Page MenuHomePhorge
Files F85629984

No OneTemporary
Actions

Size
7 KB
Referenced Files
None
Subscribers
None

View Options

diff --git a/lib/mix/tasks/pleroma/search/meilisearch.ex b/lib/mix/tasks/pleroma/search/meilisearch.ex
index 3704e0bdc..b5a394e34 100644
--- a/lib/mix/tasks/pleroma/search/meilisearch.ex
+++ b/lib/mix/tasks/pleroma/search/meilisearch.ex
@@ -1,122 +1,91 @@
# Pleroma: A lightweight social networking server
# Copyright © 2017-2021 Pleroma Authors <https://pleroma.social/>
# SPDX-License-Identifier: AGPL-3.0-only
defmodule Mix.Tasks.Pleroma.Search.Meilisearch do
require Logger
require Pleroma.Constants
import Mix.Pleroma
import Ecto.Query
def run(["index"]) do
start_pleroma()
endpoint = Pleroma.Config.get([Pleroma.Search.Meilisearch, :url])
{:ok, _} =
Pleroma.HTTP.post(
"#{endpoint}/indexes/objects/settings/ranking-rules",
Jason.encode!([
"desc(published)",
"typo",
"words",
"proximity",
"attribute",
"wordsPosition",
"exactness"
])
)
{:ok, _} =
Pleroma.HTTP.post(
"#{endpoint}/indexes/objects/settings/searchable-attributes",
Jason.encode!([
"content"
])
)
chunk_size = 10_000
Pleroma.Repo.transaction(
fn ->
Pleroma.Repo.stream(
from(Pleroma.Object,
# Only index public posts which are notes and have some text
where:
fragment("data->>'type' = 'Note'") and
fragment("LENGTH(data->>'content') > 0") and
fragment("data->'to' \\? ?", ^Pleroma.Constants.as_public()),
order_by: [desc: fragment("data->'published'")]
),
timeout: :infinity
)
+ |> Stream.map(&Pleroma.Search.Meilisearch.object_to_search_data/1)
+ |> Stream.filter(fn o -> not is_nil(o) end)
|> Stream.chunk_every(chunk_size)
- |> Stream.map(fn objects ->
- Enum.map(objects, fn object ->
- data = object.data
-
- content_str =
- case data["content"] do
- [nil | rest] -> to_string(rest)
- str -> str
- end
-
- {:ok, published, _} = DateTime.from_iso8601(data["published"])
-
- content =
- with {:ok, scrubbed} <- FastSanitize.strip_tags(content_str),
- trimmed <- String.trim(scrubbed) do
- trimmed
- end
-
- # Only index if there is anything in the string. If there is a single symbol,
- # it's probably a dot from mastodon posts with just the picture
- if String.length(content) > 1 do
- %{
- id: object.id,
- content: content,
- ap: data["id"],
- published: published |> DateTime.to_unix()
- }
- else
- nil
- end
- end)
- |> Enum.filter(fn o -> not is_nil(o) end)
- end)
|> Stream.transform(0, fn objects, acc ->
new_acc = acc + Enum.count(objects)
IO.puts("Indexed #{new_acc} entries")
{[objects], new_acc}
end)
|> Stream.each(fn objects ->
{:ok, result} =
Pleroma.HTTP.post(
"#{endpoint}/indexes/objects/documents",
Jason.encode!(objects)
)
if not Map.has_key?(Jason.decode!(result.body), "updateId") do
IO.puts("Failed to index: #{result}")
end
end)
|> Stream.run()
end,
timeout: :infinity
)
end
def run(["clear"]) do
start_pleroma()
endpoint = Pleroma.Config.get([Pleroma.Search.Meilisearch, :url])
{:ok, _} =
Pleroma.HTTP.request(:delete, "#{endpoint}/indexes/objects/documents", "", [],
timeout: :infinity
)
end
end
diff --git a/lib/pleroma/search/meilisearch.ex b/lib/pleroma/search/meilisearch.ex
index 87fdeaf5e..10468e36c 100644
--- a/lib/pleroma/search/meilisearch.ex
+++ b/lib/pleroma/search/meilisearch.ex
@@ -1,84 +1,102 @@
defmodule Pleroma.Search.Meilisearch do
require Logger
require Pleroma.Constants
alias Pleroma.Activity
import Pleroma.Activity.Search
import Ecto.Query
def search(user, query, options \\ []) do
limit = Enum.min([Keyword.get(options, :limit), 40])
offset = Keyword.get(options, :offset, 0)
author = Keyword.get(options, :author)
endpoint = Pleroma.Config.get([Pleroma.Search.Meilisearch, :url])
{:ok, result} =
Pleroma.HTTP.post(
"#{endpoint}/indexes/objects/search",
Jason.encode!(%{q: query, offset: offset, limit: limit})
)
hits = Jason.decode!(result.body)["hits"] |> Enum.map(& &1["ap"])
try do
hits
|> Activity.create_by_object_ap_id()
|> Activity.with_preloaded_object()
|> Activity.with_preloaded_object()
|> Activity.restrict_deactivated_users()
|> maybe_restrict_local(user)
|> maybe_restrict_author(author)
|> maybe_restrict_blocked(user)
|> maybe_fetch(user, query)
|> order_by([object: obj], desc: obj.data["published"])
|> Pleroma.Repo.all()
rescue
_ -> maybe_fetch([], user, query)
end
end
- def add_to_index(activity) do
- object = activity.object
-
- if activity.data["type"] == "Create" and not is_nil(object) and object.data["type"] == "Note" and
+ def object_to_search_data(object) do
+ if not is_nil(object) and object.data["type"] == "Note" and
Pleroma.Constants.as_public() in object.data["to"] do
data = object.data
- endpoint = Pleroma.Config.get([Pleroma.Search.Meilisearch, :url])
+ content_str =
+ case data["content"] do
+ [nil | rest] -> to_string(rest)
+ str -> str
+ end
+
+ content =
+ with {:ok, scrubbed} <- FastSanitize.strip_tags(content_str),
+ trimmed <- String.trim(scrubbed) do
+ trimmed
+ end
+
+ if String.length(content) > 1 do
+ {:ok, published, _} = DateTime.from_iso8601(data["published"])
+
+ %{
+ id: object.id,
+ content: content,
+ ap: data["id"],
+ published: published |> DateTime.to_unix()
+ }
+ end
+ end
+ end
- {:ok, published, _} = DateTime.from_iso8601(data["published"])
+ def add_to_index(activity) do
+ maybe_search_data = object_to_search_data(activity)
+
+ if activity.data["type"] == "Create" and maybe_search_data do
+ endpoint = Pleroma.Config.get([Pleroma.Search.Meilisearch, :url])
{:ok, result} =
Pleroma.HTTP.post(
"#{endpoint}/indexes/objects/documents",
- Jason.encode!([
- %{
- id: object.id,
- content: data["content"] |> Pleroma.HTML.filter_tags(),
- ap: data["id"],
- published: published |> DateTime.to_unix()
- }
- ])
+ Jason.encode!([maybe_search_data])
)
if not Map.has_key?(Jason.decode!(result.body), "updateId") do
Logger.error("Failed to add activity #{activity.id} to index: #{result.body}")
end
end
end
def remove_from_index(object) do
endpoint = Pleroma.Config.get([Pleroma.Search.Meilisearch, :url])
{:ok, _} =
Pleroma.HTTP.request(
:delete,
"#{endpoint}/indexes/objects/documents/#{object.id}",
"",
[],
[]
)
end
end

File Metadata

Mime Type
text/x-diff
Expires
Sun, Aug 9, 8:39 AM (1 d, 14 h)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
1724362
Default Alt Text
(7 KB)

Event Timeline