Created
July 4, 2023 19:00
-
-
Save raphlinus/2fdb1ec32521fde2a73be043c7c7bf68 to your computer and use it in GitHub Desktop.
Property testing of email scanner
This file contains 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
// SPDX-License-Identifier: MIT | |
use proptest::test_runner::TestRunner; | |
use proptest::strategy::{Strategy, ValueTree}; | |
fn main() { | |
let email_re = "^[a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\ | |
(?:\\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*$"; | |
let re = regex::Regex::new(email_re).unwrap(); | |
let mut runner = TestRunner::default(); | |
for _ in 0..100_000_000 { | |
let str_val = "[a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]{0,10}@?[a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]{0, 70}".new_tree(&mut runner).unwrap(); | |
let s = str_val.current(); | |
let re_match = re.is_match(&s); | |
let scan_match = scan_email(&format!("<{}>", s), 1).is_some(); | |
assert!(re_match == scan_match, "{re_match} {s}"); | |
} | |
} | |
pub(crate) fn scan_ch(data: &[u8], c: u8) -> usize { | |
(data.get(0) == Some(&c)) as usize | |
} | |
fn is_ascii_alphanumeric(c: u8) -> bool { | |
matches!(c, b'0'..=b'9' | b'a'..=b'z' | b'A'..=b'Z') | |
} | |
fn scan_email(text: &str, start_ix: usize) -> Option<(usize, String)> { | |
// using a regex library would be convenient, but doing it by hand is not too bad | |
let bytes = &text.as_bytes()[start_ix..]; | |
let mut i = 0; | |
while i < bytes.len() { | |
let c = bytes[i]; | |
i += 1; | |
match c { | |
c if is_ascii_alphanumeric(c) => (), | |
b'.' | b'!' | b'#' | b'$' | b'%' | b'&' | b'\'' | b'*' | b'+' | b'/' | b'=' | b'?' | |
| b'^' | b'_' | b'`' | b'{' | b'|' | b'}' | b'~' | b'-' => (), | |
b'@' if i > 1 => break, | |
_ => return None, | |
} | |
} | |
loop { | |
let label_start_ix = i; | |
let mut fresh_label = true; | |
while i < bytes.len() { | |
match bytes[i] { | |
c if is_ascii_alphanumeric(c) => (), | |
b'-' if fresh_label => { | |
return None; | |
} | |
b'-' => (), | |
_ => break, | |
} | |
fresh_label = false; | |
i += 1; | |
} | |
if i == label_start_ix || i - label_start_ix > 63 || bytes[i - 1] == b'-' { | |
return None; | |
} | |
if scan_ch(&bytes[i..], b'.') == 0 { | |
break; | |
} | |
i += 1; | |
} | |
if scan_ch(&bytes[i..], b'>') == 0 { | |
return None; | |
} | |
Some((start_ix + i + 1, text[start_ix..(start_ix + i)].into())) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment