Remove ScoreHistoryMatch::Builder

chrome/browser/autocomplete/scored_history_match.h

Index: chrome/browser/autocomplete/scored_history_match.h
diff --git a/chrome/browser/autocomplete/scored_history_match.h b/chrome/browser/autocomplete/scored_history_match.h
index a73b67d9eadde72412eac3d96c1f02b232a6dc16..dfcaae1a99425431fea2d4903fd64b84fb4b7f0f 100644
--- a/chrome/browser/autocomplete/scored_history_match.h
+++ b/chrome/browser/autocomplete/scored_history_match.h
@@ -13,62 +13,46 @@
 #include "chrome/browser/autocomplete/in_memory_url_index_types.h"
 #include "components/history/core/browser/history_match.h"
 #include "components/history/core/browser/history_types.h"
+#include "testing/gtest/include/gtest/gtest_prod.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 {
-  // The Builder inner class allows the embedder to control how matches are
-  // scored (we cannot use a base::Callback<> as base::Bind() is limited to 6
-  // parameters).
-  // TODO(sdefresne): remove this since ScoredHistoryMatch can now depends on
-  // chrome/browser/autocomplete and components/bookmarks
-  // http://crbug.com/462645
-  class Builder {
-   public:
-    Builder() {}
-    virtual ~Builder() {}
-
-    // Creates a new match with a raw score calculated for the history item
-    // given in |row| with recent visits as indicated in |visits|.  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|.  |history_client| is used to determine
-    // if 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.  |languages| is used
-    // to help parse/format the URL before looking for the terms.
-    virtual ScoredHistoryMatch Build(
-        const history::URLRow& row,
-        const VisitInfoVector& visits,
-        const std::string& languages,
-        const base::string16& lower_string,
-        const String16Vector& terms_vector,
-        const WordStarts& terms_to_word_starts_offsets,
-        const RowWordStarts& word_starts,
-        const base::Time now) const = 0;
-  };
+  // 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 HQP relevance buckets.
+  // Please see GetFinalRelevancyScore() for details.
+  typedef std::pair<double, int> ScoreMaxRelevance;
 
   // Required for STL, we don't use this directly.
   ScoredHistoryMatch();
 
-  // Initialize the ScoredHistoryMatch, passing |url_info|, |input_location|,
-  // |match_in_scheme| and |innermost_match| to HistoryMatch constructor, and
-  // using |raw_score|, |url_matches|, |title_matches| and |can_inline| to
-  // initialize the corresponding properties of this class.
-  ScoredHistoryMatch(const history::URLRow& url_info,
-                     size_t input_location,
-                     bool match_in_scheme,
-                     bool innermost_match,
-                     int raw_score,
-                     const TermMatches& url_matches,
-                     const TermMatches& title_matches,
-                     bool can_inline);
+  // Initializes the ScoredHistoryMatch with a raw score calculated for the
+  // 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.  |languages| is used to help
+  // parse/format the URL before looking for the terms.
+  ScoredHistoryMatch(const history::URLRow& row,
+                     const VisitInfoVector& visits,
+                     const std::string& languages,
+                     const base::string16& lower_string,
+                     const String16Vector& terms_vector,
+                     const WordStarts& terms_to_word_starts_offsets,
+                     const RowWordStarts& word_starts,
+                     bool is_url_bookmarked,
+                     base::Time now);
 
   ~ScoredHistoryMatch();
 
@@ -78,6 +62,18 @@ struct ScoredHistoryMatch : public history::HistoryMatch {
   static bool MatchScoreGreater(const ScoredHistoryMatch& m1,
                                 const ScoredHistoryMatch& m2);
 
+  // Returns |term_matches| after removing all matches that are not at a
+  // word break that are in the range [|start_pos|, |end_pos|).
+  // start_pos == string::npos is treated as start_pos = length of string.
+  // (In other words, no matches will be filtered.)
+  // end_pos == string::npos is treated as end_pos = length of string.
+  static TermMatches FilterTermMatchesByWordStarts(
+      const TermMatches& term_matches,
+      const WordStarts& terms_to_word_starts_offsets,
+      const WordStarts& word_starts,
+      size_t start_pos,
+      size_t end_pos);
+
   // The maximum number of recent visits to examine in GetFrequency().
   // Public so url_index_private_data.cc knows how many visits it is
   // expected to deliver (at minimum) to this class.
@@ -101,6 +97,88 @@ struct ScoredHistoryMatch : public history::HistoryMatch {
 
   // True if this is a candidate for in-line autocompletion.
   bool can_inline;
+
+ private:
+  friend class ScoredHistoryMatchTest;
+  FRIEND_TEST_ALL_PREFIXES(ScoredHistoryMatchTest, GetFinalRelevancyScore);
+  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();
+
+  // Return a topicality score based on how many matches appear in the url and
+  // the page's title and where they are (e.g., at word boundaries).  Revises
+  // url_matches and title_matches of |scored_history_match| in the process so

[Mark P, 2015/03/12 21:31:37]

update this comment.  This variable no longer exists.

[sdefresne, 2015/03/12 21:36:21]

Done.

+  // they only reflect matches used for scoring.  (For instance, some mid-word
+  // matches are not given credit in scoring.)
+  float GetTopicalityScore(const int num_terms,
+                           const base::string16& cleaned_up_url,
+                           const WordStarts& terms_to_word_starts_offsets,
+                           const RowWordStarts& word_starts);
+
+  // Returns a recency score based on |last_visit_days_ago|, which is
+  // how many days ago the page was last visited.
+  static float GetRecencyScore(int last_visit_days_ago);
+
+  // Examines the first kMaxVisitsToScore and return 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.
+  static float GetFrequency(const base::Time& now,
+                            const bool bookmarked,
+                            const VisitInfoVector& visits);
+
+  // Combines the two component scores into a final score that's
+  // an appropriate value to use as a relevancy score. Scoring buckets are
+  // specified through |hqp_relevance_buckets|. Please see the function
+  // implementation for more details.
+  static float GetFinalRelevancyScore(
+      float topicality_score,
+      float frequency_score,
+      const std::vector<ScoreMaxRelevance>& hqp_relevance_buckets);
+
+  // Initializes the HQP experimental params: |hqp_relevance_buckets_|
+  // to default buckets. If hqp experimental scoring is enabled, it
+  // fetches the |hqp_experimental_scoring_enabled_|, |topicality_threshold_|
+  // and |hqp_relevance_buckets_| from omnibox field trials.
+  static void InitHQPExperimentalParams();
+
+  // Helper function to parse the string containing the scoring buckets.
+  // For example,
+  // String: "0.0:400,1.5:600,12.0:1300,20.0:1399"
+  // Buckets: vector[(0.0, 400),(1.5,600),(12.0,1300),(20.0,1399)]
+  // Returns false, in case if it fail to parse the string.
+  static bool GetHQPBucketsFromString(
+      const std::string& buckets_str,
+      std::vector<ScoreMaxRelevance>* hqp_buckets);
+
+  // Untyped visits to bookmarked pages score this, compared to 1 for
+  // untyped visits to non-bookmarked pages and 20 for typed visits.
+  static int bookmark_value_;
+
+  // If true, we allow input terms to match in the TLD (e.g., ".com").
+  static bool allow_tld_matches_;
+
+  // If true, we allow input terms to match in the scheme (e.g., "http://").
+  static bool allow_scheme_matches_;
+
+  // True, if hqp experimental scoring is enabled.
+  static bool hqp_experimental_scoring_enabled_;
+
+  // |topicality_threshold_| is used to control the topicality scoring.
+  // If |topicality_threshold_| > 0, then URLs with topicality-score < threshold
+  // are given topicality score of 0. By default it is initalized to -1.
+  static float topicality_threshold_;
+
+  // |hqp_relevance_buckets_| gives mapping from (topicality*frequency)
+  // to the final relevance scoring. Please see GetFinalRelevancyScore()
+  // for more details and scoring method.
+  static std::vector<ScoreMaxRelevance>* hqp_relevance_buckets_;
 };
 typedef std::vector<ScoredHistoryMatch> ScoredHistoryMatches;