From 9018d2c455df78d3f2900b4ced3ed63962e4f11e Mon Sep 17 00:00:00 2001
From: Nicholas Nethercote <n.nethercote@gmail.com>
Date: Thu, 7 Dec 2023 09:53:08 +1100
Subject: Detect `NulInCStr` error earlier.

By making it an `EscapeError` instead of a `LitError`. This makes it
like the other errors produced when checking string literals contents,
e.g. for invalid escape sequences or bare CR chars.

NOTE: this means these errors are issued earlier, before expansion,
which changes behaviour. It will be possible to move the check back to
the later point if desired. If that happens, it's likely that all the
string literal contents checks will be delayed together.

One nice thing about this: the old approach had some code in
`report_lit_error` to calculate the span of the nul char from a range.
This code used a hardwired `+2` to account for the `c"` at the start of
a C string literal, but this should have changed to a `+3` for raw C
string literals to account for the `cr"`, which meant that the caret in
`cr"` nul error messages was one short of where it should have been. The
new approach doesn't need any of this and avoids the off-by-one error.
---
 compiler/rustc_parse/messages.ftl                          | 2 ++
 compiler/rustc_parse/src/errors.rs                         | 5 +++++
 compiler/rustc_parse/src/lexer/unescape_error_reporting.rs | 3 +++
 3 files changed, 10 insertions(+)

(limited to 'compiler/rustc_parse')

diff --git a/compiler/rustc_parse/messages.ftl b/compiler/rustc_parse/messages.ftl
index c11a6fab7e5..3c2fb53b294 100644
--- a/compiler/rustc_parse/messages.ftl
+++ b/compiler/rustc_parse/messages.ftl
@@ -613,6 +613,8 @@ parse_note_mut_pattern_usage = `mut` may be followed by `variable` and `variable
 
 parse_note_pattern_alternatives_use_single_vert = alternatives in or-patterns are separated with `|`, not `||`
 
+parse_nul_in_c_str = null characters in C string literals are not supported
+
 parse_or_pattern_not_allowed_in_fn_parameters = top-level or-patterns are not allowed in function parameters
 parse_or_pattern_not_allowed_in_let_binding = top-level or-patterns are not allowed in `let` bindings
 parse_out_of_range_hex_escape = out of range hex escape
diff --git a/compiler/rustc_parse/src/errors.rs b/compiler/rustc_parse/src/errors.rs
index 0de252707bd..ef8e9d0a248 100644
--- a/compiler/rustc_parse/src/errors.rs
+++ b/compiler/rustc_parse/src/errors.rs
@@ -2144,6 +2144,11 @@ pub enum UnescapeError {
         #[subdiagnostic]
         suggestion: MoreThanOneCharSugg,
     },
+    #[diag(parse_nul_in_c_str)]
+    NulInCStr {
+        #[primary_span]
+        span: Span,
+    },
 }
 
 #[derive(Subdiagnostic)]
diff --git a/compiler/rustc_parse/src/lexer/unescape_error_reporting.rs b/compiler/rustc_parse/src/lexer/unescape_error_reporting.rs
index fbc77f28780..3238f8e23bb 100644
--- a/compiler/rustc_parse/src/lexer/unescape_error_reporting.rs
+++ b/compiler/rustc_parse/src/lexer/unescape_error_reporting.rs
@@ -262,6 +262,9 @@ pub(crate) fn emit_unescape_error(
         EscapeError::LoneSlash => {
             dcx.emit_err(UnescapeError::LoneSlash(err_span));
         }
+        EscapeError::NulInCStr => {
+            dcx.emit_err(UnescapeError::NulInCStr { span: err_span });
+        }
         EscapeError::UnskippedWhitespaceWarning => {
             let (c, char_span) = last_char();
             dcx.emit_warn(UnescapeError::UnskippedWhitespace {
-- 
cgit 1.4.1-3-g733a5