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 170 matching lines @@
   }
 
  private:
   int* const depth_;
 
   DISALLOW_COPY_AND_ASSIGN(StackMarker);
 };
 
 }  // namespace
 
+const char kUnicodeReplacementString[] = "\xFF\xDF";

[brettw, 2016/11/08 19:21:19]

I'm not sure where you got this string. U+FFFD in UTF-8 is "\EF\BF\BD". Is that
what you meant?

[brettw, 2016/11/08 20:26:56]

(add x's in there after the backslashes)

[sky, 2016/11/08 23:55:35]

Done.

+
 JSONParser::JSONParser(int options)
     : options_(options),
       start_pos_(nullptr),
       pos_(nullptr),
       end_pos_(nullptr),
       index_(0),
       stack_depth_(0),
       line_number_(0),
       index_last_line_(0),
       error_code_(JSONReader::JSON_NO_ERROR),
@@ skipping 421 matching lines @@
   // std::string.
   StringBuilder string(NextChar());
 
   int length = end_pos_ - start_pos_;
   int32_t next_char = 0;
 
   while (CanConsume(1)) {
     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_REPLACE_INVALID_CHARACTERS) == 0) {
+        ReportError(JSONReader::JSON_UNSUPPORTED_ENCODING, 1);
+        return false;
+      }
+      string.Convert();
+      string.AppendString(kUnicodeReplacementString);
+      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