components/journey/proto/batch_get_switcher_journey_from_pageload_request.proto

// Copyright 2018 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.

// Protocol buffer definition for a delta file.

syntax = "proto2";

option optimize_for = LITE_RUNTIME;

package journey;

message BatchGetSwitcherJourneyFromPageloadRequest {
  // Next ID to use: 5

  // The timestamps of the pageloads to request journeys from. This will be
  // ignored if task_id is present.
  // TODO(ghyde): Deprecate this once client moves over.
  repeated int64 page_timestamp_usec = 1;

  // Override journey creation parameters.
  optional JourneyCreationOverrides journey_overrides = 2;

  // The maximum number of pageloads allowed per autotabs.
  optional int64 max_pageloads = 3 [default = 50];

  // The task ids frokm the client to request journeys from.
  repeated int64 task_id = 4;
}

message JourneyCreationOverrides {
  optional JourneyAlgorithmParameters journey_algorithm_parameters = 1;
}

message JourneyAlgorithmParameters {
  // Next ID to use: 11

  // Similarity threshold in [0,1]. Clusters with similarity greater
  // then this threshold and which were done in short timespans will be
  // merged. If set to 1, non temporal merging is performed.
  optional float temporal_merge_threshold = 1 [default = 1];

  // Similarity threshold in [0,1]. Threshold above which journeys are
  // considered to be related to each other.
  optional float semantically_related_threshold = 2 [default = 0.1];

  // Similarity threshold in [0, 1]. Threshold above which journeys appear in
  // searches for a given query.
  optional float search_threshold = 3 [default = 0.1];

  // If true, dedupe pageloads in journeys by URL. remove_duplicate_titles
  // and remove_duplicates_between_tasks will only be used if this value is
  // true.
  optional bool remove_duplicate_urls = 6 [default = true];

  // If true, remove URLs as duplicates if they are from the same domain and
  // have the same title. Otherwise, only remove duplicate URLs that have
  // identical URLs.
  // This value is only used if remove_duplicate_urls is also true.
  optional bool remove_duplicate_titles = 4 [default = true];

  // If true, remove duplicates across the whole journey. Otherwise,
  // only remove duplicates within each task.
  // Note: This value is only used if remove_duplicate_urls is also true.
  optional bool remove_duplicates_between_tasks = 7 [default = false];

  // Type of labels to use for subtitles.
  enum SubtitleTermsType {
    TYPE_UNKNOWN = 0;

    // Use knowledge entities as subtitle terms.
    TYPE_KE = 1;

    // Use petacat as subtitle terms.
    TYPE_PETACAT = 2;
  }
  optional SubtitleTermsType subtitle_type = 5 [default = TYPE_KE];

  // If set to true, bookmarks will be fetched and pageloads will be annotated
  // with them.
  optional bool get_bookmarks = 8 [default = false];

  // The number of days between tasks in the same cluster required in order
  // to break into a new journey.
  optional int32 journey_break_days = 9 [default = 7];

  // The max number of pageloads to be added to a journey.
  // NOTE: We will actually add tasks as long as we are under this limit, so
  // it is possible that the last task pushes us over.
  optional int32 max_pages_in_journey = 10 [default = 500];
}