[parser] implement error reporting for Scanner errors

src/messages.h

 // Copyright 2006-2008 the V8 project authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 // The infrastructure used for (localized) message reporting in V8.
 //
 // Note: there's a big unresolved issue about ownership of the data
 // structures used by this framework.
 
 #ifndef V8_MESSAGES_H_
@@ skipping 444 matching lines @@
   T(UnexpectedTokenNumber, "Unexpected number")                                \
   T(UnexpectedTokenString, "Unexpected string")                                \
   T(UnexpectedTokenRegExp, "Unexpected regular expression")                    \
   T(UnknownLabel, "Undefined label '%'")                                       \
   T(UnterminatedArgList, "missing ) after argument list")                      \
   T(UnterminatedRegExp, "Invalid regular expression: missing /")               \
   T(UnterminatedTemplate, "Unterminated template literal")                     \
   T(UnterminatedTemplateExpr, "Missing } in template expression")              \
   T(FoundNonCallableHasInstance, "Found non-callable @@hasInstance")           \
   T(NonObjectInInstanceOfCheck, "Expecting an object in instanceof check")     \
+  T(InvalidHexEscapeSequence, "Invalid hexadecimal escape sequence")           \
+  T(InvalidUnicodeEscapeSequence, "Invalid Unicode escape sequence")           \
+  T(UndefinedUnicodeCodePoint, "Undefined Unicode code-point")                 \
+  T(UnclosedUnicodeEscapeSequence,                                             \
+    "Unclosed Unicode escape sequence --- Expected `}`")                       \

[adamk, 2016/03/18 18:21:55]

This one is weird in a couple ways:

- More traditional formatting would be "[...] sequence: expected '}'" (note
forward-single quotes, lower case, and colon instead of "---").
- In the example message test, the error doesn't actually seem all that helpful,
since there _is_ a '}', it's just too late. But maybe that's ok?

[caitp (gmail), 2016/03/21 16:15:03]

I rewrote the message to match similar-ish messages in ToT. Some of the Proxy
invariant check messages have the (expected ...) stuff in parentheses, lower
cased.
Maybe once there's more of a reason to, it could march ahead up to a set number
of characters to look for a  `}`, and choose a better error message if it finds
one? But I'm not really sure it matters that much ---- Either way it's still
more information than "Unexpected or illegal token"

   /* EvalError */                                                              \
   T(CodeGenFromStrings, "%")                                                   \
   /* URIError */                                                               \
   T(URIMalformed, "URI malformed")
 
 class MessageTemplate {
  public:
   enum Template {
 #define TEMPLATE(NAME, STRING) k##NAME,
     MESSAGE_TEMPLATES(TEMPLATE)
@@ skipping 32 matching lines @@
   static Handle<String> GetMessage(Isolate* isolate, Handle<Object> data);
   static base::SmartArrayPointer<char> GetLocalizedMessage(Isolate* isolate,
                                                            Handle<Object> data);
 };
 
 
 }  // namespace internal
 }  // namespace v8
 
 #endif  // V8_MESSAGES_H_