptian_Hieroglyphs': 'Egyp',
-	'Inherited': 'Zyyy',
-	'Meetei_Mayek': 'Mtei',
-	'Nko': 'Nkoo',
-	'Phags_Pa': 'Phag',
-	# Codes in http://www.unicode.org/iso15924/iso15924-codes.html not in IANA:
-	'Cuneiform': 'Xsux',
-	'Duployan': 'Dupl',
-}
-
-for ref, tag in iana.read_iana_subtags('data/language-subtag-registry').items():
-	if tag['Type'] == 'Script':
-		# Convert the IANA scipt tag descriptions to the UCD script names:
-		desc = tag['Description']
-		if ' (' in desc:
-			desc = desc.split(' (')[0]
-		desc = desc.replace(' ', '_')
-		script_map[desc] = ref
-# Fix up incorrectly mapped script names:
-script_map['Cyrillic'] = 'Cyrl'
+script_map = {}
 
 class CodePoint:
 	def __init__(self, x):
 					data[key], linedata = typemap(linedata)
 				yield data
 
+def parse_property_mapping(ucd_rootdir, propname, reverse=False):
+	ret = {}
+	for data in parse_ucd_data(ucd_rootdir, 'PropertyValueAliases'):
+		if data['Property'] == propname:
+			if reverse:
+				ret[data['Value']] = data['Key']
+			else:
+				ret[data['Key']] = data['Value']
+	return ret
+
 if __name__ == '__main__':
 	try:
 		items = sys.argv[3].split(',')
 	except:
 		items = None
+	script_map = parse_property_mapping(sys.argv[1], 'sc', reverse=True)
 	for entry in parse_ucd_data(sys.argv[1], sys.argv[2]):
 		if items:
 			print ','.join([str(entry[item]) for item in items])
 		else:
 			print entry
+else:
+	script_map = parse_property_mapping('data/ucd', 'sc', reverse=True)