layout: Add support for white-space-collapse: break-spaces (#32388)

This change adds support for `white-space-collapse: break-spaces` and
adds initial parsing support for `overflow-wrap` and `word-break`. The
later two properties are not fully supported, only in their interaction
with `break-spaces`. This is a preliminary change preparing to implement
them.

In addition, `break_and_shape` is now forked and added to Layout 2020.
This function is going to change a lot soon and forking is preparation
for this. More code that is only used by Layout 2013 is moved from `gfx`
to that crate.

Co-authored-by: Rakhi Sharma <atbrakhi@igalia.com>
This commit is contained in:
Martin Robinson 2024-05-30 07:33:07 +02:00 committed by GitHub
parent c0dedf06d6
commit 60b4b6c9f0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
96 changed files with 410 additions and 537 deletions

View file

@ -4,106 +4,6 @@
use ucd::{Codepoint, UnicodeBlock};
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
pub enum CompressionMode {
CompressNone,
CompressWhitespace,
CompressWhitespaceNewline,
DiscardNewline,
}
// ported from Gecko's nsTextFrameUtils::TransformText.
//
// High level TODOs:
//
// * Issue #113: consider incoming text state (arabic, etc)
// and propagate outgoing text state (dual of above)
//
// * Issue #114: record skipped and kept chars for mapping original to new text
//
// * Untracked: various edge cases for bidi, CJK, etc.
pub fn transform_text(
text: &str,
mode: CompressionMode,
incoming_whitespace: bool,
output_text: &mut String,
) -> bool {
let out_whitespace = match mode {
CompressionMode::CompressNone | CompressionMode::DiscardNewline => {
for ch in text.chars() {
if is_discardable_char(ch, mode) {
// TODO: record skipped char
} else {
// TODO: record kept char
if ch == '\t' {
// TODO: set "has tab" flag
}
output_text.push(ch);
}
}
false
},
CompressionMode::CompressWhitespace | CompressionMode::CompressWhitespaceNewline => {
let mut in_whitespace: bool = incoming_whitespace;
for ch in text.chars() {
// TODO: discard newlines between CJK chars
let mut next_in_whitespace: bool = is_in_whitespace(ch, mode);
if !next_in_whitespace {
if is_always_discardable_char(ch) {
// revert whitespace setting, since this char was discarded
next_in_whitespace = in_whitespace;
// TODO: record skipped char
} else {
// TODO: record kept char
output_text.push(ch);
}
} else {
/* next_in_whitespace; possibly add a space char */
if in_whitespace {
// TODO: record skipped char
} else {
// TODO: record kept char
output_text.push(' ');
}
}
// save whitespace context for next char
in_whitespace = next_in_whitespace;
} /* /for str::each_char */
in_whitespace
},
};
return out_whitespace;
fn is_in_whitespace(ch: char, mode: CompressionMode) -> bool {
match (ch, mode) {
(' ', _) => true,
('\t', _) => true,
('\n', CompressionMode::CompressWhitespaceNewline) => true,
(_, _) => false,
}
}
fn is_discardable_char(ch: char, mode: CompressionMode) -> bool {
if is_always_discardable_char(ch) {
return true;
}
match mode {
CompressionMode::DiscardNewline | CompressionMode::CompressWhitespaceNewline => {
ch == '\n'
},
_ => false,
}
}
fn is_always_discardable_char(ch: char) -> bool {
// TODO: check for soft hyphens.
is_bidi_control(ch)
}
}
pub fn float_to_fixed(before: usize, f: f64) -> i32 {
((1i32 << before) as f64 * f) as i32
}