Rollup merge of #104439 - ferrocene:pa-generate-copyright, r=pnkfelix

Add prototype to generate `COPYRIGHT` from REUSE metadata

This PR adds a prototype to generate the `COPYRIGHT` file from the metadata gathered with REUSE. There are two new tools:

* `src/tools/collect-license-metadata` invokes REUSE, parses its output and stores a concise JSON representation of the metadata in `src/etc/license-metadata.json`.
* `src/tools/generate-copyright` parses the metadata generated above, (in the future will) gather crate dependencies metadata, and renders the `COPYRIGHT.md` file.

Note that since the contents of those files are currently incorrect, rather than outputting in the paths above, the files will be stored in `build/` and not committed. This will be changed once we're confident about the metadata.

Eventually, `src/etc/license-metadata.json` will be committed into the repository and verified to be up to date by CI (similar to our GitHub Actions configuration), to avoid having people install REUSE on their local machine in most cases.

You can see the (incorrect) generated files in https://gist.github.com/pietroalbini/3f3f22b6f9cc8533abf7494b6a50cf97.

r? `@pnkfelix`

5 files changed, 77 insertions, 0 deletions

diff --git a/src/bootstrap/builder.rs b/src/bootstrap/builder.rs
index cff5fd8c5b0..8ee6d49da8f 100644
--- a/src/bootstrap/builder.rs
+++ b/src/bootstrap/builder.rs
@@ -754,6 +754,8 @@ impl<'a> Builder<'a> {
                 run::BumpStage0,
                 run::ReplaceVersionPlaceholder,
                 run::Miri,
+                run::CollectLicenseMetadata,
+                run::GenerateCopyright,
             ),
             // These commands either don't use paths, or they're special-cased in Build::build()
             Kind::Clean | Kind::Format | Kind::Setup => vec![],
diff --git a/src/bootstrap/config.rs b/src/bootstrap/config.rs
index babf09d2b93..d8c15c76e2d 100644
--- a/src/bootstrap/config.rs
+++ b/src/bootstrap/config.rs
@@ -213,6 +213,7 @@ pub struct Config {
     pub npm: Option<PathBuf>,
     pub gdb: Option<PathBuf>,
     pub python: Option<PathBuf>,
+    pub reuse: Option<PathBuf>,
     pub cargo_native_static: bool,
     pub configure_args: Vec<String>,
 
@@ -611,6 +612,7 @@ define_config! {
         nodejs: Option<String> = "nodejs",
         npm: Option<String> = "npm",
         python: Option<String> = "python",
+        reuse: Option<String> = "reuse",
         locked_deps: Option<bool> = "locked-deps",
         vendor: Option<bool> = "vendor",
         full_bootstrap: Option<bool> = "full-bootstrap",
@@ -1004,6 +1006,7 @@ impl Config {
         config.npm = build.npm.map(PathBuf::from);
         config.gdb = build.gdb.map(PathBuf::from);
         config.python = build.python.map(PathBuf::from);
+        config.reuse = build.reuse.map(PathBuf::from);
         config.submodules = build.submodules;
         set(&mut config.low_priority, build.low_priority);
         set(&mut config.compiler_docs, build.compiler_docs);
diff --git a/src/bootstrap/run.rs b/src/bootstrap/run.rs
index d49b41c5132..05de51f8cc5 100644
--- a/src/bootstrap/run.rs
+++ b/src/bootstrap/run.rs
@@ -1,3 +1,4 @@
+use std::path::PathBuf;
 use std::process::Command;
 
 use crate::builder::{Builder, RunConfig, ShouldRun, Step};
@@ -189,3 +190,65 @@ impl Step for Miri {
         builder.run(&mut miri);
     }
 }
+
+#[derive(Debug, PartialOrd, Ord, Copy, Clone, Hash, PartialEq, Eq)]
+pub struct CollectLicenseMetadata;
+
+impl Step for CollectLicenseMetadata {
+    type Output = PathBuf;
+    const ONLY_HOSTS: bool = true;
+
+    fn should_run(run: ShouldRun<'_>) -> ShouldRun<'_> {
+        run.path("src/tools/collect-license-metadata")
+    }
+
+    fn make_run(run: RunConfig<'_>) {
+        run.builder.ensure(CollectLicenseMetadata);
+    }
+
+    fn run(self, builder: &Builder<'_>) -> Self::Output {
+        let Some(reuse) = &builder.config.reuse else {
+            panic!("REUSE is required to collect the license metadata");
+        };
+
+        // Temporary location, it will be moved to src/etc once it's accurate.
+        let dest = builder.out.join("license-metadata.json");
+
+        let mut cmd = builder.tool_cmd(Tool::CollectLicenseMetadata);
+        cmd.env("REUSE_EXE", reuse);
+        cmd.env("DEST", &dest);
+        builder.run(&mut cmd);
+
+        dest
+    }
+}
+
+#[derive(Debug, PartialOrd, Ord, Copy, Clone, Hash, PartialEq, Eq)]
+pub struct GenerateCopyright;
+
+impl Step for GenerateCopyright {
+    type Output = PathBuf;
+    const ONLY_HOSTS: bool = true;
+
+    fn should_run(run: ShouldRun<'_>) -> ShouldRun<'_> {
+        run.path("src/tools/generate-copyright")
+    }
+
+    fn make_run(run: RunConfig<'_>) {
+        run.builder.ensure(GenerateCopyright);
+    }
+
+    fn run(self, builder: &Builder<'_>) -> Self::Output {
+        let license_metadata = builder.ensure(CollectLicenseMetadata);
+
+        // Temporary location, it will be moved to the proper one once it's accurate.
+        let dest = builder.out.join("COPYRIGHT.md");
+
+        let mut cmd = builder.tool_cmd(Tool::GenerateCopyright);
+        cmd.env("LICENSE_METADATA", &license_metadata);
+        cmd.env("DEST", &dest);
+        builder.run(&mut cmd);
+
+        dest
+    }
+}
diff --git a/src/bootstrap/sanity.rs b/src/bootstrap/sanity.rs
index 631d42acb93..8a40b0f64f4 100644
--- a/src/bootstrap/sanity.rs
+++ b/src/bootstrap/sanity.rs
@@ -140,6 +140,13 @@ than building it.
         .map(|p| cmd_finder.must_have(p))
         .or_else(|| cmd_finder.maybe_have("gdb"));
 
+    build.config.reuse = build
+        .config
+        .reuse
+        .take()
+        .map(|p| cmd_finder.must_have(p))
+        .or_else(|| cmd_finder.maybe_have("reuse"));
+
     // We're gonna build some custom C code here and there, host triples
     // also build some C++ shims for LLVM so we need a C++ compiler.
     for target in &build.targets {
diff --git a/src/bootstrap/tool.rs b/src/bootstrap/tool.rs
index ba329ea6c75..e0be4c432f1 100644
--- a/src/bootstrap/tool.rs
+++ b/src/bootstrap/tool.rs
@@ -380,6 +380,8 @@ bootstrap_tool!(
     HtmlChecker, "src/tools/html-checker", "html-checker";
     BumpStage0, "src/tools/bump-stage0", "bump-stage0";
     ReplaceVersionPlaceholder, "src/tools/replace-version-placeholder", "replace-version-placeholder";
+    CollectLicenseMetadata, "src/tools/collect-license-metadata", "collect-license-metadata";
+    GenerateCopyright, "src/tools/generate-copyright", "generate-copyright";
 );
 
 #[derive(Debug, Copy, Clone, Hash, PartialEq, Eq, Ord, PartialOrd)]