From 6ff67be0f6e79ec403e08c69717ee8c89451c70e Mon Sep 17 00:00:00 2001 From: Eugen Rochko Date: Sat, 13 Jul 2019 16:45:50 +0200 Subject: Add a spam check (#11217) * Add a spam check * Use Nilsimsa to generate locality-sensitive hashes and compare using Levenshtein distance * Add more tests * Add exemption when the message is a reply to something that mentions the sender * Use Nilsimsa Compare Value instead of Levenshtein distance * Use MD5 for messages shorter than 10 characters * Add message to automated report, do not add non-public statuses to automated report, add trust level to accounts and make unsilencing raise the trust level to prevent repeated spam checks on that account * Expire spam check data after 3 months * Add support for local statuses, reduce expiration to 1 week, always create a report * Add content warnings to the spam check and exempt empty statuses * Change Nilsimsa threshold to 95 and make sure removed statuses are removed from the spam check * Add all matched statuses into automatic report --- db/migrate/20190701022101_add_trust_level_to_accounts.rb | 5 +++++ db/schema.rb | 1 + 2 files changed, 6 insertions(+) create mode 100644 db/migrate/20190701022101_add_trust_level_to_accounts.rb (limited to 'db') diff --git a/db/migrate/20190701022101_add_trust_level_to_accounts.rb b/db/migrate/20190701022101_add_trust_level_to_accounts.rb new file mode 100644 index 000000000..917486d2e --- /dev/null +++ b/db/migrate/20190701022101_add_trust_level_to_accounts.rb @@ -0,0 +1,5 @@ +class AddTrustLevelToAccounts < ActiveRecord::Migration[5.2] + def change + add_column :accounts, :trust_level, :integer + end +end diff --git a/db/schema.rb b/db/schema.rb index 2e38fb1f2..c7b6b9be6 100644 --- a/db/schema.rb +++ b/db/schema.rb @@ -148,6 +148,7 @@ ActiveRecord::Schema.define(version: 2019_07_06_233204) do t.string "also_known_as", array: true t.datetime "silenced_at" t.datetime "suspended_at" + t.integer "trust_level" t.index "(((setweight(to_tsvector('simple'::regconfig, (display_name)::text), 'A'::\"char\") || setweight(to_tsvector('simple'::regconfig, (username)::text), 'B'::\"char\")) || setweight(to_tsvector('simple'::regconfig, (COALESCE(domain, ''::character varying))::text), 'C'::\"char\")))", name: "search_index", using: :gin t.index "lower((username)::text), lower((domain)::text)", name: "index_accounts_on_username_and_domain_lower", unique: true t.index ["moved_to_account_id"], name: "index_accounts_on_moved_to_account_id" -- cgit