Auto merge of #116001 - fmease:validate-crate-name-extern-cli-opt, r=est31

[breaking change] Validate crate name in `--extern` [MCP 650]

Reject non-ASCII-identifier crate names passed to the CLI option `--extern` (`rustc`, `rustdoc`).
Implements [MCP 650](https://github.com/rust-lang/compiler-team/issues/650) (except that we only allow ASCII identifiers not arbitrary Rust identifiers).
Fixes #113035.

[As mentioned on Zulip](https://rust-lang.zulipchat.com/#narrow/stream/233931-t-compiler.2Fmajor-changes/topic/Disallow.20non-identifier-valid.20--extern.20cr.E2.80.A6.20compiler-team.23650/near/376826988), doing a crater run probably doesn't make sense since it wouldn't yield anything. Most users don't interact with `rustc` directly but only ever through Cargo which always passes a valid crate name to `--extern` when it invokes `rustc` and `rustdoc`. In any case, the user wouldn't be able to use such a crate name in the source code anyway.

Note that I'm not using [`rustc_session::output::validate_crate_name`](https://doc.rust-lang.org/nightly/nightly-rustc/rustc_session/output/fn.validate_crate_name.html) (used for `--crate-name` and `#![crate_name]`) since the latter doesn't reject non-ASCII crate names and ones that start with a digit.

As an aside, I've also thought about getting rid of `validate_crate_name` entirely in a separate PR (with another MCP) in favor of `is_ascii_ident` to reject more weird `--crate-name`s, `#![crate_name]`s and file names but I think that would lead to a lot of actual breakage, namely because of file names starting with a digit. In `tests/ui` 9 tests would be impacted for example.

CC `@estebank`
r? `@est31`

3 files changed, 31 insertions, 0 deletions

diff --git a/compiler/rustc_session/src/config.rs b/compiler/rustc_session/src/config.rs
index 956ae149e55..d29ab02c1a6 100644
--- a/compiler/rustc_session/src/config.rs
+++ b/compiler/rustc_session/src/config.rs
@@ -2475,6 +2475,19 @@ pub fn parse_externs(
             Some((opts, name)) => (Some(opts), name.to_string()),
         };
 
+        if !crate::utils::is_ascii_ident(&name) {
+            let mut error = handler.early_struct_error(format!(
+                "crate name `{name}` passed to `--extern` is not a valid ASCII identifier"
+            ));
+            let adjusted_name = name.replace("-", "_");
+            if crate::utils::is_ascii_ident(&adjusted_name) {
+                error.help(format!(
+                    "consider replacing the dashes with underscores: `{adjusted_name}`"
+                ));
+            }
+            error.emit();
+        }
+
         let path = path.map(|p| CanonicalizedPath::new(p));
 
         let entry = externs.entry(name.to_owned());
diff --git a/compiler/rustc_session/src/session.rs b/compiler/rustc_session/src/session.rs
index 86f4e7b48da..b484978eed2 100644
--- a/compiler/rustc_session/src/session.rs
+++ b/compiler/rustc_session/src/session.rs
@@ -1726,6 +1726,15 @@ impl EarlyErrorHandler {
 
     #[allow(rustc::untranslatable_diagnostic)]
     #[allow(rustc::diagnostic_outside_of_impl)]
+    pub(crate) fn early_struct_error(
+        &self,
+        msg: impl Into<DiagnosticMessage>,
+    ) -> DiagnosticBuilder<'_, !> {
+        self.handler.struct_fatal(msg)
+    }
+
+    #[allow(rustc::untranslatable_diagnostic)]
+    #[allow(rustc::diagnostic_outside_of_impl)]
     pub fn early_warn(&self, msg: impl Into<DiagnosticMessage>) {
         self.handler.struct_warn(msg).emit()
     }
diff --git a/compiler/rustc_session/src/utils.rs b/compiler/rustc_session/src/utils.rs
index f76c69af526..aea7c6c2842 100644
--- a/compiler/rustc_session/src/utils.rs
+++ b/compiler/rustc_session/src/utils.rs
@@ -158,3 +158,12 @@ pub fn extra_compiler_flags() -> Option<(Vec<String>, bool)> {
 
     if !result.is_empty() { Some((result, excluded_cargo_defaults)) } else { None }
 }
+
+pub(crate) fn is_ascii_ident(string: &str) -> bool {
+    let mut chars = string.chars();
+    if let Some(start) = chars.next() && (start.is_ascii_alphabetic() || start == '_') {
+        chars.all(|char| char.is_ascii_alphanumeric() || char == '_')
+    } else {
+        false
+    }
+}