Rollup merge of #118691 - chfogelman:improve-cstr-error, r=fmease

Add check for possible CStr literals in pre-2021 Fixes [#118654](#118654) Adds information to errors caused by possible CStr literals in pre-2021. The lexer separates `c"str"` into two tokens if the edition is less than 2021, which later causes an error when parsing. This error now has a more helpful message that directs them to information about editions. However, the user might also have written `c "str"` in a later edition, so to not confuse people who _are_ using a recent edition, I also added a note about whitespace. We could probably figure out exactly which scenario has been encountered by examining spans and editions, but I figured it would be better not to overcomplicate the creation of the error too much. This is my first code PR and I tried to follow existing conventions as much as possible, but I probably missed something, so let me know!
rust-lang · Dec 20, 2023 · f3f9b30 · f3f9b30
2 parents 5810dee + 2c96025
commit f3f9b30
Show file tree

Hide file tree

Showing 3 changed files with 158 additions and 7 deletions.
diff --git a/compiler/rustc_parse/src/parser/diagnostics.rs b/compiler/rustc_parse/src/parser/diagnostics.rs
@@ -10,13 +10,13 @@ use crate::errors::{
     ConstGenericWithoutBracesSugg, DocCommentDoesNotDocumentAnything, DocCommentOnParamType,
     DoubleColonInBound, ExpectedIdentifier, ExpectedSemi, ExpectedSemiSugg,
     GenericParamsWithoutAngleBrackets, GenericParamsWithoutAngleBracketsSugg,
-    HelpIdentifierStartsWithNumber, InInTypo, IncorrectAwait, IncorrectSemicolon,
-    IncorrectUseOfAwait, PatternMethodParamWithoutBody, QuestionMarkInType, QuestionMarkInTypeSugg,
-    SelfParamNotFirst, StructLiteralBodyWithoutPath, StructLiteralBodyWithoutPathSugg,
-    StructLiteralNeedingParens, StructLiteralNeedingParensSugg, SuggAddMissingLetStmt,
-    SuggEscapeIdentifier, SuggRemoveComma, TernaryOperator, UnexpectedConstInGenericParam,
-    UnexpectedConstParamDeclaration, UnexpectedConstParamDeclarationSugg, UnmatchedAngleBrackets,
-    UseEqInstead, WrapType,
+    HelpIdentifierStartsWithNumber, HelpUseLatestEdition, InInTypo, IncorrectAwait,
+    IncorrectSemicolon, IncorrectUseOfAwait, PatternMethodParamWithoutBody, QuestionMarkInType,
+    QuestionMarkInTypeSugg, SelfParamNotFirst, StructLiteralBodyWithoutPath,
+    StructLiteralBodyWithoutPathSugg, StructLiteralNeedingParens, StructLiteralNeedingParensSugg,
+    SuggAddMissingLetStmt, SuggEscapeIdentifier, SuggRemoveComma, TernaryOperator,
+    UnexpectedConstInGenericParam, UnexpectedConstParamDeclaration,
+    UnexpectedConstParamDeclarationSugg, UnmatchedAngleBrackets, UseEqInstead, WrapType,
 };
 use crate::fluent_generated as fluent;
 use crate::parser;
@@ -640,6 +640,28 @@ impl<'a> Parser<'a> {
             }
         }
 
+        // Try to detect an intended c-string literal while using a pre-2021 edition. The heuristic
+        // here is to identify a cooked, uninterpolated `c` id immediately followed by a string, or
+        // a cooked, uninterpolated `cr` id immediately followed by a string or a `#`, in an edition
+        // where c-string literals are not allowed. There is the very slight possibility of a false
+        // positive for a `cr#` that wasn't intended to start a c-string literal, but identifying
+        // that in the parser requires unbounded lookahead, so we only add a hint to the existing
+        // error rather than replacing it entirely.
+        if ((self.prev_token.kind == TokenKind::Ident(sym::c, false)
+            && matches!(&self.token.kind, TokenKind::Literal(token::Lit { kind: token::Str, .. })))
+            || (self.prev_token.kind == TokenKind::Ident(sym::cr, false)
+                && matches!(
+                    &self.token.kind,
+                    TokenKind::Literal(token::Lit { kind: token::Str, .. }) | token::Pound
+                )))
+            && self.prev_token.span.hi() == self.token.span.lo()
+            && !self.token.span.at_least_rust_2021()
+        {
+            err.note("you may be trying to write a c-string literal");
+            err.note("c-string literals require Rust 2021 or later");
+            HelpUseLatestEdition::new().add_to_diagnostic(&mut err);
+        }
+
         // `pub` may be used for an item or `pub(crate)`
         if self.prev_token.is_ident_named(sym::public)
             && (self.token.can_begin_item()

diff --git a/tests/ui/editions/edition-cstr-2015-2018.rs b/tests/ui/editions/edition-cstr-2015-2018.rs
@@ -0,0 +1,62 @@
+macro_rules! construct { ($x:ident) => { $x"str" } }
+    //~^ ERROR expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `"str"`
+    //~| NOTE expected one of 8 possible tokens
+
+macro_rules! contain { () => { c"str" } }
+    //~^ ERROR expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `"str"`
+    //~| NOTE expected one of 8 possible tokens
+    //~| NOTE you may be trying to write a c-string literal
+    //~| NOTE c-string literals require Rust 2021 or later
+    //~| HELP pass `--edition 2021` to `rustc`
+    //~| NOTE for more on editions, read https://doc.rust-lang.org/edition-guide
+
+fn check_macro_construct() {
+    construct!(c); //~ NOTE in this expansion of construct!
+}
+
+fn check_macro_contain() {
+    contain!();
+    //~^ NOTE in this expansion of contain!
+    //~| NOTE in this expansion of contain!
+    //~| NOTE in this expansion of contain!
+    //~| NOTE in this expansion of contain!
+    //~| NOTE in this expansion of contain!
+}
+
+fn check_basic() {
+    c"str";
+    //~^ ERROR expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `"str"`
+    //~| NOTE expected one of 8 possible tokens
+    //~| NOTE you may be trying to write a c-string literal
+    //~| NOTE c-string literals require Rust 2021 or later
+    //~| HELP pass `--edition 2021` to `rustc`
+    //~| NOTE for more on editions, read https://doc.rust-lang.org/edition-guide
+}
+
+fn check_craw() {
+    cr"str";
+    //~^ ERROR expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `"str"`
+    //~| NOTE expected one of 8 possible tokens
+    //~| NOTE you may be trying to write a c-string literal
+    //~| NOTE c-string literals require Rust 2021 or later
+    //~| HELP pass `--edition 2021` to `rustc`
+    //~| NOTE for more on editions, read https://doc.rust-lang.org/edition-guide
+}
+
+fn check_craw_hash() {
+    cr##"str"##;
+    //~^ ERROR expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `#`
+    //~| NOTE expected one of 8 possible tokens
+    //~| NOTE you may be trying to write a c-string literal
+    //~| NOTE c-string literals require Rust 2021 or later
+    //~| HELP pass `--edition 2021` to `rustc`
+    //~| NOTE for more on editions, read https://doc.rust-lang.org/edition-guide
+}
+
+fn check_cstr_space() {
+    c "str";
+    //~^ ERROR expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `"str"`
+    //~| NOTE expected one of 8 possible tokens
+}
+
+fn main() {}
diff --git a/tests/ui/editions/edition-cstr-2015-2018.stderr b/tests/ui/editions/edition-cstr-2015-2018.stderr
@@ -0,0 +1,67 @@
+error: expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `"str"`
+  --> $DIR/edition-cstr-2015-2018.rs:27:6
+   |
+LL |     c"str";
+   |      ^^^^^ expected one of 8 possible tokens
+   |
+   = note: you may be trying to write a c-string literal
+   = note: c-string literals require Rust 2021 or later
+   = help: pass `--edition 2021` to `rustc`
+   = note: for more on editions, read https://doc.rust-lang.org/edition-guide
+
+error: expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `"str"`
+  --> $DIR/edition-cstr-2015-2018.rs:37:7
+   |
+LL |     cr"str";
+   |       ^^^^^ expected one of 8 possible tokens
+   |
+   = note: you may be trying to write a c-string literal
+   = note: c-string literals require Rust 2021 or later
+   = help: pass `--edition 2021` to `rustc`
+   = note: for more on editions, read https://doc.rust-lang.org/edition-guide
+
+error: expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `#`
+  --> $DIR/edition-cstr-2015-2018.rs:47:7
+   |
+LL |     cr##"str"##;
+   |       ^ expected one of 8 possible tokens
+   |
+   = note: you may be trying to write a c-string literal
+   = note: c-string literals require Rust 2021 or later
+   = help: pass `--edition 2021` to `rustc`
+   = note: for more on editions, read https://doc.rust-lang.org/edition-guide
+
+error: expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `"str"`
+  --> $DIR/edition-cstr-2015-2018.rs:57:7
+   |
+LL |     c "str";
+   |       ^^^^^ expected one of 8 possible tokens
+
+error: expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `"str"`
+  --> $DIR/edition-cstr-2015-2018.rs:1:44
+   |
+LL | macro_rules! construct { ($x:ident) => { $x"str" } }
+   |                                            ^^^^^ expected one of 8 possible tokens
+...
+LL |     construct!(c);
+   |     ------------- in this macro invocation
+   |
+   = note: this error originates in the macro `construct` (in Nightly builds, run with -Z macro-backtrace for more info)
+
+error: expected one of `!`, `.`, `::`, `;`, `?`, `{`, `}`, or an operator, found `"str"`
+  --> $DIR/edition-cstr-2015-2018.rs:5:33
+   |
+LL | macro_rules! contain { () => { c"str" } }
+   |                                 ^^^^^ expected one of 8 possible tokens
+...
+LL |     contain!();
+   |     ---------- in this macro invocation
+   |
+   = note: you may be trying to write a c-string literal
+   = note: c-string literals require Rust 2021 or later
+   = help: pass `--edition 2021` to `rustc`
+   = note: for more on editions, read https://doc.rust-lang.org/edition-guide
+   = note: this error originates in the macro `contain` (in Nightly builds, run with -Z macro-backtrace for more info)
+
+error: aborting due to 6 previous errors
+