Unpunycode search keywords and short names.

components/search_engines/template_url_parser.cc

 // Copyright 2014 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 "components/search_engines/template_url_parser.h"
 
 #include <algorithm>
 #include <map>
+#include <string>
 #include <vector>
 
 #include "base/logging.h"
 #include "base/memory/scoped_ptr.h"
 #include "base/strings/string_number_conversions.h"
 #include "base/strings/string_util.h"
 #include "base/strings/utf_string_conversions.h"
 #include "components/search_engines/template_url.h"
 #include "libxml/parser.h"
 #include "libxml/xmlwriter.h"
+#include "net/base/net_util.h"
 #include "ui/gfx/favicon_size.h"
 #include "url/gurl.h"
 #include "url/url_constants.h"
 
 namespace {
 
 // NOTE: libxml uses the UTF-8 encoding. As 0-127 of UTF-8 corresponds
 // to that of char, the following names are all in terms of char. This avoids
 // having to convert to wide, then do comparisons.
 
@@ skipping 215 matching lines @@
 
 // static
 void TemplateURLParsingContext::EndElementImpl(void* ctx, const xmlChar* name) {
   TemplateURLParsingContext* context =
       reinterpret_cast<TemplateURLParsingContext*>(ctx);
   switch (context->GetKnownType()) {
     case TemplateURLParsingContext::URL:
       context->ProcessURLParams();
       break;
     case TemplateURLParsingContext::SHORT_NAME:
-      context->data_.SetShortName(context->string_);
+      // If someone gives us ShortName in punycode, decode it.
+      context->data_.SetShortName(
+          base::IsStringASCII(context->string_)

[Matt Giuca, 2015/07/17 04:13:11]

This should not be unpunycoded. The ShortName field is not a domain and should
not be expected to be Punycode-encoded.

[alshabalin, 2015/07/20 14:06:38]

Done.

+              ? net::IDNToUnicode(base::UTF16ToASCII(context->string_),
+                                  std::string())
+              : context->string_);
       break;
     case TemplateURLParsingContext::IMAGE: {
       GURL image_url(base::UTF16ToUTF8(context->string_));
       if (image_url.SchemeIs(url::kDataScheme)) {
         // TODO (jcampan): bug 1169256: when dealing with data URL, we need to
         // decode the data URL in the renderer. For now, we'll just point to the
         // favicon from the URL.
         context->derive_image_from_url_ = true;
       } else if (context->image_is_valid_for_favicon_ && image_url.is_valid() &&
                  (image_url.SchemeIs(url::kHttpScheme) ||
@@ skipping 238 matching lines @@
   sax_handler.startElement = &TemplateURLParsingContext::StartElementImpl;
   sax_handler.endElement = &TemplateURLParsingContext::EndElementImpl;
   sax_handler.characters = &TemplateURLParsingContext::CharactersImpl;
   int error = xmlSAXUserParseMemory(&sax_handler, &context, data,
                                     static_cast<int>(length));
   xmlSubstituteEntitiesDefault(last_sub_entities_value);
 
   return error ?
       NULL : context.GetTemplateURL(search_terms_data, show_in_default_list);
 }