mirrors/uv
1
0
Fork 0
mirror of https://github.com/astral-sh/uv.git synced 2025-10-15 04:49:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Ignore non-hash fragments in HTML API responses (#11107)

Browse source 
## Summary

I'm not a fan of registries including fragments here that aren't hashes,
but the spec doesn't expressly forbid it. I think it's reasonable to
ignore them.

Specifically, the spec is here:
https://packaging.python.org/en/latest/specifications/simple-repository-api/.
It says that:

> The URL **SHOULD** include a hash in the form of a URL fragment with
the following syntax: `#<hashname>=<hashvalue>`, where `<hashname>`he
lowercase name of the hash function (such as sha256) and `<hashvalue>`
is the hex encoded digest.

But it doesn't mention other fragments.

Closes https://github.com/astral-sh/uv/issues/7257.
This commit is contained in:
Charlie Marsh 2025-01-30 13:35:11 -05:00 • committed by GitHub
parent 220821bc39
commit a440735fac
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 65 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

72
crates/uv-client/src/html.rs
View file

@ -2,12 +2,12 @@ use std::str::FromStr;
use jiff::Timestamp; use jiff::Timestamp;
use tl::HTMLTag; use tl::HTMLTag;
use tracing::{instrument, warn}; use tracing::{debug, instrument, warn};
use url::Url; use url::Url;
use uv_pep440::VersionSpecifiers; use uv_pep440::VersionSpecifiers;
use uv_pypi_types::LenientVersionSpecifiers;
use uv_pypi_types::{BaseUrl, CoreMetadata, File, Hashes, Yanked}; use uv_pypi_types::{BaseUrl, CoreMetadata, File, Hashes, Yanked};
use uv_pypi_types::{HashError, LenientVersionSpecifiers};
/// A parsed structure from PyPI "HTML" index format for a single package. /// A parsed structure from PyPI "HTML" index format for a single package.
#[derive(Debug, Clone)] #[derive(Debug, Clone)]
@ -99,7 +99,24 @@ impl SimpleHtml {
if fragment.trim().is_empty() { if fragment.trim().is_empty() {
Hashes::default() Hashes::default()
} else { } else {
Hashes::parse_fragment(&fragment)? match Hashes::parse_fragment(&fragment) {
Ok(hashes) => hashes,
Err(
err
@ (HashError::InvalidFragment(..) | HashError::InvalidStructure(..)),
) => {
// If the URL includes an irrelevant hash (e.g., `#main`), ignore it.
debug!("{err}");
Hashes::default()
}
Err(
err
@ (HashError::UnsupportedHashAlgorithm(..) | HashError::NonUtf8(..)),
) => {
// If the URL references a hash, but it's unsupported, error.
return Err(err.into());
}
}
}, },
) )
} else { } else {
@ -836,20 +853,61 @@ mod tests {
} }
#[test] #[test]
fn parse_missing_hash_value() { fn parse_unknown_fragment() {
let text = r#" let text = r#"
<!DOCTYPE html> <!DOCTYPE html>
<html> <html>
<body> <body>
<h1>Links for jinja2</h1> <h1>Links for jinja2</h1>
<a href="/whl/Jinja2-3.1.2-py3-none-any.whl#sha256">Jinja2-3.1.2-py3-none-any.whl</a><br/> <a href="/whl/Jinja2-3.1.2-py3-none-any.whl#main">Jinja2-3.1.2-py3-none-any.whl</a><br/>
</body> </body>
</html> </html>
<!--TIMESTAMP 1703347410--> <!--TIMESTAMP 1703347410-->
"#; "#;
let base = Url::parse("https://download.pytorch.org/whl/jinja2/").unwrap(); let base = Url::parse("https://download.pytorch.org/whl/jinja2/").unwrap();
let result = SimpleHtml::parse(text, &base).unwrap_err(); let result = SimpleHtml::parse(text, &base);
insta::assert_snapshot!(result, @"Unexpected fragment (expected `#sha256=...` or similar) on URL: sha256"); insta::assert_debug_snapshot!(result, @r###"
Ok(
SimpleHtml {
base: BaseUrl(
Url {
scheme: "https",
cannot_be_a_base: false,
username: "",
password: None,
host: Some(
Domain(
"download.pytorch.org",
),
),
port: None,
path: "/whl/jinja2/",
query: None,
fragment: None,
},
),
files: [
File {
core_metadata: None,
dist_info_metadata: None,
data_dist_info_metadata: None,
filename: "Jinja2-3.1.2-py3-none-any.whl",
hashes: Hashes {
md5: None,
sha256: None,
sha384: None,
sha512: None,
},
requires_python: None,
size: None,
upload_time: None,
url: "/whl/Jinja2-3.1.2-py3-none-any.whl#main",
yanked: None,
},
],
},
)
"###);
} }
#[test] #[test]