Rollup merge of #110436 - Mark-Simulacrum:support-xz-version, r=pietroalbini

Support loading version information from xz tarballs

This is intended to allow us to move recompression from xz (produced in CI) to gz after an initial manifest run, which produces a list of actually required artifacts. The rest are then deleted, which means that we can avoid recompressing them, saving a bunch of time.

This is essentially untested and more might be needed, will run a patched promote-release against try artifacts from this PR. If we do go ahead with this we'll either need to backport this patch to beta/stable, wait for it to propagate, or temporarily recompress to gzip but not xz tarballs (or similar).

r? `@pietroalbini`

Author: Dylan-DPC

Cargo.lock

@@ -297,6 +297,7 @@ dependencies = [
  "sha2",
  "tar",
  "toml",
+ "xz2",
 ]
 
 [[package]]
@@ -2060,9 +2061,9 @@ dependencies = [
 
 [[package]]
 name = "lzma-sys"
-version = "0.1.16"
+version = "0.1.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f24f76ec44a8ac23a31915d6e326bca17ce88da03096f1ff194925dc714dac99"
+checksum = "5fda04ab3764e6cde78b9974eec4f779acaba7c4e84b36eca3cf77c581b85d27"
 dependencies = [
  "cc",
  "libc",
@@ -5658,9 +5659,9 @@ dependencies = [
 
 [[package]]
 name = "xz2"
-version = "0.1.6"
+version = "0.1.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c179869f34fc7c01830d3ce7ea2086bc3a07e0d35289b667d0a8bf910258926c"
+checksum = "388c44dc09d76f1536602ead6d325eb532f5c122f17782bd57fb47baeeb767e2"
 dependencies = [
  "lzma-sys",
 ]

src/tools/build-manifest/Cargo.toml

@@ -9,6 +9,7 @@ serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
 anyhow = "1.0.32"
 flate2 = "1.0.16"
+xz2 = "0.1.7"
 tar = "0.4.29"
 sha2 = "0.10.1"
 rayon = "1.5.1"

src/tools/build-manifest/src/versions.rs

@@ -5,6 +5,7 @@ use std::fs::File;
 use std::io::Read;
 use std::path::{Path, PathBuf};
 use tar::Archive;
+use xz2::read::XzDecoder;
 
 const DEFAULT_TARGET: &str = "x86_64-unknown-linux-gnu";
 
@@ -175,9 +176,23 @@ impl Versions {
     }
 
     fn load_version_from_tarball(&mut self, package: &PkgType) -> Result<VersionInfo, Error> {
-        let tarball_name = self.tarball_name(package, DEFAULT_TARGET)?;
-        let tarball = self.dist_path.join(tarball_name);
+        for ext in ["xz", "gz"] {
+            let info =
+                self.load_version_from_tarball_inner(&self.dist_path.join(self.archive_name(
+                    package,
+                    DEFAULT_TARGET,
+                    &format!("tar.{}", ext),
+                )?))?;
+            if info.present {
+                return Ok(info);
+            }
+        }
+
+        // If neither tarball is present, we fallback to returning the non-present info.
+        Ok(VersionInfo::default())
+    }
 
+    fn load_version_from_tarball_inner(&mut self, tarball: &Path) -> Result<VersionInfo, Error> {
         let file = match File::open(&tarball) {
             Ok(file) => file,
             Err(err) if err.kind() == std::io::ErrorKind::NotFound => {
@@ -187,7 +202,14 @@ impl Versions {
             }
             Err(err) => return Err(err.into()),
         };
-        let mut tar = Archive::new(GzDecoder::new(file));
+        let mut tar: Archive<Box<dyn std::io::Read>> =
+            Archive::new(if tarball.extension().map_or(false, |e| e == "gz") {
+                Box::new(GzDecoder::new(file))
+            } else if tarball.extension().map_or(false, |e| e == "xz") {
+                Box::new(XzDecoder::new(file))
+            } else {
+                unimplemented!("tarball extension not recognized: {}", tarball.display())
+            });
 
         let mut version = None;
         let mut git_commit = None;