Adds option for JSON reader to allow invalid utf characters

base/json/json_parser.cc

 // Copyright (c) 2012 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "base/json/json_parser.h"
 
 #include <cmath>
 #include <utility>
 
 #include "base/logging.h"
@@ skipping 608 matching lines @@
 
   // StringBuilder will internally build a StringPiece unless a UTF-16
   // conversion occurs, at which point it will perform a copy into a
   // std::string.
   StringBuilder string(NextChar());
 
   int length = end_pos_ - start_pos_;
   int32_t next_char = 0;
 
   while (CanConsume(1)) {
+    const int start_index = index_;

[sky, 2016/11/03 19:14:14]

It may be possible to backtrack for the first valid character, but I'm keeping
it simple.

     pos_ = start_pos_ + index_;  // CBU8_NEXT is postcrement.
     CBU8_NEXT(start_pos_, index_, length, next_char);
     if (next_char < 0 || !IsValidCharacter(next_char)) {
-      ReportError(JSONReader::JSON_UNSUPPORTED_ENCODING, 1);
-      return false;
+      if ((options_ & JSON_ALLOW_NON_UTF_STRINGS) == 0) {
+        ReportError(JSONReader::JSON_UNSUPPORTED_ENCODING, 1);
+        return false;
+      }
+      string.Convert();
+      std::string invalid_string(index_ - start_index, 0);
+      memcpy(&invalid_string.front(), pos_, index_ - start_index);

[brettw, 2016/11/04 23:17:13]

Personally, I would prefer substituting it with the "Unicode replacement
character" than keeping it as-is. Various Chrome code assumes strings are
encoded properly, and I think this will be safer.

The replacement character = U+FFFD.

[sky, 2016/11/08 01:02:20]

Done.

+      string.AppendString(invalid_string);
+      continue;
     }
 
     if (next_char == '"') {
       --index_;  // Rewind by one because of CBU8_NEXT.
       out->Swap(&string);
       return true;
     }
 
     // If this character is not an escape sequence...
     if (next_char != '\\') {
@@ skipping 335 matching lines @@
                                            const std::string& description) {
   if (line || column) {
     return StringPrintf("Line: %i, column: %i, %s",
         line, column, description.c_str());
   }
   return description;
 }
 
 }  // namespace internal
 }  // namespace base