Skip to content

librustdoc: Use pulldown-cmark-escape for HTML escaping #137285

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

Merged
merged 1 commit into from
Feb 24, 2025
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
1 change: 1 addition & 0 deletions Cargo.lock
Original file line number Diff line number Diff line change
Expand Up @@ -4577,6 +4577,7 @@ dependencies = [
"itertools",
"minifier",
"pulldown-cmark 0.9.6",
"pulldown-cmark-escape",
"regex",
"rinja",
"rustdoc-json-types",
Expand Down
1 change: 1 addition & 0 deletions src/librustdoc/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ itertools = "0.12"
indexmap = "2"
minifier = { version = "0.3.5", default-features = false }
pulldown-cmark-old = { version = "0.9.6", package = "pulldown-cmark", default-features = false }
pulldown-cmark-escape = { version = "0.11.0", features = ["simd"] }
regex = "1"
rustdoc-json-types = { path = "../rustdoc-json-types" }
serde_json = "1.0"
Expand Down
51 changes: 3 additions & 48 deletions src/librustdoc/html/escape.rs
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@

use std::fmt;

use pulldown_cmark_escape::FmtWriter;
use unicode_segmentation::UnicodeSegmentation;

/// Wrapper struct which will emit the HTML-escaped version of the contained
Expand All @@ -13,31 +14,7 @@ pub(crate) struct Escape<'a>(pub &'a str);

impl fmt::Display for Escape<'_> {
fn fmt(&self, fmt: &mut fmt::Formatter<'_>) -> fmt::Result {
// Because the internet is always right, turns out there's not that many
// characters to escape: http://stackoverflow.com/questions/7381974
let Escape(s) = *self;
let pile_o_bits = s;
let mut last = 0;
for (i, ch) in s.char_indices() {
let s = match ch {
'>' => "&gt;",
'<' => "&lt;",
'&' => "&amp;",
'\'' => "&#39;",
'"' => "&quot;",
_ => continue,
};
fmt.write_str(&pile_o_bits[last..i])?;
fmt.write_str(s)?;
// NOTE: we only expect single byte characters here - which is fine as long as we
// only match single byte characters
last = i + 1;
}

if last < s.len() {
fmt.write_str(&pile_o_bits[last..])?;
}
Ok(())
pulldown_cmark_escape::escape_html(FmtWriter(fmt), self.0)
}
}

Expand All @@ -51,29 +28,7 @@ pub(crate) struct EscapeBodyText<'a>(pub &'a str);

impl fmt::Display for EscapeBodyText<'_> {
fn fmt(&self, fmt: &mut fmt::Formatter<'_>) -> fmt::Result {
// Because the internet is always right, turns out there's not that many
// characters to escape: http://stackoverflow.com/questions/7381974
let EscapeBodyText(s) = *self;
let pile_o_bits = s;
let mut last = 0;
for (i, ch) in s.char_indices() {
let s = match ch {
'>' => "&gt;",
'<' => "&lt;",
'&' => "&amp;",
_ => continue,
};
fmt.write_str(&pile_o_bits[last..i])?;
fmt.write_str(s)?;
// NOTE: we only expect single byte characters here - which is fine as long as we
// only match single byte characters
last = i + 1;
}

if last < s.len() {
fmt.write_str(&pile_o_bits[last..])?;
}
Ok(())
pulldown_cmark_escape::escape_html_body_text(FmtWriter(fmt), self.0)
}
}

Expand Down
Loading