Rollup merge of #143465 - kornelski:extern-name, r=petrochenkov

Support multiple crate versions in --extern-html-root-url

Rustdoc's `--extern-html-root-url` used to use `tcx.crate_name()` to identify crates, but that used crates' internal names from their metadata, instead of names given to them in `--extern`. That was confusing, because both `--extern…` arguments seem related and use similar syntax. Crucially, this didn't work correctly with Cargo's package aliases or multiple versions of crates.

`sess.opts.externs` lacks `CrateNum`, and `Resolver.extern_prelude` gets destroyed before `rustdoc` has a chance to see it, so I've had to save this mapping in `CStore`.

Just in case, I've kept the previous mapping by crate name as a fallback for crates that weren't matched by their extern name.

Fixes #76296

Author: samueltardieu

compiler/rustc_metadata/src/creader.rs

@@ -12,6 +12,7 @@ use rustc_data_structures::fx::FxHashSet;
 use rustc_data_structures::owned_slice::OwnedSlice;
 use rustc_data_structures::svh::Svh;
 use rustc_data_structures::sync::{self, FreezeReadGuard, FreezeWriteGuard};
+use rustc_data_structures::unord::UnordMap;
 use rustc_expand::base::SyntaxExtension;
 use rustc_fs_util::try_canonicalize;
 use rustc_hir as hir;
@@ -69,6 +70,9 @@ pub struct CStore {
     /// This crate has a `#[alloc_error_handler]` item.
     has_alloc_error_handler: bool,
 
+    /// Names that were used to load the crates via `extern crate` or paths.
+    resolved_externs: UnordMap<Symbol, CrateNum>,
+
     /// Unused externs of the crate
     unused_externs: Vec<Symbol>,
 
@@ -249,6 +253,22 @@ impl CStore {
         self.metas[cnum] = Some(Box::new(data));
     }
 
+    /// Save the name used to resolve the extern crate in the local crate
+    ///
+    /// The name isn't always the crate's own name, because `sess.opts.externs` can assign it another name.
+    /// It's also not always the same as the `DefId`'s symbol due to renames `extern crate resolved_name as defid_name`.
+    pub(crate) fn set_resolved_extern_crate_name(&mut self, name: Symbol, extern_crate: CrateNum) {
+        self.resolved_externs.insert(name, extern_crate);
+    }
+
+    /// Crate resolved and loaded via the given extern name
+    /// (corresponds to names in `sess.opts.externs`)
+    ///
+    /// May be `None` if the crate wasn't used
+    pub fn resolved_extern_crate(&self, externs_name: Symbol) -> Option<CrateNum> {
+        self.resolved_externs.get(&externs_name).copied()
+    }
+
     pub(crate) fn iter_crate_data(&self) -> impl Iterator<Item = (CrateNum, &CrateMetadata)> {
         self.metas
             .iter_enumerated()
@@ -475,6 +495,7 @@ impl CStore {
             alloc_error_handler_kind: None,
             has_global_allocator: false,
             has_alloc_error_handler: false,
+            resolved_externs: UnordMap::default(),
             unused_externs: Vec::new(),
             used_extern_options: Default::default(),
         }
@@ -511,7 +532,7 @@ impl CStore {
             // We're also sure to compare *paths*, not actual byte slices. The
             // `source` stores paths which are normalized which may be different
             // from the strings on the command line.
-            let source = self.get_crate_data(cnum).cdata.source();
+            let source = data.source();
             if let Some(entry) = externs.get(name.as_str()) {
                 // Only use `--extern crate_name=path` here, not `--extern crate_name`.
                 if let Some(mut files) = entry.files() {
@@ -1308,6 +1329,7 @@ impl CStore {
                 let path_len = definitions.def_path(def_id).data.len();
                 self.update_extern_crate(
                     cnum,
+                    name,
                     ExternCrate {
                         src: ExternCrateSource::Extern(def_id.to_def_id()),
                         span: item.span,
@@ -1332,6 +1354,7 @@ impl CStore {
 
         self.update_extern_crate(
             cnum,
+            name,
             ExternCrate {
                 src: ExternCrateSource::Path,
                 span,

compiler/rustc_metadata/src/rmeta/decoder.rs

@@ -1937,9 +1937,13 @@ impl CrateMetadata {
         self.root.decode_target_modifiers(&self.blob).collect()
     }
 
-    pub(crate) fn update_extern_crate(&mut self, new_extern_crate: ExternCrate) -> bool {
+    /// Keep `new_extern_crate` if it looks better in diagnostics
+    pub(crate) fn update_extern_crate_diagnostics(
+        &mut self,
+        new_extern_crate: ExternCrate,
+    ) -> bool {
         let update =
-            Some(new_extern_crate.rank()) > self.extern_crate.as_ref().map(ExternCrate::rank);
+            self.extern_crate.as_ref().is_none_or(|old| old.rank() < new_extern_crate.rank());
         if update {
             self.extern_crate = Some(new_extern_crate);
         }

compiler/rustc_metadata/src/rmeta/decoder/cstore_impl.rs

@@ -627,14 +627,37 @@ impl CStore {
         }
     }
 
-    pub(crate) fn update_extern_crate(&mut self, cnum: CrateNum, extern_crate: ExternCrate) {
+    /// Track how an extern crate has been loaded. Called after resolving an import in the local crate.
+    ///
+    /// * the `name` is for [`Self::set_resolved_extern_crate_name`] saving `--extern name=`
+    /// * `extern_crate` is for diagnostics
+    pub(crate) fn update_extern_crate(
+        &mut self,
+        cnum: CrateNum,
+        name: Symbol,
+        extern_crate: ExternCrate,
+    ) {
+        debug_assert_eq!(
+            extern_crate.dependency_of, LOCAL_CRATE,
+            "this function should not be called on transitive dependencies"
+        );
+        self.set_resolved_extern_crate_name(name, cnum);
+        self.update_transitive_extern_crate_diagnostics(cnum, extern_crate);
+    }
+
+    /// `CrateMetadata` uses `ExternCrate` only for diagnostics
+    fn update_transitive_extern_crate_diagnostics(
+        &mut self,
+        cnum: CrateNum,
+        extern_crate: ExternCrate,
+    ) {
         let cmeta = self.get_crate_data_mut(cnum);
-        if cmeta.update_extern_crate(extern_crate) {
+        if cmeta.update_extern_crate_diagnostics(extern_crate) {
             // Propagate the extern crate info to dependencies if it was updated.
             let extern_crate = ExternCrate { dependency_of: cnum, ..extern_crate };
             let dependencies = mem::take(&mut cmeta.dependencies);
             for &dep_cnum in &dependencies {
-                self.update_extern_crate(dep_cnum, extern_crate);
+                self.update_transitive_extern_crate_diagnostics(dep_cnum, extern_crate);
             }
             self.get_crate_data_mut(cnum).dependencies = dependencies;
         }

src/doc/rustdoc/src/unstable-features.md

@@ -395,6 +395,12 @@ flags to control that behavior. When the `--extern-html-root-url` flag is given
 one of your dependencies, rustdoc use that URL for those docs. Keep in mind that if those docs exist
 in the output directory, those local docs will still override this flag.
 
+The names in this flag are first matched against the names given in the `--extern name=` flags,
+which allows selecting between multiple crates with the same name (e.g. multiple versions of
+the same crate). For transitive dependencies that haven't been loaded via an `--extern` flag, matching
+falls backs to using crate names only, without ability to distinguish between multiple crates with
+the same name.
+
 ## `-Z force-unstable-if-unmarked`
 
 Using this flag looks like this:

src/librustdoc/formats/cache.rs

@@ -4,6 +4,7 @@ use rustc_ast::join_path_syms;
 use rustc_attr_data_structures::StabilityLevel;
 use rustc_data_structures::fx::{FxHashMap, FxHashSet, FxIndexMap, FxIndexSet};
 use rustc_hir::def_id::{CrateNum, DefId, DefIdMap, DefIdSet};
+use rustc_metadata::creader::CStore;
 use rustc_middle::ty::{self, TyCtxt};
 use rustc_span::Symbol;
 use tracing::debug;
@@ -158,18 +159,33 @@ impl Cache {
         assert!(cx.external_traits.is_empty());
         cx.cache.traits = mem::take(&mut krate.external_traits);
 
+        let render_options = &cx.render_options;
+        let extern_url_takes_precedence = render_options.extern_html_root_takes_precedence;
+        let dst = &render_options.output;
+
+        // Make `--extern-html-root-url` support the same names as `--extern` whenever possible
+        let cstore = CStore::from_tcx(tcx);
+        for (name, extern_url) in &render_options.extern_html_root_urls {
+            if let Some(crate_num) = cstore.resolved_extern_crate(Symbol::intern(name)) {
+                let e = ExternalCrate { crate_num };
+                let ___location = e.___location(Some(extern_url), extern_url_takes_precedence, dst, tcx);
+                cx.cache.extern_locations.insert(e.crate_num, ___location);
+            }
+        }
+
         // Cache where all our extern crates are located
-        // FIXME: this part is specific to HTML so it'd be nice to remove it from the common code
+        // This is also used in the JSON output.
         for &crate_num in tcx.crates(()) {
             let e = ExternalCrate { crate_num };
 
             let name = e.name(tcx);
-            let render_options = &cx.render_options;
-            let extern_url = render_options.extern_html_root_urls.get(name.as_str()).map(|u| &**u);
-            let extern_url_takes_precedence = render_options.extern_html_root_takes_precedence;
-            let dst = &render_options.output;
-            let ___location = e.___location(extern_url, extern_url_takes_precedence, dst, tcx);
-            cx.cache.extern_locations.insert(e.crate_num, ___location);
+            cx.cache.extern_locations.entry(e.crate_num).or_insert_with(|| {
+                // falls back to matching by crates' own names, because
+                // transitive dependencies and injected crates may be loaded without `--extern`
+                let extern_url =
+                    render_options.extern_html_root_urls.get(name.as_str()).map(|u| &**u);
+                e.___location(extern_url, extern_url_takes_precedence, dst, tcx)
+            });
             cx.cache.external_paths.insert(e.def_id(), (vec![name], ItemType::Module));
         }
 

tests/rustdoc/extern/extern-html-alias.rs

@@ -0,0 +1,9 @@
+//@ compile-flags:-Z unstable-options --extern-html-root-url externs_name=https://renamed.example.com  --extern-html-root-url empty=https://bad.invalid
+//@ aux-crate:externs_name=empty.rs
+//@ edition: 2018
+
+extern crate externs_name as renamed;
+
+//@ has extern_html_alias/index.html
+//@ has - '//a/@href' 'https://renamed.example.com/empty/index.html'
+pub use renamed as yet_different_name;

tests/rustdoc/extern/extern-html-fallback.rs

@@ -0,0 +1,14 @@
+//@ compile-flags:-Z unstable-options --extern-html-root-url yet_another_name=https://bad.invalid --extern-html-root-url renamed_privately=https://bad.invalid --extern-html-root-url renamed_locally=https://bad.invalid --extern-html-root-url empty=https://localhost
+//@ aux-crate:externs_name=empty.rs
+//@ edition: 2018
+
+mod m {
+    pub extern crate externs_name as renamed_privately;
+}
+
+// renaming within the crate's source code is not supposed to affect CLI flags
+extern crate externs_name as renamed_locally;
+
+//@ has extern_html_fallback/index.html
+//@ has - '//a/@href' 'https://localhost/empty/index.html'
+pub use crate::renamed_locally as yet_another_name;