Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit ab06a8b

Browse files
fixed: is_email is now complaint with email specifications
1 parent ad3c497 commit ab06a8b

File tree

3 files changed

+146
-13
lines changed

3 files changed

+146
-13
lines changed

‎string_utils/_regex.py‎

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,9 @@
2222

2323
URLS_RE = re.compile(r'({})'.format(URLS_RAW_STRING), re.IGNORECASE)
2424

25-
EMAILS_RAW_STRING = r'[a-zA-Z\d._+-]+@[a-z\d-]+\.?[a-z\d-]+\.[a-z]{2,4}'
25+
ESCAPED_AT_SIGN = re.compile(r'(?!"[^"]*)@+(?=[^"]*")|\\@')
26+
27+
EMAILS_RAW_STRING = r"[a-zA-Z\d._\+\-'`!%#$&*/=\?\^\{\}\|~\\]+@[a-z\d-]+\.?[a-z\d-]+\.[a-z]{2,4}"
2628

2729
EMAIL_RE = re.compile(r'^{}$'.format(EMAILS_RAW_STRING))
2830

‎string_utils/validation.py‎

Lines changed: 43 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -200,15 +200,22 @@ def is_url(input_string: Any, allowed_schemes: Optional[List[str]] = None) -> bo
200200
return valid
201201

202202

203+
# todo: fix me
204+
'''
205+
That limit is a maximum of 64 characters (octets)
206+
in the "local part" (before the "@") and a maximum of 255 characters
207+
(octets) in the domain part (after the "@") for a total length of 320
208+
characters. Systems that handle email should be prepared to process
209+
addresses which are that long, even though they are rarely
210+
encountered.
211+
'''
212+
213+
203214
def is_email(input_string: Any) -> bool:
204215
"""
205-
Check if a string is an email.
216+
Check if a string is a valid email.
206217
207-
By design, the implementation of this checking does not strictly follow the specification for a valid \
208-
email address, but instead it's based on real world cases in order to match more than 99% \
209-
of emails and catch user mistakes. For example the percentage sign "%" is a valid sign for an email, \
210-
but actually no one use it, instead if such sign is found in a string coming from user input (like a \
211-
web form) it's very likely that it's a mistake.
218+
Reference: https://tools.ietf.org/html/rfc3696#section-3
212219
213220
*Examples:*
214221
@@ -219,7 +226,36 @@ def is_email(input_string: Any) -> bool:
219226
:type input_string: str
220227
:return: True if email, false otherwise.
221228
"""
222-
return is_full_string(input_string) and EMAIL_RE.match(input_string) is not None
229+
# first simple "pre check": it must be a non empty string with max len 320 and cannot start with a dot
230+
if not is_full_string(input_string) or len(input_string) > 320 or input_string.startswith('.'):
231+
return False
232+
233+
try:
234+
# we expect 2 tokens, one before "@" and one after, otherwise we have an exception and the email is not valid
235+
head, tail = input_string.split('@')
236+
237+
# removes escaped spaces, so that later on the test regex will accept the string
238+
head = head.replace('\\ ', '')
239+
if head.startswith('"') and head.endswith('"'):
240+
head = head.replace(' ', '')[1:-1]
241+
242+
if head.endswith('.') or len(head) > 64 or len(tail) > 255:
243+
return False
244+
245+
# multiple consecutive dots are forbidden
246+
if '..' in head:
247+
return False
248+
249+
return EMAIL_RE.match(head + '@' + tail) is not None
250+
251+
except ValueError:
252+
# borderline case in which we have multiple "@" signs but the head part is correctly escaped
253+
if ESCAPED_AT_SIGN.search(input_string) is not None:
254+
# replace "@" with "a" in the head
255+
sanitized = ESCAPED_AT_SIGN.sub('a', input_string)
256+
return is_email(sanitized)
257+
258+
return False
223259

224260

225261
def is_credit_card(input_string: Any, card_type: str = None) -> bool:

‎tests/test_is_email.py‎

Lines changed: 100 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -44,11 +44,9 @@ def test_domain_extension_should_be_letters_only_from_2_to_4_chars(self):
4444
self.assertFalse(is_email('me@foo.___'))
4545
self.assertFalse(is_email('me@foo.toolongext'))
4646

47-
def test_name_part_cannot_contain_bad_signs(self):
48-
self.assertFalse(is_email('#me#@foo.com'))
49-
self.assertFalse(is_email('me!@foo.com'))
50-
self.assertFalse(is_email('[][]@foo.com'))
51-
self.assertFalse(is_email('john%@john5music.net'))
47+
def test_name_part_cannot_contain_suqare_brackets(self):
48+
self.assertFalse(is_email('[myemail@foo.com'))
49+
self.assertFalse(is_email('my]email@foo.com'))
5250

5351
def test_domain_part_cannot_contain_bad_signs(self):
5452
self.assertFalse(is_email('me@#foo#.com'))
@@ -74,3 +72,100 @@ def test_should_accept_valid_emails(self):
7472
self.assertTrue(is_email('foo@domamin.subdomain.com'))
7573
self.assertTrue(is_email('is1email@domain.org'))
7674
self.assertTrue(is_email('UPPER_CASE_EMAIL@somesite.com'))
75+
76+
def test_max_email_length_is_respected(self):
77+
invalid_email = ('a' * 320) + '@gmail.com'
78+
self.assertFalse(is_email(invalid_email))
79+
80+
def test_local_part_length_is_respected(self):
81+
# max local part is 64 (before "@")
82+
invalid_email = ('a' * 65) + '@gmail.com'
83+
self.assertFalse(is_email(invalid_email))
84+
85+
def test_octects_part_length_is_respected(self):
86+
# max octets part is 255 (after "@")
87+
invalid_email = 'a@{}.com'.format(255 * 'x')
88+
self.assertFalse(is_email(invalid_email))
89+
90+
def test_plus_is_valid_char_in_local_part(self):
91+
self.assertTrue(is_email("my+mail@gmail.com"))
92+
93+
def test_minus_is_valid_char_in_local_part(self):
94+
self.assertTrue(is_email("my-mail@gmail.com"))
95+
96+
def test_slash_is_valid_char_in_local_part(self):
97+
self.assertTrue(is_email("my/mail@gmail.com"))
98+
99+
def test_back_slash_is_valid_char_in_local_part(self):
100+
self.assertTrue(is_email("my\\mail@gmail.com"))
101+
102+
def test_equal_is_valid_char_in_local_part(self):
103+
self.assertTrue(is_email("my=mail@gmail.com"))
104+
105+
def test_question_mark_is_valid_char_in_local_part(self):
106+
self.assertTrue(is_email("my?mail@gmail.com"))
107+
108+
def test_sharp_is_valid_char_in_local_part(self):
109+
self.assertTrue(is_email("my#mail@gmail.com"))
110+
111+
def test_dollar_is_valid_char_in_local_part(self):
112+
self.assertTrue(is_email("my$mail@gmail.com"))
113+
114+
def test_and_is_valid_char_in_local_part(self):
115+
self.assertTrue(is_email("my&mail@gmail.com"))
116+
117+
def test_asterisk_is_valid_char_in_local_part(self):
118+
self.assertTrue(is_email("my*mail@gmail.com"))
119+
120+
def test_apostrophe_is_valid_char_in_local_part(self):
121+
self.assertTrue(is_email("my'mail@gmail.com"))
122+
123+
def test_acute_accent_is_valid_char_in_local_part(self):
124+
self.assertTrue(is_email("my`mail@gmail.com"))
125+
126+
def test_percentage_is_valid_char_in_local_part(self):
127+
self.assertTrue(is_email("my%mail@gmail.com"))
128+
129+
def test_exclamation_mark_is_valid_char_in_local_part(self):
130+
self.assertTrue(is_email("my!mail@gmail.com"))
131+
132+
def test_caret_is_valid_char_in_local_part(self):
133+
self.assertTrue(is_email("my^mail@gmail.com"))
134+
135+
def test_pipe_is_valid_char_in_local_part(self):
136+
self.assertTrue(is_email("my|mail@gmail.com"))
137+
138+
def test_tilde_is_valid_char_in_local_part(self):
139+
self.assertTrue(is_email("my~mail@gmail.com"))
140+
141+
def test_curly_braces_are_valid_char_in_local_part(self):
142+
self.assertTrue(is_email("my{mail@gmail.com"))
143+
self.assertTrue(is_email("my}mail@gmail.com"))
144+
self.assertTrue(is_email("{mymail}@gmail.com"))
145+
146+
def test_local_part_cannot_start_with_period(self):
147+
self.assertFalse(is_email('.myemail@gmail.com'))
148+
149+
def test_local_part_cannot_end_with_period(self):
150+
self.assertFalse(is_email('myemail.@gmail.com'))
151+
152+
def test_local_part_cannot_have_multiple_consecutive_periods(self):
153+
self.assertFalse(is_email('my..email@gmail.com'))
154+
self.assertFalse(is_email('my.email...nope@gmail.com'))
155+
156+
def test_empty_spaces_are_allowed_only_if_escaped(self):
157+
self.assertFalse(is_email('my mail@gmail.com'))
158+
self.assertTrue(is_email('my\\ mail@gmail.com'))
159+
self.assertTrue(is_email('"my mail"@gmail.com'))
160+
161+
def test_local_part_can_be_quoted(self):
162+
self.assertTrue(is_email('"foo"@example.com'))
163+
164+
def test_with_quoted_string_multiple_at_are_accepted(self):
165+
self.assertTrue(is_email('"Abc@def"@example.com'))
166+
167+
def test_with_escape_multiple_at_are_accepted(self):
168+
self.assertTrue(is_email('Abc\\@def@example.com'))
169+
170+
def test_local_part_can_have_self_escape(self):
171+
self.assertTrue(is_email('Joe.\\\\Blow@example.com'))

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /