mirror of
https://github.com/crate-ci/typos.git
synced 2024-11-25 10:31:02 -05:00
feat(parser): Ignore emails
This skips a lot of validation for being "good enough" (comment open/closes matching, etc). This has a chance of incorrectly matching in languages with `@` as an operator, like Python, but Python encourages spaces arround operators, so hopefully this won't be a problem.
This commit is contained in:
parent
2a1e6ca0f6
commit
6915d85c0b
1 changed files with 61 additions and 0 deletions
|
@ -186,6 +186,7 @@ mod parser {
|
||||||
terminated(hex_literal, sep1),
|
terminated(hex_literal, sep1),
|
||||||
terminated(dec_literal, sep1),
|
terminated(dec_literal, sep1),
|
||||||
terminated(base64_literal, sep1),
|
terminated(base64_literal, sep1),
|
||||||
|
terminated(email_literal, sep1),
|
||||||
)))(input)
|
)))(input)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -305,6 +306,27 @@ mod parser {
|
||||||
Ok(input.take_split(after_offset))
|
Ok(input.take_split(after_offset))
|
||||||
}
|
}
|
||||||
|
|
||||||
|
fn email_literal<T>(input: T) -> IResult<T, T>
|
||||||
|
where
|
||||||
|
T: nom::InputTakeAtPosition
|
||||||
|
+ nom::InputTake
|
||||||
|
+ nom::InputIter
|
||||||
|
+ nom::InputLength
|
||||||
|
+ nom::Offset
|
||||||
|
+ nom::Slice<std::ops::RangeTo<usize>>
|
||||||
|
+ nom::Slice<std::ops::RangeFrom<usize>>
|
||||||
|
+ std::fmt::Debug
|
||||||
|
+ Clone,
|
||||||
|
<T as nom::InputTakeAtPosition>::Item: AsChar + Copy,
|
||||||
|
<T as nom::InputIter>::Item: AsChar + Copy,
|
||||||
|
{
|
||||||
|
recognize(tuple((
|
||||||
|
take_while1(is_email_localport_char),
|
||||||
|
char('@'),
|
||||||
|
take_while1(is_email_domain_char),
|
||||||
|
)))(input)
|
||||||
|
}
|
||||||
|
|
||||||
fn take_many0<I, E, F>(mut f: F) -> impl FnMut(I) -> IResult<I, I, E>
|
fn take_many0<I, E, F>(mut f: F) -> impl FnMut(I) -> IResult<I, I, E>
|
||||||
where
|
where
|
||||||
I: nom::Offset + nom::InputTake + Clone + PartialEq + std::fmt::Debug,
|
I: nom::Offset + nom::InputTake + Clone + PartialEq + std::fmt::Debug,
|
||||||
|
@ -338,19 +360,23 @@ mod parser {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
#[inline]
|
||||||
fn is_dec_digit_with_sep(i: impl AsChar + Copy) -> bool {
|
fn is_dec_digit_with_sep(i: impl AsChar + Copy) -> bool {
|
||||||
i.is_dec_digit() || is_digit_sep(i.as_char())
|
i.is_dec_digit() || is_digit_sep(i.as_char())
|
||||||
}
|
}
|
||||||
|
|
||||||
|
#[inline]
|
||||||
fn is_hex_digit_with_sep(i: impl AsChar + Copy) -> bool {
|
fn is_hex_digit_with_sep(i: impl AsChar + Copy) -> bool {
|
||||||
i.is_hex_digit() || is_digit_sep(i.as_char())
|
i.is_hex_digit() || is_digit_sep(i.as_char())
|
||||||
}
|
}
|
||||||
|
|
||||||
|
#[inline]
|
||||||
fn is_lower_hex_digit(i: impl AsChar + Copy) -> bool {
|
fn is_lower_hex_digit(i: impl AsChar + Copy) -> bool {
|
||||||
let c = i.as_char();
|
let c = i.as_char();
|
||||||
('a'..='f').contains(&c) || ('0'..='9').contains(&c)
|
('a'..='f').contains(&c) || ('0'..='9').contains(&c)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
#[inline]
|
||||||
fn is_base64_digit(i: impl AsChar + Copy) -> bool {
|
fn is_base64_digit(i: impl AsChar + Copy) -> bool {
|
||||||
let c = i.as_char();
|
let c = i.as_char();
|
||||||
('a'..='z').contains(&c)
|
('a'..='z').contains(&c)
|
||||||
|
@ -360,11 +386,31 @@ mod parser {
|
||||||
|| c == '/'
|
|| c == '/'
|
||||||
}
|
}
|
||||||
|
|
||||||
|
#[inline]
|
||||||
fn is_base64_padding(i: impl AsChar + Copy) -> bool {
|
fn is_base64_padding(i: impl AsChar + Copy) -> bool {
|
||||||
let c = i.as_char();
|
let c = i.as_char();
|
||||||
c == '='
|
c == '='
|
||||||
}
|
}
|
||||||
|
|
||||||
|
#[inline]
|
||||||
|
fn is_email_localport_char(i: impl AsChar + Copy) -> bool {
|
||||||
|
let c = i.as_char();
|
||||||
|
('a'..='z').contains(&c)
|
||||||
|
|| ('A'..='Z').contains(&c)
|
||||||
|
|| ('0'..='9').contains(&c)
|
||||||
|
|| "!#$%&'*+-/=?^_`{|}~().".find(c).is_some()
|
||||||
|
}
|
||||||
|
|
||||||
|
#[inline]
|
||||||
|
fn is_email_domain_char(i: impl AsChar + Copy) -> bool {
|
||||||
|
let c = i.as_char();
|
||||||
|
('a'..='z').contains(&c)
|
||||||
|
|| ('A'..='Z').contains(&c)
|
||||||
|
|| ('0'..='9').contains(&c)
|
||||||
|
|| "-().".find(c).is_some()
|
||||||
|
}
|
||||||
|
|
||||||
|
#[inline]
|
||||||
fn is_xid_continue(i: impl AsChar + Copy) -> bool {
|
fn is_xid_continue(i: impl AsChar + Copy) -> bool {
|
||||||
let c = i.as_char();
|
let c = i.as_char();
|
||||||
unicode_xid::UnicodeXID::is_xid_continue(c)
|
unicode_xid::UnicodeXID::is_xid_continue(c)
|
||||||
|
@ -799,6 +845,21 @@ mod test {
|
||||||
assert_eq!(expected, actual);
|
assert_eq!(expected, actual);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn tokenize_ignore_email() {
|
||||||
|
let parser = TokenizerBuilder::new().build();
|
||||||
|
|
||||||
|
let input = "Good example@example.com Bye";
|
||||||
|
let expected: Vec<Identifier> = vec![
|
||||||
|
Identifier::new_unchecked("Good", Case::None, 0),
|
||||||
|
Identifier::new_unchecked("Bye", Case::None, 25),
|
||||||
|
];
|
||||||
|
let actual: Vec<_> = parser.parse_bytes(input.as_bytes()).collect();
|
||||||
|
assert_eq!(expected, actual);
|
||||||
|
let actual: Vec<_> = parser.parse_str(input).collect();
|
||||||
|
assert_eq!(expected, actual);
|
||||||
|
}
|
||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
fn tokenize_leading_digits() {
|
fn tokenize_leading_digits() {
|
||||||
let parser = TokenizerBuilder::new().build();
|
let parser = TokenizerBuilder::new().build();
|
||||||
|
|
Loading…
Reference in a new issue