Allow keywords to match either substrings or whole words.

Word-boundary matching only works as intended in English and languages
that use similar word-breaking characters; it doesn't work so well in
(say) Japanese, Chinese, or Thai.  It's unacceptable to have a feature
that doesn't work as intended for some languages.  (Moreso especially
considering that it's likely that the largest contingent on the Mastodon
bit of the fediverse speaks Japanese.)

There are rules specified in Unicode TR29[1] for word-breaking across
all languages supported by Unicode, but the rules deliberately do not
cover all cases.  In fact, TR29 states

    For example, reliable detection of word boundaries in languages such
    as Thai, Lao, Chinese, or Japanese requires the use of dictionary
    lookup, analogous to English hyphenation.

So we aren't going to be able to make word detection work with regexes
within Mastodon (or glitchsoc).  However, for a first pass (even if it's
kind of punting) we can allow the user to choose whether they want word
or substring detection and warn about the limitations of this
implementation in, say, docs.

[1]: https://unicode.org/reports/tr29/
     https://web.archive.org/web/20171001005125/https://unicode.org/reports/tr29/
This commit is contained in:
David Yip 2017-10-15 19:49:22 -05:00
parent 2e03a10059
commit 4a64181461
4 changed files with 16 additions and 6 deletions

View File

@ -6,6 +6,7 @@
# id :integer not null, primary key # id :integer not null, primary key
# account_id :integer not null # account_id :integer not null
# keyword :string not null # keyword :string not null
# whole_word :boolean default(TRUE), not null
# created_at :datetime not null # created_at :datetime not null
# updated_at :datetime not null # updated_at :datetime not null
# #
@ -32,12 +33,13 @@ class KeywordMute < ApplicationRecord
def initialize(account_id) def initialize(account_id)
re = [].tap do |arr| re = [].tap do |arr|
KeywordMute.where(account_id: account_id).select(:keyword, :id).find_each do |m| KeywordMute.where(account_id: account_id).select(:keyword, :id, :whole_word).find_each do |m|
arr << Regexp.escape(m.keyword.strip) boundary = m.whole_word ? '\b' : ''
arr << "#{boundary}#{Regexp.escape(m.keyword.strip)}#{boundary}"
end end
end.join('|') end.join('|')
@regex = /\b(?:#{re})\b/i unless re.empty? @regex = /#{re}/i unless re.empty?
end end
def =~(str) def =~(str)

View File

@ -3,6 +3,7 @@ class CreateKeywordMutes < ActiveRecord::Migration[5.1]
create_table :keyword_mutes do |t| create_table :keyword_mutes do |t|
t.references :account, null: false t.references :account, null: false
t.string :keyword, null: false t.string :keyword, null: false
t.boolean :whole_word, null: false, default: true
t.timestamps t.timestamps
end end

View File

@ -170,6 +170,7 @@ ActiveRecord::Schema.define(version: 20171010025614) do
create_table "keyword_mutes", force: :cascade do |t| create_table "keyword_mutes", force: :cascade do |t|
t.bigint "account_id", null: false t.bigint "account_id", null: false
t.string "keyword", null: false t.string "keyword", null: false
t.boolean "whole_word", default: true, null: false
t.datetime "created_at", null: false t.datetime "created_at", null: false
t.datetime "updated_at", null: false t.datetime "updated_at", null: false
t.index ["account_id"], name: "index_keyword_mutes_on_account_id" t.index ["account_id"], name: "index_keyword_mutes_on_account_id"

View File

@ -30,10 +30,16 @@ RSpec.describe KeywordMute, type: :model do
expect(matcher =~ 'This is a hot take').to be_falsy expect(matcher =~ 'This is a hot take').to be_falsy
end end
it 'does not match substrings matching keywords' do it 'considers word boundaries when matching' do
KeywordMute.create!(account: alice, keyword: 'take') KeywordMute.create!(account: alice, keyword: 'bob', whole_word: true)
expect(matcher =~ 'This is a shiitake mushroom').to be_falsy expect(matcher =~ 'bobcats').to be_falsy
end
it 'matches substrings if whole_word is false' do
KeywordMute.create!(account: alice, keyword: 'take', whole_word: false)
expect(matcher =~ 'This is a shiitake mushroom').to be_truthy
end end
it 'matches keywords at the beginning of the text' do it 'matches keywords at the beginning of the text' do