Improve char escaping in lexer messages

Currently ', " and \ are escaped as \', \" and \\ respectively. This
leads to confusing messages such as `error: unknown start of token: \\`
when encountering a single backslash.

Fix by emitting printable ASCII characters directly. This will still
escape \r, \n, \t and Unicode characters.

Fixes #47902

3 files changed, 33 insertions, 13 deletions

diff --git a/src/libsyntax/parse/lexer/mod.rs b/src/libsyntax/parse/lexer/mod.rs
index 0fd069b76aa..11ab84a5729 100644
--- a/src/libsyntax/parse/lexer/mod.rs
+++ b/src/libsyntax/parse/lexer/mod.rs
@@ -246,14 +246,27 @@ impl<'a> StringReader<'a> {
         self.err_span(self.mk_sp(from_pos, to_pos), m)
     }
 
+    /// Pushes a character to a message string for error reporting
+    fn push_escaped_char_for_msg(m: &mut String, c: char) {
+        match c {
+            '\u{20}'...'\u{7e}' => {
+                // Don't escape \, ' or " for user-facing messages
+                m.push(c);
+            }
+            _ => {
+                for c in c.escape_default() {
+                    m.push(c);
+                }
+            }
+        }
+    }
+
     /// Report a lexical error spanning [`from_pos`, `to_pos`), appending an
     /// escaped character to the error message
     fn fatal_span_char(&self, from_pos: BytePos, to_pos: BytePos, m: &str, c: char) -> FatalError {
         let mut m = m.to_string();
         m.push_str(": ");
-        for c in c.escape_default() {
-            m.push(c)
-        }
+        Self::push_escaped_char_for_msg(&mut m, c);
         self.fatal_span_(from_pos, to_pos, &m[..])
     }
     fn struct_fatal_span_char(&self,
@@ -264,9 +277,7 @@ impl<'a> StringReader<'a> {
                               -> DiagnosticBuilder<'a> {
         let mut m = m.to_string();
         m.push_str(": ");
-        for c in c.escape_default() {
-            m.push(c)
-        }
+        Self::push_escaped_char_for_msg(&mut m, c);
         self.sess.span_diagnostic.struct_span_fatal(self.mk_sp(from_pos, to_pos), &m[..])
     }
 
@@ -275,9 +286,7 @@ impl<'a> StringReader<'a> {
     fn err_span_char(&self, from_pos: BytePos, to_pos: BytePos, m: &str, c: char) {
         let mut m = m.to_string();
         m.push_str(": ");
-        for c in c.escape_default() {
-            m.push(c)
-        }
+        Self::push_escaped_char_for_msg(&mut m, c);
         self.err_span_(from_pos, to_pos, &m[..]);
     }
     fn struct_err_span_char(&self,
@@ -288,9 +297,7 @@ impl<'a> StringReader<'a> {
                             -> DiagnosticBuilder<'a> {
         let mut m = m.to_string();
         m.push_str(": ");
-        for c in c.escape_default() {
-            m.push(c)
-        }
+        Self::push_escaped_char_for_msg(&mut m, c);
         self.sess.span_diagnostic.struct_span_err(self.mk_sp(from_pos, to_pos), &m[..])
     }
 
diff --git a/src/test/parse-fail/bad-char-literals.rs b/src/test/parse-fail/bad-char-literals.rs
index 96311d6de17..821015ece77 100644
--- a/src/test/parse-fail/bad-char-literals.rs
+++ b/src/test/parse-fail/bad-char-literals.rs
@@ -15,7 +15,7 @@
 fn main() {
     // these literals are just silly.
     ''';
-    //~^ ERROR: character constant must be escaped: \'
+    //~^ ERROR: character constant must be escaped: '
 
     // note that this is a literal "\n" byte
     '
diff --git a/src/test/parse-fail/lex-stray-backslash.rs b/src/test/parse-fail/lex-stray-backslash.rs
new file mode 100644
index 00000000000..b6042bbdc1a
--- /dev/null
+++ b/src/test/parse-fail/lex-stray-backslash.rs
@@ -0,0 +1,13 @@
+// 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.
+
+// compile-flags: -Z parse-only
+
+\ //~ ERROR: unknown start of token: \