ddidderr
5b8c92b98c
ghostty-unicode: Ghostty computes codepoint properties with the uucode Zig package (v0.2.0, Unicode 17.0.0). There is no Rust equivalent, so a trimmed UCD set is vendored in ucd/ and build.rs re-implements uucode's derivations: cell width rules incl. Ghostty's overrides for emoji modifiers and Prepend, grapheme break classes with the compile-time grapheme_break state table, the is_symbol set, and emoji presentation. Lookups are three array indexes per codepoint. Validated against the official GraphemeBreakTest.txt. ghostty-datastruct: split_tree (used for GTK splits; f16 ratios so rounding and debug diagrams match Zig), circ_buf, lru, cache_table, blocking_queue, segmented_pool, message_data, comparison, array_list_collection. intrusive_linked_list is not needed (lru is index based). lru now reports the evicted (old) key, Zig reported the new key, which appears to be a bug. Not yet covered: case_folding_full (needed by input bindings). Test Plan: - cargo test -p ghostty-unicode (16) -p ghostty-datastruct (88) - cargo clippy for both crates with -D warnings
101 lines
3.2 KiB
Rust
101 lines
3.2 KiB
Rust
//! Property set per codepoint that Ghostty cares about.
|
|
//!
|
|
//! Adding to this lets you find new properties but also potentially makes
|
|
//! our lookup tables less efficient.
|
|
//!
|
|
//! NOTE: this file is also `#[path]`-included by `build.rs`, so it must not
|
|
//! depend on anything else in the crate.
|
|
|
|
/// Grapheme break property with the control/CR/LF classes removed
|
|
/// (`uucode.x.types.GraphemeBreakNoControl`). The discriminant order matches
|
|
/// uucode and is used to index the precomputed break table.
|
|
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Default)]
|
|
#[repr(u8)]
|
|
pub enum GraphemeBreakNoControl {
|
|
#[default]
|
|
Other = 0,
|
|
Prepend,
|
|
RegionalIndicator,
|
|
SpacingMark,
|
|
L,
|
|
V,
|
|
T,
|
|
Lv,
|
|
Lvt,
|
|
Zwj,
|
|
Zwnj,
|
|
ExtendedPictographic,
|
|
EmojiModifierBase,
|
|
EmojiModifier,
|
|
// extend, ==
|
|
// zwnj +
|
|
// indic_conjunct_break_extend +
|
|
// indic_conjunct_break_linker
|
|
IndicConjunctBreakExtend,
|
|
IndicConjunctBreakLinker,
|
|
IndicConjunctBreakConsonant,
|
|
}
|
|
|
|
impl GraphemeBreakNoControl {
|
|
/// Number of variants.
|
|
pub const COUNT: usize = 17;
|
|
|
|
/// Variant name in Rust syntax (used by the table generator).
|
|
#[must_use]
|
|
pub const fn rust_name(self) -> &'static str {
|
|
match self {
|
|
Self::Other => "Other",
|
|
Self::Prepend => "Prepend",
|
|
Self::RegionalIndicator => "RegionalIndicator",
|
|
Self::SpacingMark => "SpacingMark",
|
|
Self::L => "L",
|
|
Self::V => "V",
|
|
Self::T => "T",
|
|
Self::Lv => "Lv",
|
|
Self::Lvt => "Lvt",
|
|
Self::Zwj => "Zwj",
|
|
Self::Zwnj => "Zwnj",
|
|
Self::ExtendedPictographic => "ExtendedPictographic",
|
|
Self::EmojiModifierBase => "EmojiModifierBase",
|
|
Self::EmojiModifier => "EmojiModifier",
|
|
Self::IndicConjunctBreakExtend => "IndicConjunctBreakExtend",
|
|
Self::IndicConjunctBreakLinker => "IndicConjunctBreakLinker",
|
|
Self::IndicConjunctBreakConsonant => "IndicConjunctBreakConsonant",
|
|
}
|
|
}
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Default)]
|
|
pub struct Properties {
|
|
/// Codepoint width. We clamp to [0, 2] since Ghostty handles control
|
|
/// characters and we max out at 2 for wide characters (i.e. 3-em dash
|
|
/// becomes a 2-em dash). (`u2` in Zig.)
|
|
pub width: u8,
|
|
|
|
/// Whether the code point does not contribute to the width of a grapheme
|
|
/// cluster (not used for single code point cells).
|
|
pub width_zero_in_grapheme: bool,
|
|
|
|
/// Grapheme break property.
|
|
pub grapheme_break: GraphemeBreakNoControl,
|
|
|
|
/// Emoji VS compatibility
|
|
pub emoji_vs_base: bool,
|
|
}
|
|
|
|
impl Properties {
|
|
/// Rust source expression for this value (the Zig `format`), used by the
|
|
/// build script when writing the generated tables.
|
|
#[must_use]
|
|
#[allow(clippy::trivially_copy_pass_by_ref)]
|
|
pub fn format_rust(&self) -> String {
|
|
format!(
|
|
"Properties {{ width: {}, width_zero_in_grapheme: {}, grapheme_break: GraphemeBreakNoControl::{}, emoji_vs_base: {} }}",
|
|
self.width,
|
|
self.width_zero_in_grapheme,
|
|
self.grapheme_break.rust_name(),
|
|
self.emoji_vs_base,
|
|
)
|
|
}
|
|
}
|