Support enabling the CSUR data.

tools/categories.py

@@ -28,6 +28,11 @@ unicode_chars = {}
 for data in ucd.parse_ucd_data(ucd_rootdir, 'UnicodeData'):
 	for codepoint in data['CodePoint']:
 		unicode_chars[codepoint] = data['GeneralCategory']
+if '--with-csur' in sys.argv:
+	for csur in ['Klingon']:
+		for data in ucd.parse_ucd_data('data/csur', csur):
+			for codepoint in data['CodePoint']:
+				unicode_chars[codepoint] = data['GeneralCategory']
 
 # This map is a combination of the information in the UnicodeData and Blocks
 # data files. It is intended to reduce the number of character tables that

tools/printdata.py

@@ -22,6 +22,7 @@ import sys
 import ucd
 
 ucd_rootdir = sys.argv[1]
+csur_rootdir = 'data/csur'
 
 unicode_chars = {}
 for data in ucd.parse_ucd_data(ucd_rootdir, 'UnicodeData'):
@@ -35,6 +36,15 @@ for data in ucd.parse_ucd_data(ucd_rootdir, 'PropList'):
 for data in ucd.parse_ucd_data(ucd_rootdir, 'Scripts'):
 	for codepoint in data['Range']:
 		unicode_chars[codepoint]['Script'] = data['Script']
+if '--with-csur' in sys.argv:
+	for csur in ['Klingon']:
+		for data in ucd.parse_ucd_data('data/csur', csur):
+			for codepoint in data['CodePoint']:
+				if not 'TitleCase'  in data: data['TitleCase']  = codepoint
+				if not 'UpperCase'  in data: data['UpperCase']  = codepoint
+				if not 'LowerCase'  in data: data['LowerCase']  = codepoint
+				if not 'Properties' in data: data['Properties'] = []
+				unicode_chars[codepoint] = data
 
 null = ucd.CodePoint('0000')
 if __name__ == '__main__':

tools/scripts.py

@@ -28,6 +28,11 @@ unicode_chars = {}
 for data in ucd.parse_ucd_data(ucd_rootdir, 'Scripts'):
 	for codepoint in data['Range']:
 		unicode_chars[codepoint] = data['Script']
+if '--with-csur' in sys.argv:
+	for csur in ['Klingon']:
+		for data in ucd.parse_ucd_data('data/csur', csur):
+			for codepoint in data['CodePoint']:
+				unicode_chars[codepoint] = data['Script']
 
 # This map is a combination of the information in the UnicodeData and Blocks
 # data files. It is intended to reduce the number of character tables that

tools/ucd.py

@@ -98,6 +98,7 @@ def strlist(x):
 	return x, []
 
 data_items = {
+	# Unicode Character Data:
 	'Blocks': [
 		('Range', codepoint),
 		('Name', string)
@@ -137,7 +138,7 @@ data_items = {
 		('LowerCase', codepoint),
 		('TitleCase', codepoint),
 	],
-	# Supplemental Data:
+	# ConScript Unicode Registry Data:
 	'Klingon': [
 		('CodePoint', codepoint),
 		('Script', string),