discourse/app/models/watched_word.rb

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

117 lines
3.1 KiB
Ruby
Raw Normal View History

# frozen_string_literal: true
class WatchedWord < ActiveRecord::Base
MAX_WORDS_PER_ACTION = 2000
before_validation { self.word = WatchedWord.normalize_word(self.word) }
before_validation do
if self.action == WatchedWord.actions[:link] && self.replacement !~ %r{\Ahttps?://}
self.replacement =
"#{Discourse.base_url}#{self.replacement&.starts_with?("/") ? "" : "/"}#{self.replacement}"
end
end
validates :word, presence: true, uniqueness: true, length: { maximum: 100 }
validates :action, presence: true
validate :replacement_is_url, if: -> { action == WatchedWord.actions[:link] }
validate :replacement_is_tag_list, if: -> { action == WatchedWord.actions[:tag] }
validates_each :word do |record, attr, val|
if WatchedWord.where(action: record.action).count >= MAX_WORDS_PER_ACTION
record.errors.add(:word, :too_many)
end
end
after_save -> { WordWatcher.clear_cache! }
after_destroy -> { WordWatcher.clear_cache! }
scope :for,
->(word:) do
where(
"(word ILIKE :word AND case_sensitive = 'f') OR (word LIKE :word AND case_sensitive = 't')",
word: word,
)
end
def self.actions
@actions ||=
Enum.new(
block: 1,
censor: 2,
require_approval: 3,
flag: 4,
link: 8,
replace: 5,
tag: 6,
silence: 7,
)
end
def self.create_or_update_word(params)
word = normalize_word(params[:word])
word = self.for(word: word).first_or_initialize(word: word)
word.replacement = params[:replacement] if params[:replacement]
word.action_key = params[:action_key] if params[:action_key]
word.action = params[:action] if params[:action]
word.case_sensitive = params[:case_sensitive] if !params[:case_sensitive].nil?
word.save
word
end
def self.has_replacement?(action)
action == :replace || action == :tag || action == :link
end
def action_key=(arg)
self.action = WatchedWord.actions[arg.to_sym]
end
def action_log_details
if replacement.present?
"#{word}#{replacement}"
else
word
end
end
private
def self.normalize_word(word)
# When a regular expression is converted to a string, it is wrapped with
# '(?-mix:' and ')'
word = word[7..-2] if word.start_with?("(?-mix:")
word.strip.squeeze("*")
end
def replacement_is_url
errors.add(:base, :invalid_url) if replacement !~ URI.regexp
end
def replacement_is_tag_list
tag_list = replacement&.split(",")
tags = Tag.where(name: tag_list)
if tag_list.blank? || tags.empty? || tag_list.size != tags.size
errors.add(:base, :invalid_tag_list)
end
end
end
# == Schema Information
#
# Table name: watched_words
#
FEATURE: Add support for case-sensitive Watched Words (#17445) * FEATURE: Add case-sensitivity flag to watched_words Currently, all watched words are matched case-insensitively. This flag allows a watched word to be flagged for case-sensitive matching. To allow allow for backwards compatibility the flag is set to false by default. * FEATURE: Support case-sensitive creation of Watched Words via API Extend admin creation and upload of Watched Words to support case sensitive flag. This lays the ground work for supporting case-insensitive matching of Watched Words. Support for an extra column has also been introduced for the Watched Words upload CSV file. The new column structure is as follows: word,replacement,case_sentive * FEATURE: Enable case-sensitive matching of Watched Words WordWatcher's word_matcher_regexp now returns a list of regular expressions instead of one case-insensitive regular expression. With the ability to flag a Watched Word as case-sensitive, an action can have words of both sensitivities.This makes the use of the global Regexp::IGNORECASE flag added to all words problematic. To get around platform limitations around the use of subexpression level switches/flags, a list of regular expressions is returned instead, one for each case sensitivity. Word matching has also been updated to use this list of regular expressions instead of one. * FEATURE: Use case-sensitive regular expressions for Watched Words Update Watched Words regular expressions matching and processing to handle the extra metadata which comes along with the introduction of case-sensitive Watched Words. This allows case-sensitive Watched Words to matched as such. * DEV: Simplify type casting of case-sensitive flag from uploads Use builtin semantics instead of a custom method for converting string case flags in uploaded Watched Words to boolean. * UX: Add case-sensitivity details to Admin Watched Words UI Update Watched Word form to include a toggle for case-sensitivity. This also adds support for, case-sensitive testing and matching of Watched Word in the admin UI. * DEV: Code improvements from review feedback - Extract watched word regex creation out to a utility function - Make JS array presence check more explicit and readable * DEV: Extract Watched Word regex creation to utility function Clean-up work from review feedback. Reduce code duplication. * DEV: Rename word_matcher_regexp to word_matcher_regexp_list Since a list is returned now instead of a single regular expression, change `word_matcher_regexp` to `word_matcher_regexp_list` to better communicate this change. * DEV: Incorporate WordWatcher updates from upstream Resolve conflicts and ensure apply_to_text does not remove non-word characters in matches that aren't at the beginning of the line.
2022-08-02 04:06:03 -04:00
# id :integer not null, primary key
# word :string not null
# action :integer not null
# created_at :datetime not null
# updated_at :datetime not null
# replacement :string
# case_sensitive :boolean default(FALSE), not null
#
# Indexes
#
# index_watched_words_on_action_and_word (action,word) UNIQUE
#