Auto merge of #30763 - gchp:issue/30033, r=nagisa

This is achieved by adding the scan_back method. This method looks back
through the source_text of the StringReader until it finds the target
char, returning it's offset in the source. We use this method to find
the offset of the opening single quote, and use that offset as the start
of the error.

Given this code:

```rust
fn main() {
    let _ = 'abcd';
}
```

The compiler would give a message like:

```
error: character literal may only contain one codepoint: ';
let _ = 'abcd';
             ^~
```
With this change, the message now displays:

```
error: character literal may only contain one codepoint: 'abcd';
let _ = 'abcd';
        ^~~~~~~
```

Fixes #30033

6 files changed, 81 insertions, 16 deletions

diff --git a/src/libsyntax/parse/lexer/mod.rs b/src/libsyntax/parse/lexer/mod.rs
index 1402b7888dd..3183dfbd954 100644
--- a/src/libsyntax/parse/lexer/mod.rs
+++ b/src/libsyntax/parse/lexer/mod.rs
@@ -1195,6 +1195,7 @@ impl<'a> StringReader<'a> {
             }
             '\'' => {
                 // Either a character constant 'a' OR a lifetime name 'abc
+                let start_with_quote = self.last_pos;
                 self.bump();
                 let start = self.last_pos;
 
@@ -1208,6 +1209,14 @@ impl<'a> StringReader<'a> {
                     while ident_continue(self.curr) {
                         self.bump();
                     }
+                    // lifetimes shouldn't end with a single quote
+                    // if we find one, then this is an invalid character literal
+                    if self.curr_is('\'') {
+                        panic!(self.fatal_span_verbose(
+                               start_with_quote, self.pos,
+                               String::from("character literal may only contain one codepoint")));
+
+                    }
 
                     // Include the leading `'` in the real identifier, for macro
                     // expansion purposes. See #12512 for the gory details of why
@@ -1233,26 +1242,22 @@ impl<'a> StringReader<'a> {
                        !keyword_checking_token.is_keyword(token::keywords::Static) {
                         self.err_span_(start, last_bpos, "invalid lifetime name");
                     }
+
                     return token::Lifetime(ident);
                 }
 
-                // Otherwise it is a character constant:
                 let valid = self.scan_char_or_byte(start,
                                                    c2,
                                                    // ascii_only =
                                                    false,
                                                    '\'');
+
                 if !self.curr_is('\'') {
-                    let last_bpos = self.last_pos;
-                    panic!(self.fatal_span_verbose(// Byte offsetting here is okay because the
-                                                   // character before position `start` is an
-                                                   // ascii single quote.
-                                                   start - BytePos(1),
-                                                   last_bpos,
-
-                                                   String::from("character literal may only \
-                                                                 contain one codepoint")));
+                    panic!(self.fatal_span_verbose(
+                           start_with_quote, self.last_pos,
+                           String::from("character literal may only contain one codepoint")));
                 }
+
                 let id = if valid {
                     self.name_from(start)
                 } else {
diff --git a/src/test/parse-fail/lex-bad-char-literals.rs b/src/test/parse-fail/lex-bad-char-literals-1.rs
index 6335632455f..7e22a11ca97 100644
--- a/src/test/parse-fail/lex-bad-char-literals.rs
+++ b/src/test/parse-fail/lex-bad-char-literals-1.rs
@@ -1,4 +1,4 @@
-// Copyright 2013 The Rust Project Developers. See the COPYRIGHT
+// Copyright 2016 The Rust Project Developers. See the COPYRIGHT
 // file at the top-level directory of this distribution and at
 // http://rust-lang.org/COPYRIGHT.
 //
@@ -25,8 +25,3 @@ static s: &'static str =
     "\●" //~ ERROR: unknown character escape
 ;
 
-// THIS MUST BE LAST, since it kills the lexer
-
-static c: char =
-    '●  //~ ERROR: character literal may only contain one codepoint
-;
diff --git a/src/test/parse-fail/lex-bad-char-literals-2.rs b/src/test/parse-fail/lex-bad-char-literals-2.rs
new file mode 100644
index 00000000000..8bd6808c5ff
--- /dev/null
+++ b/src/test/parse-fail/lex-bad-char-literals-2.rs
@@ -0,0 +1,17 @@
+// Copyright 2016 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
+
+// This test needs to the last one appearing in this file as it kills the parser
+static c: char =
+    'nope' //~ ERROR: character literal may only contain one codepoint: 'nope'
+;
+
diff --git a/src/test/parse-fail/lex-bad-char-literals-3.rs b/src/test/parse-fail/lex-bad-char-literals-3.rs
new file mode 100644
index 00000000000..92432dc8b63
--- /dev/null
+++ b/src/test/parse-fail/lex-bad-char-literals-3.rs
@@ -0,0 +1,16 @@
+// Copyright 2016 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
+
+// This test needs to the last one appearing in this file as it kills the parser
+static c: char =
+    '●●' //~ ERROR: character literal may only contain one codepoint: '●
+;
diff --git a/src/test/parse-fail/lex-bad-char-literals-4.rs b/src/test/parse-fail/lex-bad-char-literals-4.rs
new file mode 100644
index 00000000000..b230e623603
--- /dev/null
+++ b/src/test/parse-fail/lex-bad-char-literals-4.rs
@@ -0,0 +1,16 @@
+// Copyright 2016 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
+//
+// This test needs to the last one appearing in this file as it kills the parser
+static c: char =
+    '●  //~ ERROR: character literal may only contain one codepoint: '●
+;
diff --git a/src/test/parse-fail/lex-bad-char-literals-5.rs b/src/test/parse-fail/lex-bad-char-literals-5.rs
new file mode 100644
index 00000000000..5259175b186
--- /dev/null
+++ b/src/test/parse-fail/lex-bad-char-literals-5.rs
@@ -0,0 +1,16 @@
+// Copyright 2016 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
+//
+// This test needs to the last one appearing in this file as it kills the parser
+static c: char =
+    '\x10\x10'  //~ ERROR: character literal may only contain one codepoint: '\x10
+;