about summary refs log tree commit diff
diff options
context:
space:
mode:
authorTyler Mandry <tmandry@gmail.com>2020-09-01 18:24:46 -0700
committerGitHub <noreply@github.com>2020-09-01 18:24:46 -0700
commit56b5de2f2938db95060c7bcc8130d509c555c11f (patch)
treea404029f91e0bd4e047c169861109756eb87ce5e
parentc22de44a80529ddee669b94b9589bd78d15a4e6a (diff)
parentb1491eacfc2f2ff05ff2a1d3b557c30e15c5f81f (diff)
downloadrust-56b5de2f2938db95060c7bcc8130d509c555c11f.tar.gz
rust-56b5de2f2938db95060c7bcc8130d509c555c11f.zip
Rollup merge of #76218 - petrochenkov:shebang3, r=matklad
lexer: Tiny improvement to shebang detection

Lexer now discerns between regular comments and doc comments, so use that.
The change only affects the choice of reported errors.
-rw-r--r--compiler/rustc_lexer/src/lib.rs14
-rw-r--r--src/test/ui/parser/shebang/shebang-doc-comment.rs5
-rw-r--r--src/test/ui/parser/shebang/shebang-doc-comment.stderr8
3 files changed, 14 insertions, 13 deletions
diff --git a/compiler/rustc_lexer/src/lib.rs b/compiler/rustc_lexer/src/lib.rs
index b7d6194cd77..44999bbe857 100644
--- a/compiler/rustc_lexer/src/lib.rs
+++ b/compiler/rustc_lexer/src/lib.rs
@@ -191,12 +191,16 @@ pub fn strip_shebang(input: &str) -> Option<usize> {
     // For simplicity we consider any line starting with `#!` a shebang,
     // regardless of restrictions put on shebangs by specific platforms.
     if let Some(input_tail) = input.strip_prefix("#!") {
-        // Ok, this is a shebang but if the next non-whitespace token is `[` or maybe
-        // a doc comment (due to `TokenKind::(Line,Block)Comment` ambiguity at lexer level),
+        // Ok, this is a shebang but if the next non-whitespace token is `[`,
         // then it may be valid Rust code, so consider it Rust code.
-        let next_non_whitespace_token = tokenize(input_tail).map(|tok| tok.kind).find(|tok|
-            !matches!(tok, TokenKind::Whitespace | TokenKind::LineComment { .. } | TokenKind::BlockComment { .. })
-        );
+        let next_non_whitespace_token = tokenize(input_tail).map(|tok| tok.kind).find(|tok| {
+            !matches!(
+                tok,
+                TokenKind::Whitespace
+                    | TokenKind::LineComment { doc_style: None }
+                    | TokenKind::BlockComment { doc_style: None, .. }
+            )
+        });
         if next_non_whitespace_token != Some(TokenKind::OpenBracket) {
             // No other choice than to consider this a shebang.
             return Some(2 + input_tail.lines().next().unwrap_or_default().len());
diff --git a/src/test/ui/parser/shebang/shebang-doc-comment.rs b/src/test/ui/parser/shebang/shebang-doc-comment.rs
index 7dbb9eebc75..72866753e0e 100644
--- a/src/test/ui/parser/shebang/shebang-doc-comment.rs
+++ b/src/test/ui/parser/shebang/shebang-doc-comment.rs
@@ -1,6 +1,3 @@
 #!///bin/bash
 [allow(unused_variables)]
-//~^^ ERROR expected `[`, found doc comment
-
-// Doc comment is misinterpreted as a whitespace (regular comment) during shebang detection.
-// Even if it wasn't, it would still result in an error, just a different one.
+//~^ ERROR expected item, found `[`
diff --git a/src/test/ui/parser/shebang/shebang-doc-comment.stderr b/src/test/ui/parser/shebang/shebang-doc-comment.stderr
index f524f556837..2227d45ec5a 100644
--- a/src/test/ui/parser/shebang/shebang-doc-comment.stderr
+++ b/src/test/ui/parser/shebang/shebang-doc-comment.stderr
@@ -1,8 +1,8 @@
-error: expected `[`, found doc comment `///bin/bash`
-  --> $DIR/shebang-doc-comment.rs:1:3
+error: expected item, found `[`
+  --> $DIR/shebang-doc-comment.rs:2:1
    |
-LL | #!///bin/bash
-   |   ^^^^^^^^^^^ expected `[`
+LL | [allow(unused_variables)]
+   | ^ expected item
 
 error: aborting due to previous error