jisxやsjisのコードマッピングから正規表現に使えるレンジリストを生成する

sample.py

#!/usr/bin/python

# -*- coding: utf8 -*-
# -*- eval: (setq flycheck-python-pylint-executable "/usr/bin/pylint") -*-
"""
This script generates the ranges of unicode character code that is defined in code mapping at unicode.org.
unicode.orgの文字コードマッピングから、unicodeの文字コードのレンジをプリントするスクリプト。
"""

from itertools import groupby
from codecs import decode
try:
    from urllib2 import urlopen
except ImportError:
    # for python3
    from urllib.request import urlopen

def create(url):
    nums = set()
    for l in urlopen(url):
        l = decode(l, 'iso8859-1')
        d = l.split('#')[0]
        if not d:
            continue
        d = d.split('\t')[1].strip()
        if not d:
            continue
        nums.update(int(n, 16) for n in d.lower().lstrip('u+').split('+'))
    offsets = groupby([(n - i, n) for i, n in enumerate(sorted(nums))], lambda t: t[0])
    for _, g in offsets:
        s = e = next(g)
        for e in g:
            pass
        if s[1] != e[1]:
            yield '\\u{:04X}-\\u{:04X}'.format(s[1], e[1])
        else:
            yield '\\u{:04X}'.format(s[1])

if __name__ == '__main__':
    # iso-8859-1
    # src = 'http://ftp.unicode.org/Public/MAPPINGS/ISO8859/8859-1.TXT'
    # euc-jp
    src = 'http://x0213.org/codetable/sjis-0213-2004-std.txt'
    for entry in create(src):
        print(entry)

http://stackoverflow.com/questions/31603075/how-can-i-represent-this-regex-to-not-get-a-bad-character-range-error
[\x273DA-\x273DC] が re.compile() でパースできない