akkoma/lib/mix/tasks/pleroma/search/meilisearch.ex

143 lines
3.7 KiB
Elixir
Raw Normal View History

# 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 Pleroma.Constants
import Mix.Pleroma
import Ecto.Query
import Pleroma.Search.Meilisearch,
only: [meili_post: 2, meili_put: 2, meili_get: 1, meili_delete!: 1]
2021-08-23 16:35:21 +00:00
def run(["index"]) do
start_pleroma()
meili_version =
(
{:ok, result} = meili_get("/version")
result["pkgVersion"]
)
# The ranking rule syntax was changed but nothing about that is mentioned in the changelog
if not Version.match?(meili_version, ">= 0.24.0") do
raise "Meilisearch <0.24.0 not supported"
end
{:ok, _} =
meili_post(
"/indexes/objects/settings/ranking-rules",
[
"published:desc",
"words",
"exactness",
"proximity",
"typo",
"attribute",
"sort"
]
)
{:ok, _} =
meili_post(
"/indexes/objects/settings/searchable-attributes",
[
"content"
]
)
IO.puts("Created indices. Starting to insert posts.")
2021-12-20 15:48:52 +00:00
chunk_size = Pleroma.Config.get([Pleroma.Search.Meilisearch, :initial_indexing_chunk_size])
Pleroma.Repo.transaction(
fn ->
query =
from(Pleroma.Object,
# Only index public and unlisted posts which are notes and have some text
where:
fragment("data->>'type' = 'Note'") and
(fragment("data->'to' \\? ?", ^Pleroma.Constants.as_public()) or
fragment("data->'cc' \\? ?", ^Pleroma.Constants.as_public())),
order_by: [desc: fragment("data->'published'")]
)
count = query |> Pleroma.Repo.aggregate(:count, :data)
IO.puts("Entries to index: #{count}")
Pleroma.Repo.stream(
query,
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.transform(0, fn objects, acc ->
new_acc = acc + Enum.count(objects)
2021-08-22 20:47:43 +00:00
# Reset to the beginning of the line and rewrite it
IO.write("\r")
IO.write("Indexed #{new_acc} entries")
{[objects], new_acc}
end)
|> Stream.each(fn objects ->
2021-08-23 16:35:21 +00:00
result =
meili_put(
2021-08-23 16:35:21 +00:00
"/indexes/objects/documents",
objects
)
with {:ok, res} <- result do
if not Map.has_key?(res, "updateId") do
IO.puts("\nFailed to index: #{inspect(result)}")
end
else
e -> IO.puts("\nFailed to index due to network error: #{inspect(e)}")
end
end)
|> Stream.run()
end,
timeout: :infinity
)
2021-08-22 20:47:43 +00:00
IO.write("\n")
end
def run(["clear"]) do
start_pleroma()
2021-08-23 16:35:21 +00:00
meili_delete!("/indexes/objects/documents")
end
def run(["show-private-key", master_key]) do
start_pleroma()
endpoint = Pleroma.Config.get([Pleroma.Search.Meilisearch, :url])
2021-08-23 16:35:21 +00:00
{:ok, result} =
Pleroma.HTTP.get(
Path.join(endpoint, "/keys"),
[{"X-Meili-API-Key", master_key}]
)
2021-08-23 16:35:21 +00:00
decoded = Jason.decode!(result.body)
if decoded["private"] do
IO.puts(decoded["private"])
else
IO.puts("Error fetching the key, check the master key is correct: #{inspect(decoded)}")
end
end
2021-08-23 17:21:46 +00:00
def run(["stats"]) do
start_pleroma()
{:ok, result} = meili_get("/indexes/objects/stats")
2021-08-23 17:21:46 +00:00
IO.puts("Number of entries: #{result["numberOfDocuments"]}")
IO.puts("Indexing? #{result["isIndexing"]}")
end
end