Omnibox - Do Not Allow HTTP/HTTPS Equivalence if User Explicitly Entered A Scheme

components/omnibox/autocomplete_match.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/omnibox/autocomplete_match.h"
 
 #include "base/i18n/time_formatting.h"
 #include "base/logging.h"
 #include "base/strings/string16.h"
 #include "base/strings/string_number_conversions.h"
 #include "base/strings/string_piece.h"
 #include "base/strings/string_util.h"
 #include "base/strings/utf_string_conversions.h"
 #include "base/time/time.h"
 #include "components/omnibox/autocomplete_provider.h"
 #include "components/omnibox/suggestion_answer.h"
 #include "components/search_engines/template_url.h"
 #include "components/search_engines/template_url_service.h"
 #include "grit/components_scaled_resources.h"
 
 namespace {
 
 bool IsTrivialClassification(const ACMatchClassifications& classifications) {
   return classifications.empty() ||
       ((classifications.size() == 1) &&
        (classifications.back().style == ACMatchClassification::NONE));
 }
 
+// Returns true if one of the input words includes a scheme and followed by
+// something that matches at the beginning of the URL's hostname.  This
+// indicates that the user desires this URL loaded with this scheme in
+// particular.
+bool InputIncludesSchemePlusPartOfHost(
+    const std::vector<base::string16>& input_words,
+    const GURL& url) {
+  // Find scheme separator and see if the stuff following it matches the
+  // beginning of the URL (after the scheme).
+  const base::string16& separator_as_utf16 =
+      base::UTF8ToUTF16(url::kStandardSchemeSeparator);
+  const base::string16& url_spec_without_scheme_as_utf16 =
+      base::UTF8ToUTF16(url.spec().substr(
+          url.scheme().length() +
+          std::string(url::kStandardSchemeSeparator).length()));

[Peter Kasting, 2015/06/01 21:04:08]

Why not just url.host().begin?

[Mark P, 2015/06/01 22:05:50]

If there is a username or password, url.host() position will be wrong.  I could
write conditional logic to figure out the position depending on the presence of
either of those two fields.  This + length seemed simplier.

[Peter Kasting, 2015/06/01 22:21:58]

Maybe url.GetContent() then?

[Mark P, 2015/06/04 23:31:31]

I think that's still ugly.  It's require a shift because GetContent returns, for
example, //www.google.com
(i.e., it's everything after the colon, not the scheme separator)

+  for (auto it : input_words) {
+    const size_t pos = it.find(separator_as_utf16);
+    if ((pos != base::string16::npos) &&
+        StartsWith(url_spec_without_scheme_as_utf16,
+                  it.substr(pos + separator_as_utf16.length()), false)) {

[Peter Kasting, 2015/06/01 21:04:08]

Won't this find input like "://foo"?  Shouldn't we be checking for the input to
actually have a scheme?

[Mark P, 2015/06/01 22:05:50]

Yes.  Do you want me to add a length>0 check?

[Peter Kasting, 2015/06/01 22:21:58]

Maybe instead we should do something like check url::IsStandard(it.data(),
url::Component(0, pos)).

[Mark P, 2015/06/04 23:31:31]

I'll prefer to add the >0 test.  I don't see any reason to require that the
scheme the user entered is a standard scheme.  Matching the suggestion is enough
(though in reality I don't think we ever suggest anything with non-standard
scheme).

+      return true;
+    }
+  }
+  return false;
+}
+
 }  // namespace
 
 // AutocompleteMatch ----------------------------------------------------------
 
 // static
 const base::char16 AutocompleteMatch::kInvalidChars[] = {
   '\n', '\r', '\t',
   0x2028,  // Line separator
   0x2029,  // Paragraph separator
   0
@@ skipping 324 matching lines @@
     return NULL;
   TemplateURL* template_url = keyword.empty() ?
       NULL : template_url_service->GetTemplateURLForKeyword(keyword);
   return (template_url || host.empty()) ?
       template_url : template_url_service->GetTemplateURLForHost(host);
 }
 
 // static
 GURL AutocompleteMatch::GURLToStrippedGURL(
     const GURL& url,
+    const std::vector<base::string16>& input_words,
     TemplateURLService* template_url_service,
     const base::string16& keyword) {
   if (!url.is_valid())
     return url;
 
   GURL stripped_destination_url = url;
 
   // If the destination URL looks like it was generated from a TemplateURL,
   // remove all substitutions other than the search terms.  This allows us
   // to eliminate cases like past search URLs from history that differ only
@@ skipping 25 matching lines @@
 
   // Remove the www. prefix from the host.
   static const char prefix[] = "www.";
   static const size_t prefix_len = arraysize(prefix) - 1;
   std::string host = stripped_destination_url.host();
   if (host.compare(0, prefix_len, prefix) == 0) {
     replacements.SetHostStr(base::StringPiece(host).substr(prefix_len));
     needs_replacement = true;
   }
 
-  // Replace https protocol with http protocol.
-  if (stripped_destination_url.SchemeIs(url::kHttpsScheme)) {
+  // Possibly replace https protocol with http protocol.
+  if (!InputIncludesSchemePlusPartOfHost(input_words, url) &&
+      stripped_destination_url.SchemeIs(url::kHttpsScheme)) {
     replacements.SetScheme(url::kHttpScheme,
                            url::Component(0, strlen(url::kHttpScheme)));
     needs_replacement = true;
   }
 
   if (needs_replacement)
     stripped_destination_url = stripped_destination_url.ReplaceComponents(
         replacements);
   return stripped_destination_url;
 }
 
 void AutocompleteMatch::ComputeStrippedDestinationURL(
+    const std::vector<base::string16>& input_words,
     TemplateURLService* template_url_service) {
-  stripped_destination_url =
-      GURLToStrippedGURL(destination_url, template_url_service, keyword);
+  stripped_destination_url = GURLToStrippedGURL(
+      destination_url, input_words, template_url_service, keyword);
 }
 
 void AutocompleteMatch::EnsureUWYTIsAllowedToBeDefault(
     const GURL& canonical_input_url,
+    const std::vector<base::string16>& input_words,
     TemplateURLService* template_url_service) {
   if (!allowed_to_be_default_match) {
     const GURL& stripped_canonical_input_url =
         AutocompleteMatch::GURLToStrippedGURL(
-            canonical_input_url, template_url_service, base::string16());
-    ComputeStrippedDestinationURL(template_url_service);
+            canonical_input_url, input_words,
+            template_url_service, base::string16());
+    ComputeStrippedDestinationURL(input_words, template_url_service);
     allowed_to_be_default_match =
         stripped_canonical_input_url == stripped_destination_url;
   }
 }
 
 void AutocompleteMatch::GetKeywordUIState(
     TemplateURLService* template_url_service,
     base::string16* keyword,
     bool* is_keyword_hint) const {
   *is_keyword_hint = associated_keyword.get() != NULL;
@@ skipping 102 matching lines @@
         << " is unsorted in relation to last offset of " << last_offset
         << ". Provider: " << provider_name << ".";
     DCHECK_LT(i->offset, text.length())
         << " Classification of [" << i->offset << "," << text.length()
         << "] is out of bounds for \"" << text << "\". Provider: "
         << provider_name << ".";
     last_offset = i->offset;
   }
 }
 #endif