bjoernager/rust
bjoernager/rust
1
Fork 0
Code Activity

Rollup merge of #135557 - estebank:wtf8, r=fee1-dead

Browse source 
Point at invalid utf-8 span on user's source code

```
error: couldn't read `$DIR/not-utf8-bin-file.rs`: stream did not contain valid UTF-8
  --> $DIR/not-utf8-2.rs:6:5
   |
LL |     include!("not-utf8-bin-file.rs");
   |     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   |
note: byte `193` is not valid utf-8
  --> $DIR/not-utf8-bin-file.rs:2:14
   |
LL |     let _ = "�|�␂!5�cc␕␂��";
   |              ^
   = note: this error originates in the macro `include` (in Nightly builds, run with -Z macro-backtrace for more info)
```

When we attempt to load a Rust source code file, if there is a OS file failure we try reading the file as bytes. If that succeeds we try to turn it into UTF-8. If *that* fails, we provide additional context about *where* the file has the first invalid UTF-8 character.

Fix #76869.
This commit is contained in:
Matthias Krüger 2025-01-22 20:37:24 +01:00 • committed by GitHub
commit b4266b0bcd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 88 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

1
compiler/rustc_builtin_macros/src/lib.rs
View file

@ -16,6 +16,7 @@
#![feature(proc_macro_internals)]
#![feature(proc_macro_quote)]
#![feature(rustdoc_internals)]
#![feature(string_from_utf8_lossy_owned)]
#![feature(try_blocks)]
#![warn(unreachable_pub)]
// tidy-alphabetical-end

11
compiler/rustc_builtin_macros/src/source_util.rs
View file

@ -13,7 +13,7 @@ use rustc_expand::base::{
use rustc_expand::module::DirOwnership;
use rustc_lint_defs::BuiltinLintDiag;
use rustc_parse::parser::{ForceCollect, Parser};
use rustc_parse::{new_parser_from_file, unwrap_or_emit_fatal};
use rustc_parse::{new_parser_from_file, unwrap_or_emit_fatal, utf8_error};
use rustc_session::lint::builtin::INCOMPLETE_INCLUDE;
use rustc_span::source_map::SourceMap;
use rustc_span::{Pos, Span, Symbol};
@ -209,9 +209,10 @@ pub(crate) fn expand_include_str(
let interned_src = Symbol::intern(src);
MacEager::expr(cx.expr_str(cx.with_def_site_ctxt(bsp), interned_src))
}
Err(_) => {
let guar = cx.dcx().span_err(sp, format!("`{path}` wasn't a utf-8 file"));
DummyResult::any(sp, guar)
Err(utf8err) => {
let mut err = cx.dcx().struct_span_err(sp, format!("`{path}` wasn't a utf-8 file"));
utf8_error(cx.source_map(), path.as_str(), None, &mut err, utf8err, &bytes[..]);
DummyResult::any(sp, err.emit())
}
},
Err(dummy) => dummy,
@ -273,7 +274,7 @@ fn load_binary_file(
.and_then(|path| path.into_os_string().into_string().ok());
if let Some(new_path) = new_path {
err.span_suggestion(
err.span_suggestion_verbose(
path_span,
"there is a file with the same name in a different directory",
format!("\"{}\"", new_path.replace('\\', "/").escape_debug()),