Skip to content

Text chunk handlers complications #256

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

Merged
merged 3 commits into from
Jun 20, 2025
Merged

Text chunk handlers complications #256

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
56a7a27
Fix text chunk tests
kornelski Jan 1, 2025
8bdb977
Init text buffer for charset decoding only if needed
kornelski Jun 12, 2025
3d68c39
Test with smaller buffers
kornelski Jan 1, 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
4 changes: 3 additions & 1 deletion src/rewritable_units/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,7 +143,9 @@ mod test_utils {
|c: &[u8]| output.push(c),
);

rewriter.write(html).unwrap();
for ch in html.chunks(15) {
rewriter.write(ch).unwrap();
}
rewriter.end().unwrap();
}

Expand Down
13 changes: 10 additions & 3 deletions src/rewritable_units/text_decoder.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,8 @@ use crate::base::SharedEncoding;
use crate::rewriter::RewritingError;
use encoding_rs::{CoderResult, Decoder, Encoding, UTF_8};

const DEFAULT_BUFFER_LEN: usize = if cfg!(test) { 13 } else { 1024 };

pub(crate) struct TextDecoder {
encoding: SharedEncoding,
pending_text_streaming_decoder: Option<Decoder>,
Expand All @@ -15,8 +17,9 @@ impl TextDecoder {
Self {
encoding,
pending_text_streaming_decoder: None,
// TODO make adjustable
text_buffer: String::from_utf8(vec![0u8; 1024]).unwrap(),
// this will be later initialized to DEFAULT_BUFFER_LEN,
// because encoding_rs wants a slice
text_buffer: String::new(),
}
}

Expand Down Expand Up @@ -52,6 +55,10 @@ impl TextDecoder {
}
}

if self.pending_text_streaming_decoder.is_none() && self.text_buffer.is_empty() {
// repeat() avoids utf8 check comapred to `String::from_utf8(vec![0; len])`
self.text_buffer = "\0".repeat(DEFAULT_BUFFER_LEN);
}
let decoder = self
.pending_text_streaming_decoder
.get_or_insert_with(|| encoding.new_decoder_without_bom_handling());
Expand Down Expand Up @@ -113,7 +120,7 @@ impl TextDecoder {
// The slow path buffers 1KB, and even though this shouldn't matter,
// it is an observable behavior, and it makes bugs worse for text handlers
// that assume they'll get only a single chunk.
if valid_up_to != raw_input.len() && valid_up_to < self.text_buffer.len() {
if valid_up_to != raw_input.len() && valid_up_to < DEFAULT_BUFFER_LEN {
return None;
}

Expand Down
78 changes: 42 additions & 36 deletions src/rewritable_units/tokens/text_chunk.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,32 +412,27 @@ mod tests {
};
}

macro_rules! skip_eof_chunk {
($c:ident) => {
if $c.last_in_text_node() {
// This is not always true — a replacement char for an incomplete UTF-8 sequence could be flushed last
assert!($c.as_str().is_empty());
return;
}
};
}

#[test]
fn parsed() {
test!(|_| {}, HTML);
}

#[test]
fn with_prepends_and_appends() {
let mut first = true;
test!(
|c| {
skip_eof_chunk!(c);
c.before("<span>", ContentType::Text);
c.before("<div>Hey</div>", ContentType::Html);
c.before("<foo>", ContentType::Html);
c.after("</foo>", ContentType::Html);
c.after("<!-- 42 -->", ContentType::Html);
c.after("<foo & bar>", ContentType::Text);
let is_first = std::mem::replace(&mut first, c.last_in_text_node());
if is_first {
c.before("<span>", ContentType::Text);
c.before("<div>Hey</div>", ContentType::Html);
c.before("<foo>", ContentType::Html);
}
if c.last_in_text_node() {
c.after("</foo>", ContentType::Html);
c.after("<!-- 42 -->", ContentType::Html);
c.after("<foo & bar>", ContentType::Text);
}
},
concat!(
"&lt;span&gt;<div>Hey</div><foo>",
Expand All @@ -452,17 +447,22 @@ mod tests {

#[test]
fn removed() {
let mut first = true;
test!(
|c| {
skip_eof_chunk!(c);
let is_first = std::mem::replace(&mut first, c.last_in_text_node());
assert!(!c.removed());

c.remove();

assert!(c.removed());

c.before("<before>", ContentType::Html);
c.after("<after>", ContentType::Html);
if is_first {
c.before("<before>", ContentType::Html);
}
if c.last_in_text_node() {
c.after("<after>", ContentType::Html);
}
},
"<before><after>"
);
Expand All @@ -472,17 +472,20 @@ mod tests {
fn replaced_with_text() {
test!(
|c| {
skip_eof_chunk!(c);
c.before("<before>", ContentType::Html);
c.after("<after>", ContentType::Html);
if c.last_in_text_node() {
c.before("<before>", ContentType::Html);
c.after("<after>", ContentType::Html);

assert!(!c.removed());
assert!(!c.removed());

c.replace("<div></div>", ContentType::Html);
c.replace("<!--42-->", ContentType::Html);
c.replace("<foo & bar>", ContentType::Text);
c.replace("<div></div>", ContentType::Html);
c.replace("<!--42-->", ContentType::Html);
c.replace("<foo & bar>", ContentType::Text);

assert!(c.removed());
assert!(c.removed());
} else {
c.remove();
}
},
"<before>&lt;foo &amp; bar&gt;<after>"
);
Expand All @@ -492,17 +495,20 @@ mod tests {
fn replaced_with_html() {
test!(
|c| {
skip_eof_chunk!(c);
c.before("<before>", ContentType::Html);
c.after("<after>", ContentType::Html);
if c.last_in_text_node() {
c.before("<before>", ContentType::Html);
c.after("<after>", ContentType::Html);

assert!(!c.removed());
assert!(!c.removed());

c.replace("<div></div>", ContentType::Html);
c.replace("<!--42-->", ContentType::Html);
c.replace("<foo & bar>", ContentType::Html);
c.replace("<div></div>", ContentType::Html);
c.replace("<!--42-->", ContentType::Html);
c.replace("<foo & bar>", ContentType::Html);

assert!(c.removed());
assert!(c.removed());
} else {
c.remove();
}
},
"<before><foo & bar><after>"
);
Expand Down