Skip to content

Switch from kuchiki to LOL_HTML #930

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 13 commits into from
Aug 3, 2020
Merged

Switch from kuchiki to LOL_HTML #930

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
d7a702e
[WIP] Initial try at LOL HTML rewriter
jyn514 Aug 2, 2020
dad0b55
Fix broken `class="rustdoc"` handling
jyn514 Aug 2, 2020
22b8bc8
Add missing html files
jyn514 Aug 2, 2020
7889db9
Remove unused files
jyn514 Aug 2, 2020
452a088
Use valid HTML for all tests
jyn514 Aug 2, 2020
d9604a2
Cleanup
jyn514 Aug 2, 2020
adb8929
Use HtmlRewriter instead of rewrite_str
jyn514 Aug 2, 2020
b39d7c3
Use log instead of println in tests
jyn514 Aug 2, 2020
b888c84
Document `rewrite_lol`
jyn514 Aug 2, 2020
cbe962b
Add whitespace
jyn514 Aug 2, 2020
ec5ca48
Make parse memory configurable and raise HTML size limit
jyn514 Aug 2, 2020
f78472b
Improve comment
jyn514 Aug 2, 2020
2dc045d
Only allot 5 MB for LOL parser
jyn514 Aug 3, 2020
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
105 changes: 105 additions & 0 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

3 changes: 2 additions & 1 deletion Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,6 @@ backtrace = "0.3"
failure = { version = "0.1.3", features = ["backtrace"] }
comrak = { version = "0.3", default-features = false }
toml = "0.5"
kuchiki = "0.8"
schemamama = "0.3"
schemamama_postgres = "0.2"
systemstat = "0.1.4"
Expand All @@ -41,6 +40,7 @@ path-slash = "0.1.3"
once_cell = { version = "1.4.0", features = ["parking_lot"] }
base64 = "0.12.1"
strum = { version = "0.18.0", features = ["derive"] }
lol_html = "0.2"

# Async
tokio = { version = "0.2.22", features = ["rt-threaded"] }
Expand Down Expand Up @@ -82,6 +82,7 @@ procfs = "0.7"

[dev-dependencies]
criterion = "0.3"
kuchiki = "0.8"
rand = "0.7.3"

[[bench]]
Expand Down
7 changes: 6 additions & 1 deletion src/config.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,8 @@ pub struct Config {
// Max size of the files served by the docs.rs frontend
pub(crate) max_file_size: usize,
pub(crate) max_file_size_html: usize,
// The most memory that can be used to parse an HTML file
pub(crate) max_parse_memory: usize,
}

impl Config {
Expand Down Expand Up @@ -55,7 +57,10 @@ impl Config {
github_accesstoken: maybe_env("CRATESFYI_GITHUB_ACCESSTOKEN")?,

max_file_size: env("DOCSRS_MAX_FILE_SIZE", 50 * 1024 * 1024)?,
max_file_size_html: env("DOCSRS_MAX_FILE_SIZE_HTML", 5 * 1024 * 1024)?,
max_file_size_html: env("DOCSRS_MAX_FILE_SIZE_HTML", 50 * 1024 * 1024)?,
// LOL HTML only uses as much memory as the size of the start tag!
// https://github.com/rust-lang/docs.rs/pull/930#issuecomment-667729380
max_parse_memory: env("DOCSRS_MAX_PARSE_MEMORY", 5 * 1024 * 1024)?,
})
}

Expand Down
14 changes: 12 additions & 2 deletions src/test/fakes.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,9 @@ pub(crate) struct FakeRelease<'a> {
readme: Option<&'a str>,
}

const DEFAULT_CONTENT: &[u8] =
b"<html><head></head><body>default content for test/fakes</body></html>";

impl<'a> FakeRelease<'a> {
pub(super) fn new(db: &'a TestDatabase, storage: Arc<Storage>) -> Self {
FakeRelease {
Expand Down Expand Up @@ -121,7 +124,14 @@ impl<'a> FakeRelease<'a> {
self
}

pub(crate) fn rustdoc_file(mut self, path: &'a str, data: &'a [u8]) -> Self {
/// Since we switched to LOL HTML, all data must have a valid <head> and <body>.
/// To avoid duplicating them in every test, this just makes up some content.
pub(crate) fn rustdoc_file(mut self, path: &'a str) -> Self {
self.rustdoc_files.push((path, DEFAULT_CONTENT));
self
}

pub(crate) fn rustdoc_file_with(mut self, path: &'a str, data: &'a [u8]) -> Self {
self.rustdoc_files.push((path, data));
self
}
Expand Down Expand Up @@ -217,7 +227,7 @@ impl<'a> FakeRelease<'a> {
let index = [&package.name, "index.html"].join("/");
let mut rustdoc_files = self.rustdoc_files;
if package.is_library() && !rustdoc_files.iter().any(|(path, _)| path == &index) {
rustdoc_files.push((&index, b"default index content"));
rustdoc_files.push((&index, DEFAULT_CONTENT));
}
for (source_path, data) in &self.source_files {
if source_path.starts_with("src/") {
Expand Down
Loading