Auto merge of #90460 - pietroalbini:bidi-stable, r=nikomatsakis,pietroalbini 1.56.1

[stable] Fix CVE-2021-42574 and prepare Rust 1.56.1

This PR implements new lints to mitigate the impact of [CVE-2021-42574], caused by the presence of bidirectional-override Unicode codepoints in the compiled source code. [See the advisory][advisory] for more information about the vulnerability.

The changes in this PR will be released later today as part of Rust 1.56.1.

[CVE-2021-42574]: https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2021-42574
[advisory]: https://blog.rust-lang.org/2021/11/01/cve-2021-42574.html

1 files changed, 19 insertions, 1 deletions

diff --git a/compiler/rustc_errors/src/emitter.rs b/compiler/rustc_errors/src/emitter.rs
index 29f352ae585..272e367dd38 100644
--- a/compiler/rustc_errors/src/emitter.rs
+++ b/compiler/rustc_errors/src/emitter.rs
@@ -2054,8 +2054,26 @@ fn num_decimal_digits(num: usize) -> usize {
     MAX_DIGITS
 }
 
+// We replace some characters so the CLI output is always consistent and underlines aligned.
+const OUTPUT_REPLACEMENTS: &[(char, &str)] = &[
+    ('\t', "    "),   // We do our own tab replacement
+    ('\u{202A}', ""), // The following unicode text flow control characters are inconsistently
+    ('\u{202B}', ""), // supported accross CLIs and can cause confusion due to the bytes on disk
+    ('\u{202D}', ""), // not corresponding to the visible source code, so we replace them always.
+    ('\u{202E}', ""),
+    ('\u{2066}', ""),
+    ('\u{2067}', ""),
+    ('\u{2068}', ""),
+    ('\u{202C}', ""),
+    ('\u{2069}', ""),
+];
+
 fn replace_tabs(str: &str) -> String {
-    str.replace('\t', "    ")
+    let mut s = str.to_string();
+    for (c, replacement) in OUTPUT_REPLACEMENTS {
+        s = s.replace(*c, replacement);
+    }
+    s
 }
 
 fn draw_col_separator(buffer: &mut StyledBuffer, line: usize, col: usize) {