Move xml_encode_email_char_at_random to utils

lib/markdown2.py

@@ -123,6 +123,7 @@
     xml_oneliner_re_from_tab_width,
     hr_tag_re_from_tab_width,
     xml_escape_attr,
+    xml_encode_email_char_at_random,
 )
 
 # ---- globals
@@ -2363,7 +2364,7 @@ def _encode_email_address(self, addr):
         #
         #  Based on a filter by Matthew Wickline, posted to the BBEdit-Talk
         #  mailing list: <http://tinyurl.com/yu7ue>
-        chars = [_xml_encode_email_char_at_random(ch)
+        chars = [xml_encode_email_char_at_random(ch)
                  for ch in "mailto:" + addr]
         # Strip the mailto: from the visible part.
         addr = '<a href="%s">%s</a>' \
@@ -2482,20 +2483,6 @@ class UnicodeWithAttrs(str):
     toc_html = None
 
 
-def _xml_encode_email_char_at_random(ch):
-    r = random()
-    # Roughly 10% raw, 45% hex, 45% dec.
-    # '@' *must* be encoded. I [John Gruber] insist.
-    # Issue 26: '_' must be encoded.
-    if r > 0.9 and ch not in "@_":
-        return ch
-    elif r < 0.45:
-        # The [1:] is to drop leading '0': 0x63 -> x63
-        return '&#%s;' % hex(ord(ch))[1:]
-    else:
-        return '&#%s;' % ord(ch)
-
-
 def _html_escape_url(attr, safe_mode=False):
     """Replace special characters that are potentially malicious in url string."""
     escaped = (attr

lib/utils.py

@@ -1,3 +1,4 @@
+from random import random
 import re
 
 
@@ -286,12 +287,23 @@ def xml_escape_attr(ampersand_re, attr, skip_single_quote=True):
     By default this doesn't bother with escaping `'` to `'`, presuming that
     the tag attribute is surrounded by double quotes.
     """
-    escaped = ampersand_re.sub('&', attr)
+    escaped = ampersand_re.sub("&", attr)
 
-    escaped = (attr
-        .replace('"', '"')
-        .replace('<', '&lt;')
-        .replace('>', '&gt;'))
+    escaped = attr.replace('"', "&quot;").replace("<", "&lt;").replace(">", "&gt;")
     if not skip_single_quote:
         escaped = escaped.replace("'", "&#39;")
-    return escaped
+    return escaped
+
+
+def xml_encode_email_char_at_random(ch):
+    r = random()
+    # Roughly 10% raw, 45% hex, 45% dec.
+    # '@' *must* be encoded. I [John Gruber] insist.
+    # Issue 26: '_' must be encoded.
+    if r > 0.9 and ch not in "@_":
+        return ch
+    elif r < 0.45:
+        # The [1:] is to drop leading '0': 0x63 -> x63
+        return "&#%s;" % hex(ord(ch))[1:]
+    else:
+        return "&#%s;" % ord(ch)