Omnibox: Highlight Matches in URLs Properly

chrome/browser/bookmarks/bookmark_index.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 "chrome/browser/bookmarks/bookmark_index.h"
 
 #include <algorithm>
 #include <iterator>
 #include <list>
 
 #include "base/i18n/case_conversion.h"
 #include "base/strings/string16.h"
+#include "base/strings/utf_offset_string_conversions.h"
 #include "chrome/browser/bookmarks/bookmark_model.h"
 #include "chrome/browser/bookmarks/bookmark_utils.h"
 #include "chrome/browser/history/history_service.h"
 #include "chrome/browser/history/history_service_factory.h"
 #include "chrome/browser/history/url_database.h"
 #include "components/bookmarks/core/browser/bookmark_match.h"
 #include "components/query_parser/query_parser.h"
 #include "components/query_parser/snippet.h"
 #include "third_party/icu/source/common/unicode/normalizer2.h"
 
@@ skipping 62 matching lines @@
 }
 
 void BookmarkIndex::Add(const BookmarkNode* node) {
   if (!node->is_url())
     return;
   std::vector<base::string16> terms =
       ExtractQueryWords(Normalize(node->GetTitle()));
   for (size_t i = 0; i < terms.size(); ++i)
     RegisterNode(terms[i], node);
   if (index_urls_) {
-    terms = ExtractQueryWords(
-        bookmark_utils::CleanUpUrlForMatching(node->url(), languages_));
+    base::OffsetAdjuster::Adjustments adjustments;
+    terms = ExtractQueryWords(bookmark_utils::CleanUpUrlForMatching(
+        node->url(), languages_, &adjustments));

[Peter Kasting, 2014/04/23 23:18:01]

Maybe we should be able to pass NULL for the last arg here.  That would clean up
two places in this file.

[Mark P, 2014/04/24 14:05:02]

Done.

     for (size_t i = 0; i < terms.size(); ++i)
       RegisterNode(terms[i], node);
   }
 }
 
 void BookmarkIndex::Remove(const BookmarkNode* node) {
   if (!node->is_url())
     return;
 
   std::vector<base::string16> terms =
       ExtractQueryWords(Normalize(node->GetTitle()));
   for (size_t i = 0; i < terms.size(); ++i)
     UnregisterNode(terms[i], node);
   if (index_urls_) {
-    terms = ExtractQueryWords(
-        bookmark_utils::CleanUpUrlForMatching(node->url(), languages_));
+    base::OffsetAdjuster::Adjustments adjustments;
+    terms = ExtractQueryWords(bookmark_utils::CleanUpUrlForMatching(
+        node->url(), languages_, &adjustments));
     for (size_t i = 0; i < terms.size(); ++i)
       UnregisterNode(terms[i], node);
   }
 }
 
 void BookmarkIndex::GetBookmarksMatching(const base::string16& input_query,
                                          size_t max_count,
                                          std::vector<BookmarkMatch>* results) {
   const base::string16 query = Normalize(input_query);
   std::vector<base::string16> terms = ExtractQueryWords(query);
@@ skipping 75 matching lines @@
     std::vector<BookmarkMatch>* results) {
   // Check that the result matches the query.  The previous search
   // was a simple per-word search, while the more complex matching
   // of QueryParser may filter it out.  For example, the query
   // ["thi"] will match the bookmark titled [Thinking], but since
   // ["thi"] is quoted we don't want to do a prefix match.
   query_parser::QueryWordVector title_words, url_words;
   const base::string16 lower_title =
       base::i18n::ToLower(Normalize(node->GetTitle()));
   parser->ExtractQueryWords(lower_title, &title_words);
+  base::OffsetAdjuster::Adjustments adjustments;
   if (index_urls_) {
-    parser->ExtractQueryWords(
-        bookmark_utils::CleanUpUrlForMatching(node->url(), languages_),
-        &url_words);
+    parser->ExtractQueryWords(bookmark_utils::CleanUpUrlForMatching(
+        node->url(), languages_, &adjustments), &url_words);
   }
   query_parser::Snippet::MatchPositions title_matches, url_matches;
   for (size_t i = 0; i < query_nodes.size(); ++i) {
     const bool has_title_matches =
         query_nodes[i]->HasMatchIn(title_words, &title_matches);
     const bool has_url_matches = index_urls_ &&
         query_nodes[i]->HasMatchIn(url_words, &url_matches);
     if (!has_title_matches && !has_url_matches)
       return;
     query_parser::QueryParser::SortAndCoalesceMatchPositions(&title_matches);
     if (index_urls_)
       query_parser::QueryParser::SortAndCoalesceMatchPositions(&url_matches);
   }
   BookmarkMatch match;
   if (lower_title.length() == node->GetTitle().length()) {
     // Only use title matches if the lowercase string is the same length
     // as the original string, otherwise the matches are meaningless.
     // TODO(mpearson): revise match positions appropriately.
     match.title_match_positions.swap(title_matches);
   }
-  if (index_urls_)
+  if (index_urls_) {
+    // Now that we're done processing this entry, correct the offsets of the
+    // matches in |url_matches| so they point to offsets in the original URL
+    // spec, not the cleaned-up URL string that we used for matching.
+    std::vector<size_t> offsets =
+        BookmarkMatch::OffsetsFromMatchPositions(url_matches);
+    base::OffsetAdjuster::UnadjustOffsets(adjustments, &offsets);
+    url_matches =
+        BookmarkMatch::ReplaceOffsetsInMatchPositions(url_matches, offsets);
     match.url_match_positions.swap(url_matches);
+  }
   match.node = node;
   results->push_back(match);
 }
 
 bool BookmarkIndex::GetBookmarksMatchingTerm(const base::string16& term,
                                                       bool first_term,
                                                       Matches* matches) {
   Index::const_iterator i = index_.lower_bound(term);
   if (i == index_.end())
     return false;
@@ skipping 93 matching lines @@
   Index::iterator i = index_.find(term);
   if (i == index_.end()) {
     // We can get here if the node has the same term more than once. For
     // example, a bookmark with the title 'foo foo' would end up here.
     return;
   }
   i->second.erase(node);
   if (i->second.empty())
     index_.erase(i);
 }