tags: track tag histories.

Track the history of the tag `category` and `is_deprecated` fields in
the `tag_versions` table.

Adds generic Versionable and VersionFor concerns that encapsulate most
of the history tracking logic. These concerns are designed to make it
easy to add history to any model.

There are a couple notable differences between tag versions and other versions:

* There is no 1 hour edit merge window. All changes to the `category`
  and `is_deprecated` fields produce a new version in the tag history.

* New versions aren't created when a tag is created. Versions are only
  created when a tag is edited for the first time. The tag's initial
  version isn't created until *after* the tag is edited for the first time.

For example, if you change the category of a tag that was last updated
10 years ago, that will create an initial version of the tag backdated
to 10 years ago, plus a new version for your edit.

This is for a few reasons:

* So that we don't have to create new tag versions every time a new tag
  is created. This would be wasteful because most tags never have their
  category or deprecation status change.
* So that if you make a typo tag, your name isn't recorded in the tag's
  history forever.
* So that we can create new tags in various places without having to know
  who created the tag (which may be unknown if the current user isn't set).
* Because we don't know the full history of most tags, so we have to
  deal with incomplete histories anyway.

This has a few important consequences:

* Most tags won't have any tag versions. They only gain tag versions if
  they're edited.
* You can't track /tag_versions to see newly created tags. It only
  shows changes to already existing tags.
* Tag version IDs won't be in strict chronological order. Higher IDs may
  have created_at timestamps before lower IDs. For example, if you
  change the category of a tag that is 10 years old, that will create an
  initial version with a high ID, but with a created_at timestamp dated
  to 10 years ago.

Fixes #4402: Track tag category changes
This commit is contained in:
evazion
2022-09-09 22:16:59 -05:00
parent 0c327a2228
commit 54a45a3021
12 changed files with 388 additions and 24 deletions

View File

@@ -26,7 +26,7 @@ class TagsController < ApplicationController
def update
@tag = authorize Tag.find(params[:id])
@tag.update(permitted_attributes(@tag))
@tag.update(updater: CurrentUser.user, **permitted_attributes(@tag))
respond_with(@tag)
end
end

View File

@@ -212,17 +212,17 @@ class BulkUpdateRequestProcessor
when :change_category
tag = Tag.find_or_create_by_name(args[0])
tag.update!(category: Tag.categories.value_for(args[1]))
tag.update!(category: Tag.categories.value_for(args[1]), updater: User.system)
when :deprecate
tag = Tag.find_or_create_by_name(args[0])
tag.update!(is_deprecated: true)
tag.update!(is_deprecated: true, updater: User.system)
TagImplication.active.where(consequent_name: tag.name).each { |ti| ti.reject!(User.system) }
TagImplication.active.where(antecedent_name: tag.name).each { |ti| ti.reject!(User.system) }
when :undeprecate
tag = Tag.find_or_create_by_name(args[0])
tag.update!(is_deprecated: false)
tag.update!(is_deprecated: false, updater: User.system)
else
# should never happen

View File

@@ -0,0 +1,103 @@
# frozen_string_literal: true
# A concern that adds a `version_for` macro for declaring that a model is the
# version model (TagVersion, PostVersion, etc) belonging to a versionable model
# (Tag, Post, etc). The counterpart to Versionable.
#
# Defines helper methods like `undo!`, `revert_to!`, `diff`, etc.
#
# Assumes the class has `previous_version_id` and `version` columns.
#
# @example
# class TagVersion
# include VersionFor
# version_for :tag
# end
#
module VersionFor
extend ActiveSupport::Concern
class_methods do
# Declare a class as the version model belonging to a `versionable` model.
def version_for(versioned_model_name)
raise "#{name} must have a `previous_version_id` attribute" if !has_attribute?(:previous_version_id)
raise "#{name} must have a `version` attribute" if !has_attribute?(:version)
@versioned_model_name = versioned_model_name # "tag"
@versioned_model_id_column = "#{versioned_model_name}_id" # "tag_id"
@versioned_class = versioned_model_name.to_s.camelize.constantize # Tag
self.class.attr_reader :versioned_model_name, :versioned_model_id_column, :versioned_class
delegate :versioned_model_name, :versioned_model_id_column, :versioned_class, to: :class
delegate :versioned_columns, to: :versioned_class
belongs_to versioned_model_name
belongs_to :updater, class_name: "User", optional: true
belongs_to :previous_version, class_name: name, optional: true
validates :previous_version_id, uniqueness: { scope: versioned_model_id_column } # scope: :tag_id
before_save :increment_version
after_save :validate_previous_version
scope :first_version, -> { where(previous_version: nil) }
scope :last_version, -> { where.not(id: where.not(previous_version: nil).select(:previous_version_id)) }
alias_method :versioned_model, versioned_model_name
end
end
# XXX This is an after_save callback instead of a normal validation so we can refer to the `id`,
# `created_at`, and `updated_at` columns (which aren't available until after saving the row).
def validate_previous_version
if previous_version.present? && previous_version_id >= id
raise "The previous version must be before the current version (id=#{id}, previous_version.id=#{previous_version.id})"
elsif previous_version.present? && previous_version.version >= version
raise "The previous version must be before the current version (version=#{version}, previous_version.version=#{previous_version.version})"
elsif previous_version.present? && previous_version.created_at >= updated_at
raise "The previous version must be before the current version (updated_at=#{updated_at}, previous_version.created_at=#{previous_version.created_at})"
elsif previous_version.present? && previous_version.updated_at >= updated_at
raise "The previous version must be before the current version (updated_at=#{updated_at}, previous_version.updated_at=#{previous_version.updated_at})"
elsif previous_version.present? && previous_version.versioned_model != versioned_model
raise "The previous version must belong to the same #{versioned_model_name} (#{versioned_model_id_column}=#{versioned_model.id}, previous_version.#{versioned_model_id_column}=#{previous_version.versioned_model.id})"
end
end
def increment_version
# XXX We assume the versioned model is locked so that this is an atomic increment and not subject to a race condition.
self.version = previous_version&.version.to_i + 1
end
# Return a hash of the versioned columns with their values.
def versioned_attributes
attributes.with_indifferent_access.slice(*versioned_columns)
end
# True if this is the first version in the versioned item's edit history.
def first_version?
previous_version.nil?
end
# Return a hash of changes made by this edit (compared to the previous version, or to another version).
#
# The hash looks like `{ attr => [old_value, new_value] }`.
def diff(version = previous_version)
versioned_columns.map { |attr| [attr, [version&.send(attr), send(attr)]] }.to_h
end
# Revert the model back to this version.
def revert_to!(updater)
versioned_model.update!(updater: updater, **versioned_attributes)
end
# Undo the changes made by this edit (compared to the previous version, or to another version).
def undo!(updater, version: previous_version)
return if version.nil?
diff(version).each do |attr, old_value, new_value|
versioned_model[attr] = old_value if old_value != new_value
end
versioned_model.update!(updater: updater)
end
end

View File

@@ -0,0 +1,105 @@
# frozen_string_literal: true
# A concern used by versioned models (Tag, Post, etc). Adds a `versionable`
# macro for declaring that a model is versioned.
#
# Assumes the class has an `updater` attribute that contains the user who
# updated the model when the model is saved.
#
# @example
# class Tag
# include Versionable
# versionable :name, :category, :is_deprecated
# end
#
module Versionable
extend ActiveSupport::Concern
class_methods do
# Declare a model is versioned. Changes to the given `columns` will be saved in a versions table.
#
# @param columns [Array<Symbol>] The columns to track as versioned. Changes to these columns will be saved to
# the versions table; changes to other columns will be ignored.
# @param merge_window [Duration] Merge multiple edits made by the same user within this time frame into one version.
# @param delay_first_version [Boolean] If true, don't create the first version until after the object is edited
# for the first time. If false, create the first version immediately when the object is first created.
def versionable(*columns, merge_window: 1.hour, delay_first_version: false)
raise "#{name} must have `updater` attribute" if !method_defined?(:updater)
@versioned_columns = columns
@version_merge_window = merge_window
@delay_first_version = delay_first_version
self.class.attr_reader :versioned_columns, :version_merge_window, :delay_first_version
delegate :versioned_columns, :version_merge_window, :delay_first_version, to: :class
has_many :versions, -> { order(id: :asc) }, class_name: "#{name}Version", dependent: :destroy, inverse_of: model_name.singular, after_add: :reset_version_association_cache
has_one :first_version, -> { first_version }, class_name: "#{name}Version"
has_one :last_version, -> { last_version }, class_name: "#{name}Version"
after_save :save_version
end
end
# Return a hash of the versioned columns with their current values.
def versioned_attributes
versioned_columns.map { |attr| [attr, send(attr)] }.to_h.with_indifferent_access
end
# Return a hash of the versioned columns with their values before the last save.
def versioned_attributes_before_last_save
versioned_columns.map { |attr| [attr, attribute_before_last_save(attr)] }.to_h.with_indifferent_access
end
def saved_changes_to_versioned_attributes?
saved_changes? && versioned_columns.any? { |attr| saved_change_to_attribute?(attr) }
end
def save_version
return unless saved_changes_to_versioned_attributes?
raise "Can't save version because updater not set" if updater.nil? && (merge_version? || create_new_version?)
if create_first_version?
create_first_version
end
if merge_version?
merge_version
elsif create_new_version?
create_new_version
end
end
# True if this edit should be merged into the previous edit by the same user.
def merge_version?
version_merge_window.present? && last_version.present? && last_version.updater == updater && last_version.created_at > version_merge_window.ago
end
# True if this edit should create a new version. We don't create a new version if this is a new record and creation of the first version is delayed.
def create_new_version?
!previously_new_record? || (previously_new_record? && !delay_first_version)
end
# True if this edit should create the first version if the first version was delayed.
def create_first_version?
delay_first_version && !previously_new_record? && first_version.nil?
end
def merge_version
last_version.update!(updater: updater, **versioned_attributes)
end
def create_new_version
versions.create!(updater: updater, previous_version: last_version, **versioned_attributes)
end
def create_first_version
versions.create!(updater: try(:creator), previous_version: nil, created_at: updated_at_before_last_save, updated_at: updated_at_before_last_save, **versioned_attributes_before_last_save)
end
# After a new version is created, we have to clear the assocation cache manually so it doesn't return stale results.
def reset_version_association_cache(record)
association(:first_version).reset
association(:last_version).reset
end
end

View File

@@ -37,9 +37,9 @@ class TagMover
# Sync the category of both tags, if one is a general tag and the other is non-general.
def move_tag_category!
if old_tag.general? && !new_tag.general?
old_tag.update!(category: new_tag.category)
old_tag.update!(category: new_tag.category, updater: user)
elsif new_tag.general? && !old_tag.general?
new_tag.update!(category: old_tag.category)
new_tag.update!(category: old_tag.category, updater: user)
end
end

View File

@@ -187,7 +187,7 @@ class Artist < ApplicationRecord
return unless !is_deleted? && name_changed? && tag.present?
if tag.category_name != "Artist" && tag.empty?
tag.update!(category: Tag.categories.artist)
tag.update!(category: Tag.categories.artist, updater: CurrentUser.user)
end
end
end

View File

@@ -1,11 +1,15 @@
# frozen_string_literal: true
class Tag < ApplicationRecord
include Versionable
ABBREVIATION_REGEXP = /([a-z0-9])[a-z0-9']*($|[^a-z0-9']+)/
# Tags that are permitted to have unbalanced parentheses, as a special exception to the normal rule that parentheses in tags must balanced.
PERMITTED_UNBALANCED_TAGS = %w[:) :( ;) ;( >:) >:(]
attr_accessor :updater
has_one :wiki_page, :foreign_key => "title", :primary_key => "name"
has_one :artist, :foreign_key => "name", :primary_key => "name"
has_one :antecedent_alias, -> {active}, :class_name => "TagAlias", :foreign_key => "antecedent_name", :primary_key => "name"
@@ -25,6 +29,8 @@ class Tag < ApplicationRecord
after_save :update_category_cache, if: :saved_change_to_category?
after_save :update_category_post_counts, if: :saved_change_to_category?
versionable :name, :category, :is_deprecated, merge_window: nil, delay_first_version: true
scope :empty, -> { where("tags.post_count <= 0") }
scope :nonempty, -> { where("tags.post_count > 0") }
scope :deprecated, -> { where(is_deprecated: true) }
@@ -194,10 +200,11 @@ class Tag < ApplicationRecord
end
def find_or_create_by_name(name, category: nil, current_user: nil)
tag = find_or_create_by(name: normalize_name(name))
cat_id = categories.value_for(category)
tag = create_with(category: cat_id).find_or_create_by(name: normalize_name(name))
if category.present? && current_user.present? && Pundit.policy!(current_user, tag).can_change_category?
tag.update(category: categories.value_for(category))
if category.present? && current_user.present? && cat_id != tag.category && Pundit.policy!(current_user, tag).can_change_category?
tag.update(category: cat_id, updater: current_user)
end
tag

View File

@@ -0,0 +1,7 @@
# frozen_string_literal: true
class TagVersion < ApplicationRecord
include VersionFor
version_for :tag
end

View File

@@ -92,10 +92,24 @@ class TagsControllerTest < ActionDispatch::IntegrationTest
@mod = create(:moderator_user)
end
should "update the tag" do
put_auth tag_path(@tag), @user, params: {:tag => {:category => Tag.categories.general}}
should "update the category for an empty tag" do
@tag = create(:tag, category: Tag.categories.copyright, post_count: 0)
put_auth tag_path(@tag), @user, params: { tag: { category: Tag.categories.general }}
assert_redirected_to tag_path(@tag)
assert_equal(Tag.categories.general, @tag.reload.category)
assert_equal(2, @tag.versions.count)
assert_equal(1, @tag.first_version.version)
assert_equal(@tag.created_at, @tag.first_version.created_at)
assert_equal(@tag.created_at, @tag.first_version.updated_at)
assert_nil(@tag.first_version.updater)
assert_equal(Tag.categories.copyright, @tag.first_version.category)
assert_equal(2, @tag.last_version.version)
assert_equal(@user, @tag.last_version.updater)
assert_equal(Tag.categories.general, @tag.last_version.category)
end
context "for a tag with >50 posts" do
@@ -109,6 +123,7 @@ class TagsControllerTest < ActionDispatch::IntegrationTest
assert_response 403
assert_not_equal(Tag.categories.general, @tag.reload.category)
assert_equal(0, @tag.versions.count)
end
should "update the category for a builder" do
@@ -116,6 +131,12 @@ class TagsControllerTest < ActionDispatch::IntegrationTest
assert_redirected_to @tag
assert_equal(Tag.categories.general, @tag.reload.category)
assert_equal(2, @tag.versions.count)
assert_nil(@tag.first_version.updater)
assert_equal(@user, @tag.last_version.updater)
assert_equal(Tag.categories.copyright, @tag.first_version.category)
assert_equal(Tag.categories.general, @tag.last_version.category)
end
end
@@ -139,6 +160,7 @@ class TagsControllerTest < ActionDispatch::IntegrationTest
assert_response 403
assert_equal(true, @deprecated_tag.reload.is_deprecated?)
assert_equal(0, @tag.versions.count)
end
should "remove the deprecated status if the user is admin" do
@@ -146,6 +168,12 @@ class TagsControllerTest < ActionDispatch::IntegrationTest
assert_redirected_to @deprecated_tag
assert_equal(false, @deprecated_tag.reload.is_deprecated?)
assert_equal(2, @deprecated_tag.versions.count)
assert_nil(@deprecated_tag.first_version.updater)
assert_equal(@admin, @deprecated_tag.last_version.updater)
assert_equal(true, @deprecated_tag.first_version.is_deprecated)
assert_equal(false, @deprecated_tag.last_version.is_deprecated)
end
should "allow marking a tag as deprecated if it's empty" do
@@ -153,6 +181,12 @@ class TagsControllerTest < ActionDispatch::IntegrationTest
assert_redirected_to @nondeprecated_tag
assert_equal(true, @nondeprecated_tag.reload.is_deprecated?)
assert_equal(2, @nondeprecated_tag.versions.count)
assert_nil(@nondeprecated_tag.first_version.updater)
assert_equal(@normal_user, @nondeprecated_tag.last_version.updater)
assert_equal(false, @nondeprecated_tag.first_version.is_deprecated)
assert_equal(true, @nondeprecated_tag.last_version.is_deprecated)
end
should "not allow marking a tag as deprecated if it's not empty" do
@@ -160,6 +194,7 @@ class TagsControllerTest < ActionDispatch::IntegrationTest
assert_response 403
assert_equal(false, @normal_tag.reload.is_deprecated?)
assert_equal(0, @normal_tag.versions.count)
end
should "allow admins to mark tags as deprecated" do
@@ -167,6 +202,12 @@ class TagsControllerTest < ActionDispatch::IntegrationTest
assert_redirected_to @normal_tag
assert_equal(true, @normal_tag.reload.is_deprecated?)
assert_equal(2, @normal_tag.versions.count)
assert_nil(@normal_tag.first_version.updater)
assert_equal(@admin, @normal_tag.last_version.updater)
assert_equal(false, @normal_tag.first_version.is_deprecated)
assert_equal(true, @normal_tag.last_version.is_deprecated)
end
should "not allow deprecation of a tag with no wiki" do
@@ -174,15 +215,17 @@ class TagsControllerTest < ActionDispatch::IntegrationTest
assert_response 403
assert_equal(false, @tag_without_wiki.reload.is_deprecated?)
assert_equal(0, @tag_without_wiki.versions.count)
end
end
should "not change category when the tag is too large to be changed by a builder" do
@tag.update(category: Tag.categories.general, post_count: 1001)
@tag = create(:tag, category: Tag.categories.general, post_count: 1001)
put_auth tag_path(@tag), @user, params: {:tag => {:category => Tag.categories.artist}}
assert_response :forbidden
assert_equal(Tag.categories.general, @tag.reload.category)
assert_equal(0, @tag.versions.count)
end
end
end

View File

@@ -128,14 +128,12 @@ module PostSets
end
context "that has a matching artist" do
setup do
Tag.find_by(name: "a").update!(category: Tag.categories.artist)
@artist = FactoryBot.create(:artist, :name => "a")
end
should "find the artist" do
assert_not_nil(@set.artist)
assert_equal(@artist.id, @set.artist.id)
set = PostSets::Post.new("bkub")
artist = create(:artist, name: "bkub")
assert_not_nil(set.artist)
assert_equal(artist, set.artist)
end
end
end

View File

@@ -345,6 +345,22 @@ class PostTest < ActiveSupport::TestCase
@post = FactoryBot.create(:post)
end
context "with a new tag" do
should "create the new tag" do
tag1 = create(:tag, name: "foo", post_count: 100, category: Tag.categories.character)
create(:post, tag_string: "foo bar")
tag2 = Tag.find_by_name("bar")
assert_equal(101, tag1.reload.post_count)
assert_equal(Tag.categories.character, tag1.category)
assert_equal(0, tag1.versions.count)
assert_equal(1, tag2.post_count)
assert_equal(Tag.categories.general, tag2.category)
assert_equal(0, tag2.versions.count)
end
end
context "with a banned artist" do
setup do
CurrentUser.scoped(FactoryBot.create(:admin_user)) do
@@ -490,7 +506,7 @@ class PostTest < ActiveSupport::TestCase
should "not remove the tag if the tag was already in the post" do
bad_tag = create(:tag, name: "bad_tag")
old_post = create(:post, tag_string: "bad_tag")
bad_tag.update!(is_deprecated: true)
bad_tag.update!(is_deprecated: true, updater: create(:user))
old_post.update!(tag_string: "asd bad_tag")
assert_equal("asd bad_tag", old_post.reload.tag_string)
@@ -525,9 +541,30 @@ class PostTest < ActiveSupport::TestCase
context "tagged with a metatag" do
context "for a tag category prefix" do
should "set the category of a new tag" do
create(:post, tag_string: "char:hoge")
create(:post, tag_string: "char:chen")
tag = Tag.find_by_name("chen")
assert_equal(Tag.categories.character, Tag.find_by_name("hoge").category)
assert_equal(Tag.categories.character, tag.category)
assert_equal(0, tag.versions.count)
end
should "change the category of an existing tag" do
user = create(:user)
tag = create(:tag, name: "hoge", post_count: 1)
post = as(user) { create(:post, tag_string: "char:hoge") }
assert_equal(Tag.categories.character, tag.reload.category)
assert_equal(2, tag.versions.count)
assert_equal(1, tag.first_version.version)
assert_nil(tag.first_version.updater)
assert_nil(tag.first_version.previous_version)
assert_equal(Tag.categories.general, tag.first_version.category)
assert_equal(2, tag.last_version.version)
assert_equal(user, tag.last_version.updater)
assert_equal(tag.first_version, tag.last_version.previous_version)
assert_equal(Tag.categories.character, tag.last_version.category)
end
should "change the category for an aliased tag" do

View File

@@ -72,7 +72,7 @@ class TagTest < ActiveSupport::TestCase
tag = FactoryBot.create(:artist_tag)
assert_equal(Tag.categories.artist, Cache.get("tc:#{Cache.hash(tag.name)}"))
tag.update_attribute(:category, Tag.categories.copyright)
tag.update!(category: Tag.categories.copyright, updater: create(:user))
assert_equal(Tag.categories.copyright, Cache.get("tc:#{Cache.hash(tag.name)}"))
end
@@ -81,6 +81,70 @@ class TagTest < ActiveSupport::TestCase
end
end
context "When a tag is created" do
should "not create a new version" do
tag = create(:tag, category: Tag.categories.character)
assert_equal(0, tag.versions.count)
end
end
context "When a tag is updated" do
should "create the initial version before the new version" do
user = create(:user)
tag = create(:tag, created_at: 1.year.ago, updated_at: 6.months.ago)
tag.update!(updater: user, category: Tag.categories.character, is_deprecated: true)
assert_equal(2, tag.versions.count)
assert_equal(1, tag.first_version.version)
assert_equal(tag.updated_at_before_last_save.round(4), tag.first_version.created_at.round(4))
assert_equal(tag.updated_at_before_last_save.round(4), tag.first_version.updated_at.round(4))
assert_nil(tag.first_version.updater)
assert_nil(tag.first_version.previous_version)
assert_equal(Tag.categories.general, tag.first_version.category)
assert_equal(false, tag.first_version.is_deprecated)
assert_equal(2, tag.last_version.version)
assert_equal(user, tag.last_version.updater)
assert_equal(tag.first_version, tag.last_version.previous_version)
assert_equal(Tag.categories.character, tag.last_version.category)
assert_equal(true, tag.last_version.is_deprecated)
end
end
context "When a tag is updated twice by the same user" do
should "not merge the edits" do
updated_at = 6.months.ago
user = create(:user)
tag = create(:tag, created_at: 1.year.ago, updated_at: updated_at)
travel_to(1.minute.ago) { tag.update!(updater: user, category: Tag.categories.character, is_deprecated: true) }
tag.update!(updater: user, category: Tag.categories.copyright)
assert_equal(3, tag.versions.count)
assert_equal(1, tag.versions[0].version)
assert_equal(updated_at.round(4), tag.versions[0].created_at.round(4))
assert_equal(updated_at.round(4), tag.versions[0].updated_at.round(4))
assert_nil(tag.versions[0].updater)
assert_nil(tag.versions[0].previous_version)
assert_equal(Tag.categories.general, tag.versions[0].category)
assert_equal(false, tag.versions[0].is_deprecated)
assert_equal(2, tag.versions[1].version)
assert_equal(user, tag.versions[1].updater)
assert_equal(tag.versions[0], tag.versions[1].previous_version)
assert_equal(Tag.categories.character, tag.versions[1].category)
assert_equal(true, tag.versions[1].is_deprecated)
assert_equal(3, tag.versions[2].version)
assert_equal(user, tag.versions[2].updater)
assert_equal(tag.versions[1], tag.versions[2].previous_version)
assert_equal(Tag.categories.copyright, tag.versions[2].category)
assert_equal(true, tag.versions[2].is_deprecated)
end
end
context "A tag" do
should "be found when one exists" do
tag = FactoryBot.create(:tag)