Use unicode.org's list of IDN characters instead of alphaNumeric characters as...

Use unicode.org's list of IDN characters instead of alphaNumeric characters as the list of legal URL haracters, plus those in settings for various punctuation marks like / which can occur in a URL

tools/list_to_range.py

+#!/usr/bin/python
+
+import itertools
+
+def get_ranges(i):
+    for a, b in itertools.groupby(enumerate(i), lambda (x, y): y - x):
+        b = list(b)
+        yield b[0][1], b[-1][1]
+
+contents = []
+while True:
+    try:
+        line = raw_input("")
+    except EOFError:
+        break
+    contents.append(line)
+
+numbers = map(lambda x: int(x, 16), contents)
+for x in get_ranges(numbers):
+  print "[set addCharactersInRange:NSMakeRange(%s, %s)];" % (hex(x[0]), str(x[1] - x[0] + 1))

tools/range_to_range.py

+#!/usr/bin/python
+
+import itertools
+
+def get_ranges(i):
+    for a, b in itertools.groupby(enumerate(i), lambda (x, y): y - x):
+        b = list(b)
+        yield b[0][1], b[-1][1]
+
+contents = []
+while True:
+    try:
+        line = raw_input("").split(" ")
+    except EOFError:
+        break
+    contents.append(line)
+
+for tuple in contents:
+  min = int(tuple[0], 16)
+  max = int(tuple[1], 16)
+  print "[set addCharactersInRange:NSMakeRange(%s, %s)];" % (hex(min), str(max - min + 1))