Unpunycode search keywords and short names.

components/search_engines/template_url.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.h"
 
 #include <string>
 #include <vector>
 
 #include "base/basictypes.h"
@@ skipping 1192 matching lines @@
   if (data_.search_terms_replacement_key ==
       "{google:instantExtendedEnabledKey}") {
     data_.search_terms_replacement_key = google_util::kInstantExtendedAPIParam;
   }
 }
 
 TemplateURL::~TemplateURL() {
 }
 
 // static
-base::string16 TemplateURL::GenerateKeyword(const GURL& url) {
+base::string16 TemplateURL::GenerateKeyword(
+    const GURL& url,
+    const std::string& accept_languages) {
   DCHECK(url.is_valid());
   // Strip "www." off the front of the keyword; otherwise the keyword won't work
   // properly.  See http://code.google.com/p/chromium/issues/detail?id=6984 .
+  // Since keyword is generated from hostname, it might be IDN-encoded.
+  // If so, decode it and convert to Unicode using user's accepted languages,
+  // making it look like Unicode hostname the user is used to seeing.

[Peter Kasting, 2015/07/21 17:34:09]

Grammar issues.  Try this:

|url|'s hostname may be IDN-encoded.  Before generating |keyword| from it,
convert to Unicode using the user's accept-languages, so it won't look like a
confusing punycode string.

[alshabalin, 2015/07/22 14:31:17]

Done.

+  base::string16 keyword =
+      net::StripWWW(net::IDNToUnicode(url.host(), accept_languages));
   // Special case: if the host was exactly "www." (not sure this can happen but
   // perhaps with some weird intranet and custom DNS server?), ensure we at
   // least don't return the empty string.
-  base::string16 keyword(net::StripWWWFromHost(url));
   return keyword.empty() ? base::ASCIIToUTF16("www") : keyword;
 }
 
 // static
 GURL TemplateURL::GenerateFaviconURL(const GURL& url) {
   DCHECK(url.is_valid());
   GURL::Replacements rep;
 
   const char favicon_path[] = "/favicon.ico";
   int favicon_path_len = arraysize(favicon_path) - 1;
@@ skipping 247 matching lines @@
   instant_url_ref_.prepopulated_ = prepopulated;
 }
 
 void TemplateURL::ResetKeywordIfNecessary(
     const SearchTermsData& search_terms_data,
     bool force) {
   if (IsGoogleSearchURLWithReplaceableKeyword(search_terms_data) || force) {
     DCHECK(GetType() != OMNIBOX_API_EXTENSION);
     GURL url(GenerateSearchURL(search_terms_data));
     if (url.is_valid())
-      data_.SetKeyword(GenerateKeyword(url));
+      data_.SetKeyword(
+          GenerateKeyword(url, search_terms_data.GetAcceptLanguages()));
   }
 }
 
 bool TemplateURL::FindSearchTermsInURL(
     const GURL& url,
     const SearchTermsData& search_terms_data,
     base::string16* search_terms,
     url::Parsed::ComponentType* search_term_component,
     url::Component* search_terms_position) const {
   DCHECK(search_terms);
@@ skipping 10 matching lines @@
       // patterns. This means that given patterns
       //    [ "http://foo/#q={searchTerms}", "http://foo/?q={searchTerms}" ],
       // calling ExtractSearchTermsFromURL() on "http://foo/?q=bar#q=' would
       // return false. This is important for at least Google, where such URLs
       // are invalid.
       return !search_terms->empty();
     }
   }
   return false;
 }