Last active
July 30, 2019 22:22
-
-
Save bofm/d8932cf04913554d8f393ba43ef30dd5 to your computer and use it in GitHub Desktop.
Escape invalid XML characters in Python 3
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import sys | |
import re | |
# https://trac-hacks.org/ticket/11050#comment:13 | |
_illegal_unichrs = ((0x00, 0x08), (0x0B, 0x1F), (0x7F, 0x84), (0x86, 0x9F), | |
(0xD800, 0xDFFF), (0xFDD0, 0xFDDF), (0xFFFE, 0xFFFF), | |
(0x1FFFE, 0x1FFFF), (0x2FFFE, 0x2FFFF), | |
(0x3FFFE, 0x3FFFF), (0x4FFFE, 0x4FFFF), | |
(0x5FFFE, 0x5FFFF), (0x6FFFE, 0x6FFFF), | |
(0x7FFFE, 0x7FFFF), (0x8FFFE, 0x8FFFF), | |
(0x9FFFE, 0x9FFFF), (0xAFFFE, 0xAFFFF), | |
(0xBFFFE, 0xBFFFF), (0xCFFFE, 0xCFFFF), | |
(0xDFFFE, 0xDFFFF), (0xEFFFE, 0xEFFFF), | |
(0xFFFFE, 0xFFFFF), (0x10FFFE, 0x10FFFF)) | |
_illegal_ranges = tuple("%s-%s" % (chr(low), chr(high)) | |
for (low, high) in _illegal_unichrs | |
if low < sys.maxunicode) | |
_illegal_xml_chars_re = re.compile('[%s]' % ''.join(_illegal_ranges)) | |
def _escape_match(match): | |
return '&#%i;' % ord(match.group(0)) | |
def escape_xml_invalid_chars(xml_text): | |
return _illegal_xml_chars_re.sub(_escape_match, xml_text) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment