From 76f732766ba36c3a94cf6b8b39fb745c1cf3f49a Mon Sep 17 00:00:00 2001 From: Mark Felder Date: Wed, 3 Feb 2021 12:32:44 -0600 Subject: [PATCH 1/5] Exclude reporter from receiving notifications from their own reports. Currently only works if the reporting actor is an admin, but if we include moderators with those who receive notification reports it will work for them. --- lib/pleroma/notification.ex | 4 ++-- lib/pleroma/web/activity_pub/activity_pub.ex | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/lib/pleroma/notification.ex b/lib/pleroma/notification.ex index 55b513212..1970fbf65 100644 --- a/lib/pleroma/notification.ex +++ b/lib/pleroma/notification.ex @@ -507,8 +507,8 @@ defmodule Pleroma.Notification do [object_id] end - def get_potential_receiver_ap_ids(%{data: %{"type" => "Flag"}}) do - User.all_superusers() |> Enum.map(fn user -> user.ap_id end) + def get_potential_receiver_ap_ids(%{data: %{"type" => "Flag", "actor" => actor}}) do + (User.all_superusers() |> Enum.map(fn user -> user.ap_id end)) -- [actor] end def get_potential_receiver_ap_ids(activity) do diff --git a/lib/pleroma/web/activity_pub/activity_pub.ex b/lib/pleroma/web/activity_pub/activity_pub.ex index 1a84375fb..5b45e2ca1 100644 --- a/lib/pleroma/web/activity_pub/activity_pub.ex +++ b/lib/pleroma/web/activity_pub/activity_pub.ex @@ -377,6 +377,7 @@ defmodule Pleroma.Web.ActivityPub.ActivityPub do :ok <- maybe_federate(stripped_activity) do User.all_superusers() + |> Enum.filter(fn user -> user.ap_id != actor end) |> Enum.filter(fn user -> not is_nil(user.email) end) |> Enum.each(fn superuser -> superuser From 5bb5949048b6eeb236cca450c8399ac412fbd2a8 Mon Sep 17 00:00:00 2001 From: Mark Felder Date: Wed, 3 Feb 2021 12:54:53 -0600 Subject: [PATCH 2/5] Validate admin making report doesn't get their own report notification, but other admins do --- test/pleroma/notification_test.exs | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/test/pleroma/notification_test.exs b/test/pleroma/notification_test.exs index 0c6ebfb76..948587292 100644 --- a/test/pleroma/notification_test.exs +++ b/test/pleroma/notification_test.exs @@ -45,6 +45,20 @@ defmodule Pleroma.NotificationTest do assert notification.type == "pleroma:report" end + test "suppresses notification to reporter if reporter is an admin" do + reporting_admin = insert(:user, is_admin: true) + reported_user = insert(:user) + other_admin = insert(:user, is_admin: true) + + {:ok, activity} = CommonAPI.report(reporting_admin, %{account_id: reported_user.id}) + + {:ok, [notification]} = Notification.create_notifications(activity) + + refute notification.user_id == reporting_admin.id + assert notification.user_id == other_admin.id + assert notification.type == "pleroma:report" + end + test "creates a notification for an emoji reaction" do user = insert(:user) other_user = insert(:user) From 000d3365c391fb3613c5365f73f5bd51d2555840 Mon Sep 17 00:00:00 2001 From: Mark Felder Date: Wed, 3 Feb 2021 14:52:49 -0600 Subject: [PATCH 3/5] Document admin actors not getting report notifications --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 47009abc9..777847fa2 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -18,6 +18,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/). - Deprecated `Pleroma.Uploaders.S3, :public_endpoint`. Now `Pleroma.Upload, :base_url` is the standard configuration key for all uploaders. - Improved Apache webserver support: updated sample configuration, MediaProxy cache invalidation verified with the included sample script - Improve OAuth 2.0 provider support. A missing `fqn` field was added to the response, but does not expose the user's email address. +- Admins no longer receive notifications for reports if they are the actor making the report.
API Changes From 1d8f1fe0772736dd71219d244783c9d671dd7223 Mon Sep 17 00:00:00 2001 From: Mark Felder Date: Fri, 5 Feb 2021 13:32:21 -0600 Subject: [PATCH 4/5] Add a default rule to not attempt to cache any files larger than 50MB This fixes connection failures when trying to retrieve large files. It is less common in typical Pleroma usage, but it's possible to encounter this on a cloud instance with lower memory. --- installation/pleroma.vcl | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/installation/pleroma.vcl b/installation/pleroma.vcl index 13dad784c..4752510ea 100644 --- a/installation/pleroma.vcl +++ b/installation/pleroma.vcl @@ -59,6 +59,13 @@ sub vcl_backend_response { set beresp.http.CR = beresp.http.content-range; } + # Bypass cache for large files + # 50000000 ~ 50MB + if (std.integer(beresp.http.content-length, 0) > 50000000) { + set beresp.uncacheable = true; + return(deliver); + } + # Don't cache objects that require authentication if (beresp.http.Authorization && !beresp.http.Cache-Control ~ "public") { set beresp.uncacheable = true; From 8d4e0342e1b5ebbe486dc538e3c8fe81d53220e6 Mon Sep 17 00:00:00 2001 From: hyperion <8027-hyperion@users.noreply.git.pleroma.social> Date: Sat, 6 Feb 2021 09:42:17 +0000 Subject: [PATCH 5/5] Update priv/repo/migrations/20190501125843_add_fts_index_to_objects.exs, priv/repo/optional_migrations/rum_indexing/20190510135645_add_fts_index_to_objects_two.exs files --- docs/administration/CLI_tasks/database.md | 18 +++++++ docs/configuration/howto_search_cjk.md | 42 +++++++++++++++++ lib/mix/tasks/pleroma/database.ex | 47 +++++++++++++++++++ lib/pleroma/activity/search.ex | 8 ++-- ...1080964_add_default_text_search_config.exs | 11 +++++ ...510135645_add_fts_index_to_objects_two.exs | 2 +- 6 files changed, 123 insertions(+), 5 deletions(-) create mode 100644 docs/configuration/howto_search_cjk.md create mode 100644 priv/repo/migrations/20210121080964_add_default_text_search_config.exs diff --git a/docs/administration/CLI_tasks/database.md b/docs/administration/CLI_tasks/database.md index 6dca83167..c53c49921 100644 --- a/docs/administration/CLI_tasks/database.md +++ b/docs/administration/CLI_tasks/database.md @@ -141,3 +141,21 @@ but should only be run if necessary. **It is safe to cancel this.** ```sh mix pleroma.database ensure_expiration ``` + +## Change Text Search Configuration + +Change `default_text_search_config` for database and (if necessary) text_search_config used in index, then rebuild index (it may take time). + +=== "OTP" + + ```sh + ./bin/pleroma_ctl database set_text_search_config english + ``` + +=== "From Source" + + ```sh + mix pleroma.database set_text_search_config english + ``` + +See [PostgreSQL documentation](https://www.postgresql.org/docs/current/textsearch-configuration.html) and `docs/configuration/howto_search_cjk.md` for more detail. diff --git a/docs/configuration/howto_search_cjk.md b/docs/configuration/howto_search_cjk.md new file mode 100644 index 000000000..d3ce28077 --- /dev/null +++ b/docs/configuration/howto_search_cjk.md @@ -0,0 +1,42 @@ +# How to enable text search for Chinese, Japanese and Korean + +Pleroma's full text search feature is powered by PostgreSQL's native [text search](https://www.postgresql.org/docs/current/textsearch.html), it works well out of box for most of languages, but needs extra configurations for some asian languages like Chinese, Japanese and Korean (CJK). + + +## Setup and test the new search config + +In most cases, you would need an extension installed to support parsing CJK text. Here are a few extension you may choose from, or you are more than welcome to share additional ones you found working for you with the rest of Pleroma community. + + * [a generic n-gram parser](https://github.com/huangjimmy/pg_cjk_parser) supports Simplifed/Traditional Chinese, Japanese, and Korean + * [a Korean parser](https://github.com/i0seph/textsearch_ko) based on mecab + * [a Japanese parser](https://www.amris.co.jp/tsja/index.html) based on mecab + * [zhparser](https://github.com/amutu/zhparser/) is a PostgreSQL extension base on the Simple Chinese Word Segmentation(SCWS) + * [another Chinese parser](https://github.com/jaiminpan/pg_jieba) based on Jieba Chinese Word Segmentation + +Once you have the new search config , make sure you test it with the `pleroma` user in PostgreSQL (change `YOUR.CONFIG` to your real configuration name) +``` +SELECT ts_debug('YOUR.CONFIG', '安装和配置Nginx, ElixirとErlangをインストールします'); +``` +Check output of the query, and see if it matches your expectation. + + +## Update text search config and index in database + +=== "OTP" + + ```sh + ./bin/pleroma_ctl database set_text_search_config YOUR.CONFIG + ``` + +=== "From Source" + + ```sh + mix pleroma.database set_text_search_config YOUR.CONFIG + ``` + +Note: index update may take a while. + +## Restart database connection +Since some changes above will only apply with a new database connection, you will have to restart either Pleroma or PostgreSQL process, or use `pg_terminate_backend` SQL command without restarting either. + +Now the search results of statuses should be much more friendly for your language of choice, the results for searching users and tags were not changed, as the default parsing/matching should work for most cases. diff --git a/lib/mix/tasks/pleroma/database.ex b/lib/mix/tasks/pleroma/database.ex index 6261910f0..2403ed581 100644 --- a/lib/mix/tasks/pleroma/database.ex +++ b/lib/mix/tasks/pleroma/database.ex @@ -167,4 +167,51 @@ defmodule Mix.Tasks.Pleroma.Database do end) |> Stream.run() end + + def run(["set_text_search_config", tsconfig]) do + start_pleroma() + %{rows: [[tsc]]} = Ecto.Adapters.SQL.query!(Pleroma.Repo, "SHOW default_text_search_config;") + shell_info("Current default_text_search_config: #{tsc}") + + %{rows: [[db]]} = Ecto.Adapters.SQL.query!(Pleroma.Repo, "SELECT current_database();") + shell_info("Update default_text_search_config: #{tsconfig}") + + %{messages: msg} = + Ecto.Adapters.SQL.query!( + Pleroma.Repo, + "ALTER DATABASE #{db} SET default_text_search_config = '#{tsconfig}';" + ) + + # non-exist config will not raise excpetion but only give >0 messages + if length(msg) > 0 do + shell_info("Error: #{inspect(msg, pretty: true)}") + else + rum_enabled = Pleroma.Config.get([:database, :rum_enabled]) + shell_info("Recreate index, RUM: #{rum_enabled}") + + # Note SQL below needs to be kept up-to-date with latest GIN or RUM index definition in future + if rum_enabled do + Ecto.Adapters.SQL.query!( + Pleroma.Repo, + "CREATE OR REPLACE FUNCTION objects_fts_update() RETURNS trigger AS $$ BEGIN + new.fts_content := to_tsvector(new.data->>'content'); + RETURN new; + END + $$ LANGUAGE plpgsql" + ) + + shell_info("Refresh RUM index") + Ecto.Adapters.SQL.query!(Pleroma.Repo, "UPDATE objects SET updated_at = NOW();") + else + Ecto.Adapters.SQL.query!(Pleroma.Repo, "DROP INDEX IF EXISTS objects_fts;") + + Ecto.Adapters.SQL.query!( + Pleroma.Repo, + "CREATE INDEX objects_fts ON objects USING gin(to_tsvector('#{tsconfig}', data->>'content')); " + ) + end + + shell_info('Done.') + end + end end diff --git a/lib/pleroma/activity/search.ex b/lib/pleroma/activity/search.ex index 52e7c048d..ed898ba4f 100644 --- a/lib/pleroma/activity/search.ex +++ b/lib/pleroma/activity/search.ex @@ -64,7 +64,7 @@ defmodule Pleroma.Activity.Search do from([a, o] in q, where: fragment( - "to_tsvector('english', ?->>'content') @@ plainto_tsquery('english', ?)", + "to_tsvector(?->>'content') @@ plainto_tsquery(?)", o.data, ^search_query ) @@ -75,7 +75,7 @@ defmodule Pleroma.Activity.Search do from([a, o] in q, where: fragment( - "to_tsvector('english', ?->>'content') @@ websearch_to_tsquery('english', ?)", + "to_tsvector(?->>'content') @@ websearch_to_tsquery(?)", o.data, ^search_query ) @@ -86,7 +86,7 @@ defmodule Pleroma.Activity.Search do from([a, o] in q, where: fragment( - "? @@ plainto_tsquery('english', ?)", + "? @@ plainto_tsquery(?)", o.fts_content, ^search_query ), @@ -98,7 +98,7 @@ defmodule Pleroma.Activity.Search do from([a, o] in q, where: fragment( - "? @@ websearch_to_tsquery('english', ?)", + "? @@ websearch_to_tsquery(?)", o.fts_content, ^search_query ), diff --git a/priv/repo/migrations/20210121080964_add_default_text_search_config.exs b/priv/repo/migrations/20210121080964_add_default_text_search_config.exs new file mode 100644 index 000000000..09b6cccc9 --- /dev/null +++ b/priv/repo/migrations/20210121080964_add_default_text_search_config.exs @@ -0,0 +1,11 @@ +defmodule Pleroma.Repo.Migrations.AddDefaultTextSearchConfig do + use Ecto.Migration + + def change do + execute("DO $$ + BEGIN + execute 'ALTER DATABASE '||current_database()||' SET default_text_search_config = ''english'' '; + END + $$;") + end +end diff --git a/priv/repo/optional_migrations/rum_indexing/20190510135645_add_fts_index_to_objects_two.exs b/priv/repo/optional_migrations/rum_indexing/20190510135645_add_fts_index_to_objects_two.exs index 82e02281d..88476fb57 100644 --- a/priv/repo/optional_migrations/rum_indexing/20190510135645_add_fts_index_to_objects_two.exs +++ b/priv/repo/optional_migrations/rum_indexing/20190510135645_add_fts_index_to_objects_two.exs @@ -17,7 +17,7 @@ defmodule Pleroma.Repo.Migrations.AddFtsIndexToObjectsTwo do execute("CREATE FUNCTION objects_fts_update() RETURNS trigger AS $$ begin - new.fts_content := to_tsvector('english', new.data->>'content'); + new.fts_content := to_tsvector(new.data->>'content'); return new; end $$ LANGUAGE plpgsql")