Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Refuse to translate if set2 contains more than one unique characters and set1 contains a character class #6472

Merged
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 19 additions & 1 deletion src/uu/tr/src/operation.rs
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ pub enum BadSequence {
ClassExceptLowerUpperInSet2,
ClassInSet2NotMatchedBySet1,
Set1LongerSet2EndsInClass,
ComplementMoreThanOneUniqueInSet2,
}

impl Display for BadSequence {
Expand Down Expand Up @@ -66,6 +67,9 @@ impl Display for BadSequence {
Self::Set1LongerSet2EndsInClass => {
write!(f, "when translating with string1 longer than string2,\nthe latter string must not end with a character class")
}
Self::ComplementMoreThanOneUniqueInSet2 => {
write!(f, "when translating with complemented character classes,\nstring2 must map all characters in the domain to one")
}
}
}
}
Expand Down Expand Up @@ -224,7 +228,6 @@ impl Sequence {
.count();

let star_compensate_len = set1_len.saturating_sub(set2_len);

//Replace CharStar with CharRepeat
set2 = set2
.iter()
Expand Down Expand Up @@ -263,6 +266,21 @@ impl Sequence {
.filter_map(to_u8)
.collect();

// Calculate the set of unique characters in set2
let mut set2_uniques = set2_solved.clone();
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
let mut set2_uniques = set2_solved.clone();
// Ensure set2_solved contains unique elements only
let mut set2_uniques = set2_solved.clone();

set2_uniques.sort();
set2_uniques.dedup();

//If the complement flag is used in translate mode, only one unique character may appear in
//set2. Validate this with the set of uniques in set2 that we just generated.
if set1.iter().any(|x| matches!(x, Self::Class(_)))
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
if set1.iter().any(|x| matches!(x, Self::Class(_)))
// Validate the complement condition
if set1.iter().any(|x| matches!(x, Self::Class(_)))

&& translating
&& complement_flag
&& set2_uniques.len() > 1
{
return Err(BadSequence::ComplementMoreThanOneUniqueInSet2);
}

if set2_solved.len() < set1_solved.len()
&& !truncate_set1_flag
&& matches!(
Expand Down
20 changes: 20 additions & 0 deletions tests/by-util/test_tr.rs
Original file line number Diff line number Diff line change
Expand Up @@ -1386,3 +1386,23 @@ fn check_set1_longer_set2_ends_in_class_with_trunc() {
.args(&["-t", "[:lower:]a", "[:upper:]"])
.succeeds();
}

#[test]
fn check_complement_2_unique_in_set2() {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
fn check_complement_2_unique_in_set2() {
#[test]
fn check_complement_2_unique_in_set2() {

let x226 = "x".repeat(226);

// [y*] is expanded tp "y" here
let arg = x226 + "[y*]xxx";
new_ucmd!().args(&["-c", "[:upper:]", arg.as_str()]).fails();
}

#[test]
fn check_complement_1_unique_in_set2() {
let x226 = "x".repeat(226);

// [y*] is expanded to "" here
let arg = x226 + "[y*]xxxx";
new_ucmd!()
.args(&["-c", "[:upper:]", arg.as_str()])
.succeeds();
}
Loading