Omnibox - Boost Frequency Scores Based on Number of Matching Pages

components/omnibox/browser/scored_history_match.h

 // 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.
 
 #ifndef COMPONENTS_OMNIBOX_BROWSER_SCORED_HISTORY_MATCH_H_
 #define COMPONENTS_OMNIBOX_BROWSER_SCORED_HISTORY_MATCH_H_
 
 #include <stddef.h>
 
 #include <string>
 #include <vector>
 
 #include "base/gtest_prod_util.h"
 #include "base/strings/string16.h"
 #include "base/time/time.h"
 #include "components/history/core/browser/history_match.h"
 #include "components/history/core/browser/history_types.h"
 #include "components/omnibox/browser/in_memory_url_index_types.h"
+#include "components/omnibox/browser/omnibox_field_trial.h"
 
 class ScoredHistoryMatchTest;
 
 // An HistoryMatch that has a score as well as metrics defining where in the
 // history item's URL and/or page title matches have occurred.
 struct ScoredHistoryMatch : public history::HistoryMatch {
   // ScoreMaxRelevance maps from an intermediate-score to the maximum
   // final-relevance score given to a URL for this intermediate score.
   // This is used to store the score ranges of relevance buckets.
   // Please see GetFinalRelevancyScore() for details.
@@ skipping 12 matching lines @@
   // history item given in |row| with recent visits as indicated in |visits|. It
   // first determines if the row qualifies by seeing if all of the terms in
   // |terms_vector| occur in |row|.  If so, calculates a raw score.  This raw
   // score is in part determined by whether the matches occur at word
   // boundaries, the locations of which are stored in |word_starts|.  For some
   // terms, it's appropriate to look for the word boundary within the term. For
   // instance, the term ".net" should look for a word boundary at the "n".
   // These offsets (".net" should have an offset of 1) come from
   // |terms_to_word_starts_offsets|. |is_url_bookmarked| indicates whether the
   // match's URL is referenced by any bookmarks, which can also affect the raw
-  // score.  The raw score allows the matches to be ordered and can be used to
-  // influence the final score calculated by the client of this index.  If the
-  // row does not qualify the raw score will be 0.
+  // score.  |num_matching_pages| indicates how many URLs in the eligible URL
+  // database match the user's input; it can also affect the raw score.  The raw
+  // score allows the matches to be ordered and can be used to influence the
+  // final score calculated by the client of this index.  If the row does not
+  // qualify the raw score will be 0.
   ScoredHistoryMatch(const history::URLRow& row,
                      const VisitInfoVector& visits,
                      const base::string16& lower_string,
                      const String16Vector& terms_vector,
                      const WordStarts& terms_to_word_starts_offsets,
                      const RowWordStarts& word_starts,
                      bool is_url_bookmarked,
+                     size_t num_matching_pages,
                      base::Time now);
 
   ~ScoredHistoryMatch();
 
   // Compares two matches by score.  Functor supporting URLIndexPrivateData's
   // HistoryItemsForTerms function.  Looks at particular fields within
   // with url_info to make tie-breaking a bit smarter.
   static bool MatchScoreGreater(const ScoredHistoryMatch& m1,
                                 const ScoredHistoryMatch& m2);
 
@@ skipping 20 matching lines @@
   // unimportant matches are eliminated by GetTopicalityScore(), called
   // during construction.)
 
   // Term matches within the URL.
   TermMatches url_matches;
   // Term matches within the page title.
   TermMatches title_matches;
 
  private:
   friend class ScoredHistoryMatchTest;
+  FRIEND_TEST_ALL_PREFIXES(ScoredHistoryMatchTest, GetDocumentSpecificityScore);
   FRIEND_TEST_ALL_PREFIXES(ScoredHistoryMatchTest, GetFinalRelevancyScore);
   FRIEND_TEST_ALL_PREFIXES(ScoredHistoryMatchTest, GetFrequency);
   FRIEND_TEST_ALL_PREFIXES(ScoredHistoryMatchTest, GetHQPBucketsFromString);
   FRIEND_TEST_ALL_PREFIXES(ScoredHistoryMatchTest, ScoringBookmarks);
   FRIEND_TEST_ALL_PREFIXES(ScoredHistoryMatchTest, ScoringScheme);
   FRIEND_TEST_ALL_PREFIXES(ScoredHistoryMatchTest, ScoringTLD);
 
   // Initialize ScoredHistoryMatch statics. Must be called before any other
   // method of ScoredHistoryMatch and before creating any instances.
   static void Init();
@@ skipping 15 matching lines @@
 
   // Examines the first |max_visits_to_score_| and returns a score (higher is
   // better) based the rate of visits, whether the page is bookmarked, and
   // how often those visits are typed navigations (i.e., explicitly
   // invoked by the user).  |now| is passed in to avoid unnecessarily
   // recomputing it frequently.
   float GetFrequency(const base::Time& now,
                      const bool bookmarked,
                      const VisitInfoVector& visits) const;
 
-  // Combines the two component scores into a final score that's an appropriate
-  // value to use as a relevancy score.
+  // Returns a document specificity score based on how many pages matched the
+  // user's input.
+  float GetDocumentSpecificityScore(size_t num_matching_pages) const;
+
+  // Combines the three component scores into a final score that's
+  // an appropriate value to use as a relevancy score.
   static float GetFinalRelevancyScore(float topicality_score,
-                                      float frequency_score);
+                                      float frequency_score,
+                                      float specificity_score);
 
   // Helper function that returns the string containing the scoring buckets
   // (either the default ones or ones specified in an experiment).
   static ScoreMaxRelevances GetHQPBuckets();
 
   // Helper function to parse the string containing the scoring buckets and
   // return the results.  For example, with |buckets_str| as
   // "0.0:400,1.5:600,12.0:1300,20.0:1399", it returns [(0.0, 400), (1.5, 600),
   // (12.0, 1300), (20.0, 1399)]. It returns an empty vector in the case of a
   // malformed |buckets_str|.
@@ skipping 34 matching lines @@
 
   // |topicality_threshold_| is used to control the topicality scoring.
   // If |topicality_threshold_| > 0, then URLs with topicality-score less than
   // the threshold are given topicality score of 0.
   static float topicality_threshold_;
 
   // Used for testing.  A possibly null pointer to a vector.  If set,
   // overrides the static local variable |relevance_buckets| declared in
   // GetFinalRelevancyScore().
   static ScoreMaxRelevances* relevance_buckets_override_;
+
+  // Used for testing.  If this pointer is not null, it overrides the static
+  // local variable |default_matches_to_specificity| declared in
+  // GetDocumentSpecificityScore().
+  static OmniboxFieldTrial::NumMatchesScores* matches_to_specificity_override_;
 };
 typedef std::vector<ScoredHistoryMatch> ScoredHistoryMatches;
 
 #endif  // COMPONENTS_OMNIBOX_BROWSER_SCORED_HISTORY_MATCH_H_