Skip to content

Use ICU4X built-in data #482

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

Open
robertbastian wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Use ICU4X built-in data #482

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
32cd871
use compiled_data feature instead of datagen
robertbastian Dec 3, 2025
559028b
remove AnalysisDataSources
robertbastian Dec 9, 2025
5b83760
slim parley_data
robertbastian Dec 9, 2025
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
788 changes: 20 additions & 768 deletions Cargo.lock
View file
Open in desktop

Large diffs are not rendered by default.

11 changes: 3 additions & 8 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,15 +33,10 @@ harfrust = { version = "0.3.2", default-features = false }
hashbrown = { version = "0.16.1", default-features = false, features = ["default-hasher"] }
icu_codepointtrie_builder = { version = "0.5.1", default-features = false, features = ["wasm"] }
icu_collections = { version = "2.1.1", default-features = false }
icu_locale = { version = "2.1.1", default-features = false }
icu_locale_core = { version = "2.1.1", default-features = false }
icu_normalizer = { version = "~2.1.1", default-features = false }
icu_properties = { version = "~2.1.2", default-features = false }
icu_provider = { version = "2.1.1", default-features = false }
icu_provider_adapters = { version = "2.1.1", default-features = false }
icu_provider_export = { version = "2.1.1", default-features = false }
icu_provider_source = { version = "2.1.1", default-features = false }
icu_segmenter = { version = "~2.1.1", default-features = false }
icu_normalizer = { version = "2.1.1", default-features = false }
icu_properties = { version = "2.1.2", default-features = false }
icu_segmenter = { version = "2.1.2", default-features = false }
linebender_resource_handle = { version = "0.1.1", default-features = false }
parley = { version = "0.7.0", default-features = false, path = "parley" }
parley_data = { path = "parley_data", default-features = false }
Expand Down
12 changes: 4 additions & 8 deletions parley/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,20 +27,16 @@ accesskit = ["dep:accesskit"]
[dependencies]
skrifa = { workspace = true }
linebender_resource_handle = { workspace = true }
fontique = { workspace = true }
fontique = { workspace = true, features = ["icu_properties"] }
core_maths = { version = "0.1.1", optional = true }
parley_data = { workspace = true, features = ["baked"] }
accesskit = { workspace = true, optional = true }
hashbrown = { workspace = true }
harfrust = { workspace = true }
icu_collections = { workspace = true }
icu_locale_core = { workspace = true }
icu_normalizer = { workspace = true }
icu_properties = { workspace = true }
icu_provider = { workspace = true }
icu_segmenter = { workspace = true, features = ["auto"] }
# Used in ICU4X baked data sources
zerovec = { workspace = true }
icu_normalizer = { workspace = true, features = ["compiled_data"] }
icu_properties = { workspace = true, features = ["compiled_data"] }
icu_segmenter = { workspace = true, features = ["compiled_data"] }

[dev-dependencies]
parley_dev = { workspace = true }
Expand Down
39 changes: 15 additions & 24 deletions parley/src/analysis/cluster.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,9 @@
// SPDX-License-Identifier: Apache-2.0 OR MIT

use alloc::vec::Vec;
use icu_normalizer::properties::Decomposed;

use crate::analysis::AnalysisDataSources;
use icu_normalizer::properties::{CanonicalComposition, CanonicalDecomposition, Decomposed};
use parley_data::Properties;

/// The maximum number of characters in a single cluster.
const MAX_CLUSTER_SIZE: usize = 32;
Expand Down Expand Up @@ -116,12 +116,12 @@ impl CharCluster {
}

#[inline(always)]
fn contributes_to_shaping(ch: char, analysis_data_sources: &AnalysisDataSources) -> bool {
let props = analysis_data_sources.composite.properties(ch as u32);
fn contributes_to_shaping(ch: char) -> bool {
let props = Properties::get(ch);
crate::analysis::contributes_to_shaping(props.general_category(), props.script())
}

fn decomposed(&mut self, analysis_data_sources: &AnalysisDataSources) -> Option<&[Char]> {
fn decomposed(&mut self) -> Option<&[Char]> {
match self.decomp.state {
FormState::Invalid => None,
FormState::None => {
Expand All @@ -132,22 +132,19 @@ impl CharCluster {
return None;
}

let decomposer = analysis_data_sources.decomposing_normalizer();
let decomp = decomposer.decompose(self.chars[0].ch);
let decomp = CanonicalDecomposition::new().decompose(self.chars[0].ch);
match decomp {
Decomposed::Default | Decomposed::Singleton(_) => {
return None;
}
Decomposed::Expansion(a, b) => {
let mut copy = self.chars[0];
copy.ch = a;
copy.contributes_to_shaping =
Self::contributes_to_shaping(a, analysis_data_sources);
copy.contributes_to_shaping = Self::contributes_to_shaping(a);
self.decomp.chars[0] = copy;

copy.ch = b;
copy.contributes_to_shaping =
Self::contributes_to_shaping(b, analysis_data_sources);
copy.contributes_to_shaping = Self::contributes_to_shaping(b);
self.decomp.chars[1] = copy;

self.decomp.len = 2;
Expand All @@ -162,7 +159,7 @@ impl CharCluster {
}
}

fn composed(&mut self, analysis_data_sources: &AnalysisDataSources) -> Option<&[Char]> {
fn composed(&mut self) -> Option<&[Char]> {
match self.comp.state {
FormState::Invalid => None,
FormState::None => {
Expand All @@ -173,15 +170,13 @@ impl CharCluster {
return None;
}

let composer = analysis_data_sources.composing_normalizer();
let comp = composer.compose(self.chars[0].ch, self.chars[1].ch);
let comp = CanonicalComposition::new().compose(self.chars[0].ch, self.chars[1].ch);
match comp {
None => {}
Some(ch) => {
let mut copy = self.chars[0];
copy.ch = ch;
copy.contributes_to_shaping =
Self::contributes_to_shaping(ch, analysis_data_sources);
copy.contributes_to_shaping = Self::contributes_to_shaping(ch);
self.comp.chars[0] = copy;
self.comp.len = 1;
}
Expand All @@ -195,19 +190,15 @@ impl CharCluster {
}
}

pub(crate) fn map(
&mut self,
f: impl Fn(char) -> GlyphId,
analysis_data_sources: &AnalysisDataSources,
) -> Status {
pub(crate) fn map(&mut self, f: impl Fn(char) -> GlyphId) -> Status {
let len = self.len();
if len == 0 {
return Status::Complete;
}
let mut glyph_ids = [0_u16; MAX_CLUSTER_SIZE];
let prev_ratio = self.best_ratio;
let mut ratio;
if self.force_normalize && self.composed(analysis_data_sources).is_some() {
if self.force_normalize && self.composed().is_some() {
ratio = self.comp.map(&f, &mut glyph_ids, self.best_ratio);
if ratio > self.best_ratio {
self.best_ratio = ratio;
Expand All @@ -229,7 +220,7 @@ impl CharCluster {
return Status::Complete;
}
}
if self.decomposed(analysis_data_sources).is_some() {
if self.decomposed().is_some() {
ratio = self.decomp.map(&f, &mut glyph_ids, self.best_ratio);
if ratio > self.best_ratio {
self.best_ratio = ratio;
Expand All @@ -238,7 +229,7 @@ impl CharCluster {
return Status::Complete;
}
}
if !self.force_normalize && self.composed(analysis_data_sources).is_some() {
if !self.force_normalize && self.composed().is_some() {
ratio = self.comp.map(&f, &mut glyph_ids, self.best_ratio);
if ratio > self.best_ratio {
self.best_ratio = ratio;
Expand Down
Loading