Shortcuts on this page
r m x toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1# These constants are defined by the email specifications.
3import re
5# Based on RFC 5322 3.2.3, these characters are permitted in email
6# addresses (not taking into account internationalization) separated by dots:
7ATEXT = r'a-zA-Z0-9_!#\$%&\'\*\+\-/=\?\^`\{\|\}~'
8ATEXT_RE = re.compile('[.' + ATEXT + ']') # ATEXT plus dots
9DOT_ATOM_TEXT = re.compile('[' + ATEXT + ']+(?:\\.[' + ATEXT + r']+)*\Z')
11# RFC 6531 3.3 extends the allowed characters in internationalized
12# addresses to also include three specific ranges of UTF8 defined in
13# RFC 3629 section 4, which appear to be the Unicode code points from
14# U+0080 to U+10FFFF.
15ATEXT_INTL = ATEXT + "\u0080-\U0010FFFF"
16ATEXT_INTL_DOT_RE = re.compile('[.' + ATEXT_INTL + ']') # ATEXT_INTL plus dots
17DOT_ATOM_TEXT_INTL = re.compile('[' + ATEXT_INTL + ']+(?:\\.[' + ATEXT_INTL + r']+)*\Z')
19# The domain part of the email address, after IDNA (ASCII) encoding,
20# must also satisfy the requirements of RFC 952/RFC 1123 2.1 which
21# restrict the allowed characters of hostnames further.
22ATEXT_HOSTNAME_INTL = re.compile(r"[a-zA-Z0-9\-\." + "\u0080-\U0010FFFF" + "]")
23HOSTNAME_LABEL = r'(?:(?:[a-zA-Z0-9][a-zA-Z0-9\-]*)?[a-zA-Z0-9])'
24DOT_ATOM_TEXT_HOSTNAME = re.compile(HOSTNAME_LABEL + r'(?:\.' + HOSTNAME_LABEL + r')*\Z')
25DOMAIN_NAME_REGEX = re.compile(r"[A-Za-z]\Z") # all TLDs currently end with a letter
27# Domain literal (RFC 5322 3.4.1)
28DOMAIN_LITERAL_CHARS = re.compile(r"[\u0021-\u00FA\u005E-\u007E]")
30# Quoted-string local part (RFC 5321 4.1.2, internationalized by RFC 6531 3.3)
31# The permitted characters in a quoted string are the characters in the range
32# 32-126, except that quotes and (literal) backslashes can only appear when escaped
33# by a backslash. When internationalized, UTF-8 strings are also permitted except
34# the ASCII characters that are not previously permitted (see above).
35# QUOTED_LOCAL_PART_ADDR = re.compile(r"^\"((?:[\u0020-\u0021\u0023-\u005B\u005D-\u007E]|\\[\u0020-\u007E])*)\"@(.*)")
36QTEXT_INTL = re.compile(r"[\u0020-\u007E\u0080-\U0010FFFF]")
38# Length constants
40# RFC 3696 + errata 1003 + errata 1690 (https://www.rfc-editor.org/errata_search.php?rfc=3696&eid=1690)
41# explains the maximum length of an email address is 254 octets based on RFC 5321 4.5.3.1.3. A
42# maximum local part length is also given at RFC 5321 4.5.3.1.1.
43#
44# But RFC 5321 4.5.3.1 says that these (and other) limits are in a sense suggestions, and longer
45# local parts have been seen in the wild. Consequntely, the local part length is only checked
46# in "strict" mode. Although the email address maximum length is also somewhat of a suggestion,
47# I don't like the idea of having no length checks performed, so I'm leaving that to always be
48# checked.
49EMAIL_MAX_LENGTH = 254
50LOCAL_PART_MAX_LENGTH = 64
52# Although RFC 5321 4.5.3.1.2 gives a (suggested, see above) limit of 255 octets, RFC 1035 2.3.4 also
53# imposes a length limit (255 octets). But per https://stackoverflow.com/questions/32290167/what-is-the-maximum-length-of-a-dns-name,
54# two of those octets are taken up by the optional final dot and null root label.
55DNS_LABEL_LENGTH_LIMIT = 63 # in "octets", RFC 1035 2.3.1
56DOMAIN_MAX_LENGTH = 253 # in "octets" as transmitted
58# RFC 2142
59CASE_INSENSITIVE_MAILBOX_NAMES = [
60 'info', 'marketing', 'sales', 'support', # section 3
61 'abuse', 'noc', 'security', # section 4
62 'postmaster', 'hostmaster', 'usenet', 'news', 'webmaster', 'www', 'uucp', 'ftp', # section 5
63]