Canonicalize URL before using Extractscheme in DoFindAndCompareScheme functio...

src/url_util.cc

 // Copyright 2007, Google Inc.
 // All rights reserved.
 //
 // Redistribution and use in source and binary forms, with or without
 // modification, are permitted provided that the following conditions are
 // met:
 //
 //     * Redistributions of source code must retain the above copyright
 // notice, this list of conditions and the following disclaimer.
 //     * Redistributions in binary form must reproduce the above
@@ skipping 100 matching lines @@
       return true;
   }
   return false;
 }
 
 template<typename CHAR>
 bool DoFindAndCompareScheme(const CHAR* str,
                             int str_len,
                             const char* compare,
                             url_parse::Component* found_scheme) {
+  // Before extracting scheme, canonicalize the URL to remove any whitespace.
+  // This matches the canonicalization done in DoCanonicalize function.
+  url_canon::RawCanonOutputT<CHAR> whitespace_buffer;
+  int spec_len;
+  const CHAR* spec = RemoveURLWhitespace(str, str_len,
+                                         &whitespace_buffer, &spec_len);
+
   url_parse::Component our_scheme;
-  if (!url_parse::ExtractScheme(str, str_len, &our_scheme)) {
+  if (!url_parse::ExtractScheme(spec, spec_len, &our_scheme)) {
     // No scheme.
     if (found_scheme)
       *found_scheme = url_parse::Component();
     return false;
   }
   if (found_scheme)
     *found_scheme = our_scheme;
-  return CompareSchemeComponent(str, our_scheme, compare);
+  return CompareSchemeComponent(spec, our_scheme, compare);
 }
 
 template<typename CHAR>
 bool DoCanonicalize(const CHAR* in_spec, int in_spec_len,
                     url_canon::CharsetConverter* charset_converter,
                     url_canon::CanonOutput* output,
                     url_parse::Parsed* output_parsed) {
   // Remove any whitespace from the middle of the relative URL, possibly
   // copying to the new buffer.
   url_canon::RawCanonOutputT<CHAR> whitespace_buffer;
@@ skipping 328 matching lines @@
   return a_begin == a_end && b_begin == b_end;
 }
 
 bool LowerCaseEqualsASCII(const char16* a_begin,
                           const char16* a_end,
                           const char* b) {
   return DoLowerCaseEqualsASCII(a_begin, a_end, b);
 }
 
 }  // namespace url_util