title: development/cirrussearch/page_weighted_tags_change
description: >
  Changes (setting and/or clearing) of weighted (scored) tags of a page, see
  https://wikitech.wikimedia.org/wiki/Search/WeightedTags
$id: /development/cirrussearch/page_weighted_tags_change/1.0.0
$schema: 'https://json-schema.org/draft-07/schema#'
type: object
additionalProperties: false
required:
  - $schema
  - dt
  - meta
  - page
  - weighted_tags
  - wiki_id
properties:
  $schema:
    description: >
      A URI identifying the JSONSchema for this event. This should match an
      schema's $id in a schema repository. E.g. /schema/title/1.0.0
    type: string
  dt:
    description: >
      ISO-8601 formatted timestamp of when the event occurred/was generated in
      UTC), AKA 'event time'. This is different than meta.dt, which is used as
      the time the system received this event.
    type: string
    format: date-time
    maxLength: 128
  meta:
    type: object
    required:
      - stream
    properties:
      domain:
        description: Domain the event or entity pertains to
        type: string
        minLength: 1
      dt:
        description: 'Time the event was received by the system, in UTC ISO-8601 format'
        type: string
        format: date-time
        maxLength: 128
      id:
        description: Unique ID of this event
        type: string
      request_id:
        description: Unique ID of the request that caused the event
        type: string
      stream:
        description: Name of the stream (dataset) that this event belongs in
        type: string
        minLength: 1
      uri:
        description: Unique URI identifying the event or entity
        type: string
        format: uri-reference
        maxLength: 8192
  page:
    title: fragment/mediawiki/state/entity/page
    description: Fields for MediaWiki page entity.
    $id: /fragment/mediawiki/state/entity/page/2.0.0
    $schema: 'https://json-schema.org/draft-07/schema#'
    type: object
    additionalProperties: false
    required:
      - page_id
      - page_title
      - namespace_id
    properties:
      is_redirect:
        description: True if the page is a redirect page at the time of this event.
        type: boolean
      namespace_id:
        description: The id of the namespace this page belongs to.
        type: integer
        maximum: 9007199254740991
        minimum: 0
      page_id:
        description: The (database) page ID of the page.
        type: integer
        maximum: 9007199254740991
        minimum: 0
      page_title:
        description: The normalized title of the page.
        type: string
        minLength: 1
    examples:
      - is_redirect: false
        namespace_id: 1351079888211148
        page_id: 1351079888211148
        page_title: dolor
  rev_based:
    description: >
      A hint for an event processor that this event has been triggered by new a
      revision. Only if set to false, the processor may skip merging it with the
      original page change (and other related events).
    type: boolean
  weighted_tags:
    description: Tags to be set for and/or cleared from the specified page
    type: object
    additionalProperties: false
    properties:
      clear:
        description: >
          A list of tag prefixes (without slash(es)) that will be cleared, see
          https://wikitech.wikimedia.org/wiki/Search/WeightedTags#Shape_of_the_data_in_elasticsearch
        type: array
        items:
          type: string
          maxLength: 100
          minLength: 1
          pattern: '^[^/]+$'
        minLength: 1
      set:
        description: >
          A multimap of prefix (without slash(es)) to list of optionally
          weighted (scored) tags, see
          https://wikitech.wikimedia.org/wiki/Search/WeightedTags#Shape_of_the_data_in_elasticsearch
        type: object
        additionalProperties:
          type: array
          items:
            type: object
            additionalProperties: false
            required:
              - tag
            properties:
              score:
                type: number
                maximum: 1
                minimum: 0
              tag:
                type: string
                minLength: 1
          minLength: 1
        minProperties: 1
    minProperties: 1
  wiki_id:
    description: >
      The wiki ID, which is usually the same as the MediaWiki database name.
      E.g. enwiki, metawiki, etc.
    type: string
    minLength: 1
examples:
  - $schema: /development/cirrussearch/page_weighted_tags_change/1.0.0
    dt: '2024-07-22T00:00:00.0Z'
    meta:
      domain: examplewiki
      dt: '2024-07-22T00:00:00.0Z'
      stream: cirrussearch.page_weighted_tags_change
    page:
      namespace_id: 0
      page_id: 42
      page_title: Set-only example
    weighted_tags:
      set:
        tag.group.A:
          - score: 0.5
            tag: A.1
          - tag: A.2
        tag.group.B:
          - tag: B.1
    wiki_id: example
  - $schema: /development/cirrussearch/page_weighted_tags_change/1.0.0
    dt: '2024-07-22T00:00:00.0Z'
    meta:
      domain: examplewiki
      dt: '2024-07-22T00:00:00.0Z'
      stream: cirrussearch.page_weighted_tags_change
    page:
      namespace_id: 0
      page_id: 42
      page_title: Clear-only example
    weighted_tags:
      clear:
        - tag.group.B
    wiki_id: example
  - $schema: /development/cirrussearch/page_weighted_tags_change/1.0.0
    dt: '2024-07-22T00:00:00.0Z'
    meta:
      domain: examplewiki
      dt: '2024-07-22T00:00:00.0Z'
      stream: cirrussearch.page_weighted_tags_change
    page:
      namespace_id: 0
      page_id: 42
      page_title: Set and Clear example
    weighted_tags:
      clear:
        - tag.group.C
      set:
        tag.group.A:
          - tag: A.1
    wiki_id: example