samypr100
42973cd9cb
## Summary Closes #1958 This adds linehaul metadata to uv's user-agent when pep 508 markers are provided to the RegistryClientBuilder. Thanks to #2381, we were able to leverage most information from markers and avoid inconsistency. Linehaul is meant to be accompanying metadata pip sends in it's user agent when talking to registries. You can see this output by running something like `python -c 'from pip._internal.network.session import user_agent; print(user_agent())'`. In PyPI, this metadata processed by the [linehaul-cloud-function](https://github.com/pypi/linehaul-cloud-function). More info about linehaul can be found in #1958. Below are some examples from pip: * Linux GHA: `pip/24.0 {"ci":true,"cpu":"x86_64","distro":{"id":"jammy","libc":{"lib":"glibc","version":"2.35"},"name":"Ubuntu","version":"22.04"},"implementation":{"name":"CPython","version":"3.12.2"},"installer":{"name":"pip","version":"24.0"},"openssl_version":"OpenSSL 3.0.2 15 Mar 2022","python":"3.12.2","rustc_version":"1.76.0","system":{"name":"Linux","release":"6.5.0-1016-azure"}}` * Windows GHA: `pip/24.0 {"ci":true,"cpu":"AMD64","implementation":{"name":"CPython","version":"3.12.2"},"installer":{"name":"pip","version":"24.0"},"openssl_version":"OpenSSL 3.0.13 30 Jan 2024","python":"3.12.2","rustc_version":"1.76.0","system":{"name":"Windows","release":"2022Server"}}` * OSX GHA: `pip/24.0 {"ci":true,"cpu":"arm64","distro":{"name":"macOS","version":"14.2.1"},"implementation":{"name":"CPython","version":"3.12.2"},"installer":{"name":"pip","version":"24.0"},"openssl_version":"OpenSSL 3.0.13 30 Jan 2024","python":"3.12.2","rustc_version":"1.76.0","system":{"name":"Darwin","release":"23.2.0"}}` Here's how uv results look like (sorry for the keys not having the same order): * Linux GHA: `uv/0.1.21 {"installer":{"name":"uv","version":"0.1.21"},"python":"3.12.2","implementation":{"name":"CPython","version":"3.12.2"},"distro":{"name":"Ubuntu","version":"22.04","id":"jammy","libc":null},"system":{"name":"Linux","release":"6.5.0-1016-azure"},"cpu":"x86_64","openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}` * Windows GHA: `uv/0.1.21 {"installer":{"name":"uv","version":"0.1.21"},"python":"3.12.2","implementation":{"name":"CPython","version":"3.12.2"},"distro":null,"system":{"name":"Windows","release":"2022Server"},"cpu":"AMD64","openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}` * OSX GHA: `uv/0.1.21 {"installer":{"name":"uv","version":"0.1.21"},"python":"3.12.2","implementation":{"name":"CPython","version":"3.12.2"},"distro":{"name":"macOS","version":"14.2.1","id":null,"libc":null},"system":{"name":"Darwin","release":"23.2.0"},"cpu":"arm64","openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}` Distro information (such as the one pip uses `from pip._vendor import distro` to retrieve instead of `platform` module) was not retrieved from markers. Instead, the linux release codename/name/version uses `sys-info` crate, adding about 50us of extra overhead on linux. The distro osx version re-used the [mac_os version implementation](https://github.com/astral-sh/uv/blob/99c992e38b220fbcda09b0b43602b3db2321480b/crates/platform-host/src/mac_os.rs) from #2381 which adds about 20us of overhead on osx. I tried to use other crates to avoid re-introducing `mac_os.rs` but most of them didn't yield satisfactory performance (40ms-60ms~) or had the wrong values needed (e.g. darwin version vs osx version). I also didn't add libc retrieval or rustc retrieval as those seem to add substantial overhead due to querying `ldd` or `rustc`. PyPy version detection was also not added to avoid adding extra overhead to [support PyPy for linehaul](https://github.com/pypa/pip/blob/24.0/src/pip/_internal/network/session.py#L123). All other behavior was kept 1-1 to match what pip's linehaul implementation does (as of 24.0). This also aligns with what was discussed in #1958. ## Test Plan Added new integration test to uv-client. --------- Co-authored-by: konstin <konstin@mailbox.org>
216 lines
6.8 KiB
Rust
216 lines
6.8 KiB
Rust
use anyhow::Result;
|
|
use futures::future;
|
|
use hyper::header::USER_AGENT;
|
|
use hyper::server::conn::Http;
|
|
use hyper::service::service_fn;
|
|
use hyper::{Body, Request, Response};
|
|
use pep508_rs::{MarkerEnvironment, StringVersion};
|
|
use platform_tags::{Arch, Os, Platform};
|
|
use tokio::net::TcpListener;
|
|
use uv_cache::Cache;
|
|
use uv_client::LineHaul;
|
|
use uv_client::RegistryClientBuilder;
|
|
use uv_version::version;
|
|
|
|
#[tokio::test]
|
|
async fn test_user_agent_has_version() -> Result<()> {
|
|
// Set up the TCP listener on a random available port
|
|
let listener = TcpListener::bind("127.0.0.1:0").await?;
|
|
let addr = listener.local_addr()?;
|
|
|
|
// Spawn the server loop in a background task
|
|
tokio::spawn(async move {
|
|
let svc = service_fn(move |req: Request<Body>| {
|
|
// Get User Agent Header and send it back in the response
|
|
let user_agent = req
|
|
.headers()
|
|
.get(USER_AGENT)
|
|
.and_then(|v| v.to_str().ok())
|
|
.map(|s| s.to_string())
|
|
.unwrap_or_default(); // Empty Default
|
|
future::ok::<_, hyper::Error>(Response::new(Body::from(user_agent)))
|
|
});
|
|
// Start Hyper Server
|
|
let (socket, _) = listener.accept().await.unwrap();
|
|
Http::new()
|
|
.http1_keep_alive(false)
|
|
.serve_connection(socket, svc)
|
|
.with_upgrades()
|
|
.await
|
|
.expect("Server Started");
|
|
});
|
|
|
|
// Initialize uv-client
|
|
let cache = Cache::temp()?;
|
|
let client = RegistryClientBuilder::new(cache).build();
|
|
|
|
// Send request to our dummy server
|
|
let res = client
|
|
.uncached_client()
|
|
.get(format!("http://{addr}"))
|
|
.send()
|
|
.await?;
|
|
|
|
// Check the HTTP status
|
|
assert!(res.status().is_success());
|
|
|
|
// Check User Agent
|
|
let body = res.text().await?;
|
|
|
|
// Verify body matches regex
|
|
assert_eq!(body, format!("uv/{}", version()));
|
|
|
|
Ok(())
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn test_user_agent_has_linehaul() -> Result<()> {
|
|
// Set up the TCP listener on a random available port
|
|
let listener = TcpListener::bind("127.0.0.1:0").await?;
|
|
let addr = listener.local_addr()?;
|
|
|
|
// Spawn the server loop in a background task
|
|
tokio::spawn(async move {
|
|
let svc = service_fn(move |req: Request<Body>| {
|
|
// Get User Agent Header and send it back in the response
|
|
let user_agent = req
|
|
.headers()
|
|
.get(USER_AGENT)
|
|
.and_then(|v| v.to_str().ok())
|
|
.map(|s| s.to_string())
|
|
.unwrap_or_default(); // Empty Default
|
|
future::ok::<_, hyper::Error>(Response::new(Body::from(user_agent)))
|
|
});
|
|
// Start Hyper Server
|
|
let (socket, _) = listener.accept().await.unwrap();
|
|
Http::new()
|
|
.http1_keep_alive(false)
|
|
.serve_connection(socket, svc)
|
|
.with_upgrades()
|
|
.await
|
|
.expect("Server Started");
|
|
});
|
|
|
|
// Add some representative markers for an Ubuntu CI runner
|
|
let markers = MarkerEnvironment {
|
|
implementation_name: "cpython".to_string(),
|
|
implementation_version: StringVersion {
|
|
string: "3.12.2".to_string(),
|
|
version: "3.12.2".parse()?,
|
|
},
|
|
os_name: "posix".to_string(),
|
|
platform_machine: "x86_64".to_string(),
|
|
platform_python_implementation: "CPython".to_string(),
|
|
platform_release: "6.5.0-1016-azure".to_string(),
|
|
platform_system: "Linux".to_string(),
|
|
platform_version: "#16~22.04.1-Ubuntu SMP Fri Feb 16 15:42:02 UTC 2024".to_string(),
|
|
python_full_version: StringVersion {
|
|
string: "3.12.2".to_string(),
|
|
version: "3.12.2".parse()?,
|
|
},
|
|
python_version: StringVersion {
|
|
string: "3.12".to_string(),
|
|
version: "3.12".parse()?,
|
|
},
|
|
sys_platform: "linux".to_string(),
|
|
};
|
|
// Linux only
|
|
let platform = Platform::new(
|
|
Os::Manylinux {
|
|
major: 2,
|
|
minor: 38,
|
|
},
|
|
Arch::X86_64,
|
|
);
|
|
|
|
// Initialize uv-client
|
|
let cache = Cache::temp()?;
|
|
let mut builder = RegistryClientBuilder::new(cache).markers(&markers);
|
|
|
|
if cfg!(target_os = "linux") {
|
|
builder = builder.platform(&platform);
|
|
}
|
|
let client = builder.build();
|
|
|
|
// Send request to our dummy server
|
|
let res = client
|
|
.uncached_client()
|
|
.get(format!("http://{addr}"))
|
|
.send()
|
|
.await?;
|
|
|
|
// Check the HTTP status
|
|
assert!(res.status().is_success());
|
|
|
|
// Check User Agent
|
|
let body = res.text().await?;
|
|
|
|
// Unpack User-Agent with linehaul
|
|
let (uv_version, uv_linehaul) = body
|
|
.split_once(' ')
|
|
.expect("Failed to split User-Agent header.");
|
|
|
|
// Deserializing Linehaul
|
|
let linehaul: LineHaul = serde_json::from_str(uv_linehaul)?;
|
|
|
|
// Assert uv version
|
|
assert_eq!(uv_version, format!("uv/{}", version()));
|
|
|
|
// Assert linehaul
|
|
let installer_info = linehaul.installer.unwrap();
|
|
let system_info = linehaul.system.unwrap();
|
|
let impl_info = linehaul.implementation.unwrap();
|
|
|
|
assert_eq!(installer_info.name.unwrap(), "uv".to_string());
|
|
assert_eq!(installer_info.version.unwrap(), version());
|
|
|
|
assert_eq!(system_info.name.unwrap(), markers.platform_system);
|
|
assert_eq!(system_info.release.unwrap(), markers.platform_release);
|
|
|
|
assert_eq!(
|
|
impl_info.name.unwrap(),
|
|
markers.platform_python_implementation
|
|
);
|
|
assert_eq!(
|
|
impl_info.version.unwrap(),
|
|
markers.python_full_version.version.to_string()
|
|
);
|
|
|
|
assert_eq!(
|
|
linehaul.python.unwrap(),
|
|
markers.python_full_version.version.to_string()
|
|
);
|
|
assert_eq!(linehaul.cpu.unwrap(), markers.platform_machine);
|
|
|
|
assert_eq!(linehaul.openssl_version, None);
|
|
assert_eq!(linehaul.setuptools_version, None);
|
|
assert_eq!(linehaul.rustc_version, None);
|
|
|
|
#[cfg(windows)]
|
|
assert_eq!(linehaul.distro, None);
|
|
|
|
// Using os_info as to confirm our values are as expected in both Linux and OSX.
|
|
#[cfg(target_os = "linux")]
|
|
{
|
|
let info = os_info::get();
|
|
let distro_info = linehaul.distro.unwrap();
|
|
assert_eq!(distro_info.id.unwrap(), info.codename().unwrap());
|
|
assert_eq!(distro_info.name.unwrap(), info.os_type().to_string());
|
|
assert_eq!(distro_info.version.unwrap(), info.version().to_string());
|
|
assert!(distro_info.libc.is_some());
|
|
}
|
|
|
|
// Using os_info as sys-info yields Darwin version, and not mac release version.
|
|
#[cfg(target_os = "macos")]
|
|
{
|
|
let info = os_info::get();
|
|
let distro_info = linehaul.distro.unwrap();
|
|
assert_eq!(distro_info.id, None);
|
|
assert_eq!(distro_info.name.unwrap(), "macOS");
|
|
assert_eq!(distro_info.version.unwrap(), info.version().to_string());
|
|
assert_eq!(distro_info.libc, None);
|
|
}
|
|
|
|
Ok(())
|
|
}
|