Handle CRLF properly in the lexer

The lexer already ignores CRLF in between tokens, but it doesn't
properly handle carriage returns inside strings and doc comments. Teach
it to treat CRLF as LF inside these tokens, and to disallow carriage
returns that are not followed by linefeeds. This includes handling an
escaped CRLF inside a regular string token the same way it handles an
escaped LF.

This is technically a breaking change, as bare carriage returns are no
longer allowed, and CRLF sequences are now treated as LF inside strings
and doc comments, but it's very unlikely to actually affect any
real-world code.

This change is necessary to have Rust code compile on Windows the same
way it does on Unix. The mozilla/rust repository explicitly sets eol=lf
for Rust source files, but other Rust repositories don't. Notably,
rust-http cannot be compiled on Windows without converting the CRLF line
endings back to LF.

[breaking-change]

3 files changed, 75 insertions, 0 deletions

diff --git a/src/test/compile-fail/lex-bare-cr-string-literal-doc-comment.rs b/src/test/compile-fail/lex-bare-cr-string-literal-doc-comment.rs
new file mode 100644
index 00000000000..c1e5121d6dd
--- /dev/null
+++ b/src/test/compile-fail/lex-bare-cr-string-literal-doc-comment.rs
@@ -0,0 +1,30 @@
+// Copyright 2014 The Rust Project Developers. See the COPYRIGHT
+// file at the top-level directory of this distribution and at
+// http://rust-lang.org/COPYRIGHT.
+//
+// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+// ignore-tidy-cr
+
+/// doc comment with bare CR: '
'
+pub fn foo() {}
+//~^^ ERROR: bare CR not allowed in doc-comment
+
+/** block doc comment with bare CR: '
' */
+pub fn bar() {}
+//~^^ ERROR: bare CR not allowed in block doc-comment
+
+fn main() {
+    // the following string literal has a bare CR in it
+    let _s = "foo
bar"; //~ ERROR: bare CR not allowed in string
+
+    // the following string literal has a bare CR in it
+    let _s = r"bar
foo"; //~ ERROR: bare CR not allowed in raw string
+
+    // the following string literal has a bare CR in it
+    let _s = "foo\
bar"; //~ ERROR: unknown character escape: \r
+}
diff --git a/src/test/run-pass/.gitattributes b/src/test/run-pass/.gitattributes
new file mode 100644
index 00000000000..c6a6f23074d
--- /dev/null
+++ b/src/test/run-pass/.gitattributes
@@ -0,0 +1 @@
+lexer-crlf-line-endings-string-literal-doc-comment.rs -text
diff --git a/src/test/run-pass/lexer-crlf-line-endings-string-literal-doc-comment.rs b/src/test/run-pass/lexer-crlf-line-endings-string-literal-doc-comment.rs
new file mode 100644
index 00000000000..5c8db524cc2
--- /dev/null
+++ b/src/test/run-pass/lexer-crlf-line-endings-string-literal-doc-comment.rs
@@ -0,0 +1,44 @@
+// ignore-tidy-cr ignore-license

+// ignore-tidy-cr (repeated again because of tidy bug)

+// license is ignored because tidy can't handle the CRLF here properly.

+

+// Copyright 2014 The Rust Project Developers. See the COPYRIGHT

+// file at the top-level directory of this distribution and at

+// http://rust-lang.org/COPYRIGHT.

+//

+// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or

+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license

+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your

+// option. This file may not be copied, modified, or distributed

+// except according to those terms.

+

+// NB: this file needs CRLF line endings. The .gitattributes file in

+// this directory should enforce it.

+

+// ignore-pretty

+

+/// Doc comment that ends in CRLF

+pub fn foo() {}

+

+/** Block doc comment that

+ *  contains CRLF characters

+ */

+pub fn bar() {}

+

+fn main() {

+    let s = "string

+literal";

+    assert_eq!(s, "string\nliteral");

+

+    let s = "literal with \

+             escaped newline";

+    assert_eq!(s, "literal with escaped newline");

+

+    let s = r"string

+literal";

+    assert_eq!(s, "string\nliteral");

+

+    // validate that our source file has CRLF endings

+    let source = include_str!("lexer-crlf-line-endings-string-literal-doc-comment.rs");

+    assert!(source.contains("string\r\nliteral"));

+}