Add support for rustdoc root URL mappings.

ci/azure-install-rust.yml

@@ -5,7 +5,7 @@ steps:
       rustup component remove --toolchain=$TOOLCHAIN rust-docs || echo "already removed"
       rustup update --no-self-update $TOOLCHAIN
       if [[ "$TOOLCHAIN" == "nightly"* ]]; then
-        rustup component add --toolchain=$TOOLCHAIN rustc-dev llvm-tools-preview
+        rustup component add --toolchain=$TOOLCHAIN rustc-dev llvm-tools-preview rust-docs
       fi
       rustup default $TOOLCHAIN
     displayName: Install rust

src/cargo/core/compiler/fingerprint.rs

@@ -73,6 +73,7 @@
 //! mtime of sources                           | ✓[^3]       |
 //! RUSTFLAGS/RUSTDOCFLAGS                     | ✓           |
 //! LTO flags                                  | ✓           |
+//! config settings[^5]                        | ✓           |
 //! is_std                                     |             | ✓
 //!
 //! [^1]: Build script and bin dependencies are not included.
@@ -82,6 +83,9 @@
 //! [^4]: `__CARGO_DEFAULT_LIB_METADATA` is set by rustbuild to embed the
 //!        release channel (bootstrap/stable/beta/nightly) in libstd.
 //!
+//! [^5]: Config settings that are not otherwise captured anywhere else.
+//!       Currently, this is only `doc.extern-map`.
+//!
 //! When deciding what should go in the Metadata vs the Fingerprint, consider
 //! that some files (like dylibs) do not have a hash in their filename. Thus,
 //! if a value changes, only the fingerprint will detect the change (consider,
@@ -533,6 +537,8 @@ pub struct Fingerprint {
     /// "description", which are exposed as environment variables during
     /// compilation.
     metadata: u64,
+    /// Hash of various config settings that change how things are compiled.
+    config: u64,
     /// Description of whether the filesystem status for this unit is up to date
     /// or should be considered stale.
     #[serde(skip)]
@@ -746,6 +752,7 @@ impl Fingerprint {
             memoized_hash: Mutex::new(None),
             rustflags: Vec::new(),
             metadata: 0,
+            config: 0,
             fs_status: FsStatus::Stale,
             outputs: Vec::new(),
         }
@@ -806,6 +813,9 @@ impl Fingerprint {
         if self.metadata != old.metadata {
             bail!("metadata changed")
         }
+        if self.config != old.config {
+            bail!("configuration settings have changed")
+        }
         let my_local = self.local.lock().unwrap();
         let old_local = old.local.lock().unwrap();
         if my_local.len() != old_local.len() {
@@ -1040,12 +1050,13 @@ impl hash::Hash for Fingerprint {
             ref deps,
             ref local,
             metadata,
+            config,
             ref rustflags,
             ..
         } = *self;
         let local = local.lock().unwrap();
         (
-            rustc, features, target, path, profile, &*local, metadata, rustflags,
+            rustc, features, target, path, profile, &*local, metadata, config, rustflags,
         )
             .hash(h);
 
@@ -1252,6 +1263,14 @@ fn calculate_normal(cx: &mut Context<'_, '_>, unit: &Unit) -> CargoResult<Finger
     // Include metadata since it is exposed as environment variables.
     let m = unit.pkg.manifest().metadata();
     let metadata = util::hash_u64((&m.authors, &m.description, &m.homepage, &m.repository));
+    let config = if unit.mode.is_doc() && cx.bcx.config.cli_unstable().rustdoc_map {
+        cx.bcx
+            .config
+            .doc_extern_map()
+            .map_or(0, |map| util::hash_u64(map))
+    } else {
+        0
+    };
     Ok(Fingerprint {
         rustc: util::hash_u64(&cx.bcx.rustc().verbose_version),
         target: util::hash_u64(&unit.target),
@@ -1264,6 +1283,7 @@ fn calculate_normal(cx: &mut Context<'_, '_>, unit: &Unit) -> CargoResult<Finger
         local: Mutex::new(local),
         memoized_hash: Mutex::new(None),
         metadata,
+        config,
         rustflags: extra_flags,
         fs_status: FsStatus::Stale,
         outputs,

src/cargo/core/compiler/mod.rs

@@ -13,6 +13,7 @@ mod layout;
 mod links;
 mod lto;
 mod output_depinfo;
+pub mod rustdoc;
 pub mod standard_lib;
 mod timings;
 mod unit;
@@ -570,6 +571,7 @@ fn rustdoc(cx: &mut Context<'_, '_>, unit: &Unit) -> CargoResult<Work> {
     }
 
     build_deps_args(&mut rustdoc, cx, unit)?;
+    rustdoc::add_root_urls(cx, unit, &mut rustdoc)?;
 
     rustdoc.args(bcx.rustdocflags_args(unit));
 

src/cargo/core/compiler/rustdoc.rs

@@ -0,0 +1,172 @@
+//! Utilities for building with rustdoc.
+
+use crate::core::compiler::context::Context;
+use crate::core::compiler::unit::Unit;
+use crate::core::compiler::CompileKind;
+use crate::sources::CRATES_IO_REGISTRY;
+use crate::util::errors::{internal, CargoResult};
+use crate::util::ProcessBuilder;
+use std::collections::HashMap;
+use std::fmt;
+use std::hash;
+use url::Url;
+
+/// Mode used for `std`.
+#[derive(Debug, Hash)]
+pub enum RustdocExternMode {
+    /// Use a local `file://` URL.
+    Local,
+    /// Use a remote URL to https://doc.rust-lang.org/ (default).
+    Remote,
+    /// An arbitrary URL.
+    Url(String),
+}
+
+impl From<String> for RustdocExternMode {
+    fn from(s: String) -> RustdocExternMode {
+        match s.as_ref() {
+            "local" => RustdocExternMode::Local,
+            "remote" => RustdocExternMode::Remote,
+            _ => RustdocExternMode::Url(s),
+        }
+    }
+}
+
+impl fmt::Display for RustdocExternMode {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match self {
+            RustdocExternMode::Local => "local".fmt(f),
+            RustdocExternMode::Remote => "remote".fmt(f),
+            RustdocExternMode::Url(s) => s.fmt(f),
+        }
+    }
+}
+
+impl<'de> serde::de::Deserialize<'de> for RustdocExternMode {
+    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
+    where
+        D: serde::de::Deserializer<'de>,
+    {
+        let s = String::deserialize(deserializer)?;
+        Ok(s.into())
+    }
+}
+
+#[derive(serde::Deserialize, Debug)]
+pub struct RustdocExternMap {
+    registries: HashMap<String, String>,
+    std: Option<RustdocExternMode>,
+}
+
+impl hash::Hash for RustdocExternMap {
+    fn hash<H: hash::Hasher>(&self, into: &mut H) {
+        self.std.hash(into);
+        for (key, value) in &self.registries {
+            key.hash(into);
+            value.hash(into);
+        }
+    }
+}
+
+pub fn add_root_urls(
+    cx: &Context<'_, '_>,
+    unit: &Unit,
+    rustdoc: &mut ProcessBuilder,
+) -> CargoResult<()> {
+    let config = cx.bcx.config;
+    if !config.cli_unstable().rustdoc_map {
+        log::debug!("`doc.extern-map` ignored, requires -Zrustdoc-map flag");
+        return Ok(());
+    }
+    let map = config.doc_extern_map()?;
+    if map.registries.len() == 0 && map.std.is_none() {
+        // Skip doing unnecessary work.
+        return Ok(());
+    }
+    let mut unstable_opts = false;
+    // Collect mapping of registry name -> index url.
+    let name2url: HashMap<&String, Url> = map
+        .registries
+        .keys()
+        .filter_map(|name| {
+            if let Ok(index_url) = config.get_registry_index(name) {
+                return Some((name, index_url));
+            } else {
+                log::warn!(
+                    "`doc.extern-map.{}` specifies a registry that is not defined",
+                    name
+                );
+                return None;
+            }
+        })
+        .collect();
+    for dep in cx.unit_deps(unit) {
+        if dep.unit.target.is_linkable() && !dep.unit.mode.is_doc() {
+            for (registry, location) in &map.registries {
+                let sid = dep.unit.pkg.package_id().source_id();
+                let matches_registry = || -> bool {
+                    if !sid.is_registry() {
+                        return false;
+                    }
+                    if sid.is_default_registry() {
+                        return registry == CRATES_IO_REGISTRY;
+                    }
+                    if let Some(index_url) = name2url.get(registry) {
+                        return index_url == sid.url();
+                    }
+                    false
+                };
+                if matches_registry() {
+                    let mut url = location.clone();
+                    if !url.contains("{pkg_name}") && !url.contains("{version}") {
+                        if !url.ends_with('/') {
+                            url.push('/');
+                        }
+                        url.push_str("{pkg_name}/{version}/");
+                    }
+                    let url = url
+                        .replace("{pkg_name}", &dep.unit.pkg.name())
+                        .replace("{version}", &dep.unit.pkg.version().to_string());
+                    rustdoc.arg("--extern-html-root-url");
+                    rustdoc.arg(format!("{}={}", dep.unit.target.crate_name(), url));
+                    unstable_opts = true;
+                }
+            }
+        }
+    }
+    let std_url = match &map.std {
+        None | Some(RustdocExternMode::Remote) => None,
+        Some(RustdocExternMode::Local) => {
+            let sysroot = &cx.bcx.target_data.info(CompileKind::Host).sysroot;
+            let html_root = sysroot.join("share").join("doc").join("rust").join("html");
+            if html_root.exists() {
+                let url = Url::from_file_path(&html_root).map_err(|()| {
+                    internal(format!(
+                        "`{}` failed to convert to URL",
+                        html_root.display()
+                    ))
+                })?;
+                Some(url.to_string())
+            } else {
+                log::warn!(
+                    "`doc.extern-map.std` is \"local\", but local docs don't appear to exist at {}",
+                    html_root.display()
+                );
+                None
+            }
+        }
+        Some(RustdocExternMode::Url(s)) => Some(s.to_string()),
+    };
+    if let Some(url) = std_url {
+        for name in &["std", "core", "alloc", "proc_macro"] {
+            rustdoc.arg("--extern-html-root-url");
+            rustdoc.arg(format!("{}={}", name, url));
+            unstable_opts = true;
+        }
+    }
+
+    if unstable_opts {
+        rustdoc.arg("-Zunstable-options");
+    }
+    Ok(())
+}

src/cargo/core/features.rs

@@ -356,6 +356,7 @@ pub struct CliUnstable {
     pub crate_versions: bool,
     pub separate_nightlies: bool,
     pub multitarget: bool,
+    pub rustdoc_map: bool,
 }
 
 impl CliUnstable {
@@ -435,6 +436,7 @@ impl CliUnstable {
             "crate-versions" => self.crate_versions = parse_empty(k, v)?,
             "separate-nightlies" => self.separate_nightlies = parse_empty(k, v)?,
             "multitarget" => self.multitarget = parse_empty(k, v)?,
+            "rustdoc-map" => self.rustdoc_map = parse_empty(k, v)?,
             _ => bail!("unknown `-Z` flag specified: {}", k),
         }
 

src/cargo/util/config/mod.rs

@@ -70,6 +70,7 @@ use serde::Deserialize;
 use url::Url;
 
 use self::ConfigValue as CV;
+use crate::core::compiler::rustdoc::RustdocExternMap;
 use crate::core::shell::Verbosity;
 use crate::core::{nightly_features_allowed, CliUnstable, Shell, SourceId, Workspace};
 use crate::ops;
@@ -172,6 +173,7 @@ pub struct Config {
     net_config: LazyCell<CargoNetConfig>,
     build_config: LazyCell<CargoBuildConfig>,
     target_cfgs: LazyCell<Vec<(String, TargetCfgConfig)>>,
+    doc_extern_map: LazyCell<RustdocExternMap>,
 }
 
 impl Config {
@@ -241,6 +243,7 @@ impl Config {
             net_config: LazyCell::new(),
             build_config: LazyCell::new(),
             target_cfgs: LazyCell::new(),
+            doc_extern_map: LazyCell::new(),
         }
     }
 
@@ -1008,12 +1011,16 @@ impl Config {
     /// Gets the index for a registry.
     pub fn get_registry_index(&self, registry: &str) -> CargoResult<Url> {
         validate_package_name(registry, "registry name", "")?;
-        Ok(
-            match self.get_string(&format!("registries.{}.index", registry))? {
-                Some(index) => self.resolve_registry_index(index)?,
-                None => bail!("No index found for registry: `{}`", registry),
-            },
-        )
+        if let Some(index) = self.get_string(&format!("registries.{}.index", registry))? {
+            self.resolve_registry_index(&index).chain_err(|| {
+                format!(
+                    "invalid index URL for registry `{}` defined in {}",
+                    registry, index.definition
+                )
+            })
+        } else {
+            bail!("no index found for registry: `{}`", registry);
+        }
     }
 
     /// Returns an error if `registry.index` is set.
@@ -1027,7 +1034,8 @@ impl Config {
         Ok(())
     }
 
-    fn resolve_registry_index(&self, index: Value<String>) -> CargoResult<Url> {
+    fn resolve_registry_index(&self, index: &Value<String>) -> CargoResult<Url> {
+        // This handles relative file: URLs, relative to the config definition.
         let base = index
             .definition
             .root(self)
@@ -1036,7 +1044,7 @@ impl Config {
         let _parsed = index.val.into_url()?;
         let url = index.val.into_url_with_base(Some(&*base))?;
         if url.password().is_some() {
-            bail!("Registry URLs may not contain passwords");
+            bail!("registry URLs may not contain passwords");
         }
         Ok(url)
     }
@@ -1154,6 +1162,14 @@ impl Config {
             .try_borrow_with(|| target::load_target_cfgs(self))
     }
 
+    pub fn doc_extern_map(&self) -> CargoResult<&RustdocExternMap> {
+        // Note: This does not support environment variables. The `Unit`
+        // fundamentally does not have access to the registry name, so there is
+        // nothing to query. Plumbing the name into SourceId is quite challenging.
+        self.doc_extern_map
+            .try_borrow_with(|| self.get::<RustdocExternMap>("doc.extern-map"))
+    }
+
     /// Returns the `[target]` table definition for the given target triple.
     pub fn target_cfg_triple(&self, target: &str) -> CargoResult<TargetConfig> {
         target::load_target_triple(self, target)