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.

Sign up for GitHub

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

Jump to bottom

Adapt the collator to Unicode 16 normalization changes #4878

Merged
merged 5 commits into from
Oct 28, 2024
Merged

Adapt the collator to Unicode 16 normalization changes #4878

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
9e61c80
Adapt the collator to Unicode 16 normalization changes
hsivonen May 8, 2024
2c7bea5
Merge branch 'main' into coll16bis
hsivonen May 13, 2024
4167a0f
Merge branch 'main' into coll16bis
hsivonen May 28, 2024
b5daa68
Merge branch 'main' into coll16bis
hsivonen Sep 18, 2024
9d76e9f
Merge branch 'main' into coll16bis
robertbastian Oct 25, 2024
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
28 changes: 21 additions & 7 deletions components/collator/src/elements.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,19 @@ use crate::provider::CollationDataV1;

/// Marker that a complex decomposition isn't round-trippable
/// under re-composition.
const NON_ROUND_TRIP_MARKER: u16 = 1;
///
/// TODO: When taking a data format break, swap this and
/// `BACKWARD_COMBINING_STARTER_DECOMPOSITION_MARKER` around
/// to make backward-combiningness use the same bit in all
/// cases.
const NON_ROUND_TRIP_MARKER: u16 = 0b1;

/// Marker that a complex decomposition starts with a starter
/// that can combine backwards.
const BACKWARD_COMBINING_STARTER_DECOMPOSITION_MARKER: u16 = 0b10;

/// Values above this are treated as a BMP character.
const HIGHEST_MARKER: u16 = NON_ROUND_TRIP_MARKER | BACKWARD_COMBINING_STARTER_DECOMPOSITION_MARKER;

/// Marker value for U+FDFA in NFKD
const FDFA_MARKER: u16 = 3;
Expand Down Expand Up @@ -1038,7 +1050,7 @@ where
} else {
let trail_or_complex = (decomposition >> 16) as u16;
let lead = decomposition as u16;
if lead > NON_ROUND_TRIP_MARKER && trail_or_complex != 0 {
if lead > HIGHEST_MARKER && trail_or_complex != 0 {
// Decomposition into two BMP characters: starter and non-starter
self.upcoming.push(
CharacterAndClassAndTrieValue::new_with_non_decomposing_starter(char_from_u16(
Expand All @@ -1052,7 +1064,7 @@ where
low_c, trie_value,
),
);
} else if lead > NON_ROUND_TRIP_MARKER {
} else if trail_or_complex == 0 {
debug_assert_ne!(
lead, FDFA_MARKER,
"How come U+FDFA NFKD marker seen in NFD?"
Expand Down Expand Up @@ -1334,7 +1346,7 @@ where
} else {
let trail_or_complex = (decomposition >> 16) as u16;
let lead = decomposition as u16;
if lead > NON_ROUND_TRIP_MARKER && trail_or_complex != 0 {
if lead > HIGHEST_MARKER && trail_or_complex != 0 {
// Decomposition into two BMP characters: starter and non-starter
c = char_from_u16(lead);
ce32 = data.ce32_for_char(c);
Expand Down Expand Up @@ -1397,9 +1409,11 @@ where
}
combining_characters
.push(CharacterAndClass::new_with_placeholder(combining));
} else if lead > NON_ROUND_TRIP_MARKER {
debug_assert_ne!(lead, 1, "How come U+FDFA NFKD marker seen in NFD?");
debug_assert_ne!(lead, 2, "How come non-starter marker seen here?");
} else if trail_or_complex == 0 {
debug_assert_ne!(
lead, FDFA_MARKER,
"How come U+FDFA NFKD marker seen in NFD?"
);
// Decomposition into one BMP character
c = char_from_u16(lead);
ce32 = data.ce32_for_char(c);
Expand Down