Git of dcc - anni/blob - test/pleroma/web/rich_media/parser_test.exs

   1 # Pleroma: A lightweight social networking server
   2 # Copyright © 2017-2022 Pleroma Authors <https://pleroma.social/>
   3 # SPDX-License-Identifier: AGPL-3.0-only
   4
   5 defmodule Pleroma.Web.RichMedia.ParserTest do
   6   use ExUnit.Case, async: true
   7
   8   alias Pleroma.Web.RichMedia.Parser
   9
  10   setup do
  11     Tesla.Mock.mock(fn
  12       %{
  13         method: :get,
  14         url: "http://example.com/ogp"
  15       } ->
  16         %Tesla.Env{status: 200, body: File.read!("test/fixtures/rich_media/ogp.html")}
  17
  18       %{
  19         method: :get,
  20         url: "http://example.com/non-ogp"
  21       } ->
  22         %Tesla.Env{status: 200, body: File.read!("test/fixtures/rich_media/non_ogp_embed.html")}
  23
  24       %{
  25         method: :get,
  26         url: "http://example.com/ogp-missing-title"
  27       } ->
  28         %Tesla.Env{
  29           status: 200,
  30           body: File.read!("test/fixtures/rich_media/ogp-missing-title.html")
  31         }
  32
  33       %{
  34         method: :get,
  35         url: "http://example.com/twitter-card"
  36       } ->
  37         %Tesla.Env{status: 200, body: File.read!("test/fixtures/rich_media/twitter_card.html")}
  38
  39       %{
  40         method: :get,
  41         url: "http://example.com/oembed"
  42       } ->
  43         %Tesla.Env{status: 200, body: File.read!("test/fixtures/rich_media/oembed.html")}
  44
  45       %{
  46         method: :get,
  47         url: "http://example.com/oembed.json"
  48       } ->
  49         %Tesla.Env{status: 200, body: File.read!("test/fixtures/rich_media/oembed.json")}
  50
  51       %{method: :get, url: "http://example.com/empty"} ->
  52         %Tesla.Env{status: 200, body: "hello"}
  53
  54       %{method: :get, url: "http://example.com/malformed"} ->
  55         %Tesla.Env{status: 200, body: File.read!("test/fixtures/rich_media/malformed-data.html")}
  56
  57       %{method: :get, url: "http://example.com/error"} ->
  58         {:error, :overload}
  59
  60       %{
  61         method: :head,
  62         url: "http://example.com/huge-page"
  63       } ->
  64         %Tesla.Env{
  65           status: 200,
  66           headers: [{"content-length", "2000001"}, {"content-type", "text/html"}]
  67         }
  68
  69       %{
  70         method: :head,
  71         url: "http://example.com/pdf-file"
  72       } ->
  73         %Tesla.Env{
  74           status: 200,
  75           headers: [{"content-length", "1000000"}, {"content-type", "application/pdf"}]
  76         }
  77
  78       %{method: :head} ->
  79         %Tesla.Env{status: 404, body: "", headers: []}
  80     end)
  81
  82     :ok
  83   end
  84
  85   test "returns error when no metadata present" do
  86     assert {:error, _} = Parser.parse("http://example.com/empty")
  87   end
  88
  89   test "doesn't just add a title" do
  90     assert {:error, {:invalid_metadata, _}} = Parser.parse("http://example.com/non-ogp")
  91   end
  92
  93   test "parses ogp" do
  94     assert Parser.parse("http://example.com/ogp") ==
  95              {:ok,
  96               %{
  97                 "image" => "http://ia.media-imdb.com/images/rock.jpg",
  98                 "title" => "The Rock",
  99                 "description" =>
 100                   "Directed by Michael Bay. With Sean Connery, Nicolas Cage, Ed Harris, John Spencer.",
 101                 "type" => "video.movie",
 102                 "url" => "http://example.com/ogp"
 103               }}
 104   end
 105
 106   test "falls back to <title> when ogp:title is missing" do
 107     assert Parser.parse("http://example.com/ogp-missing-title") ==
 108              {:ok,
 109               %{
 110                 "image" => "http://ia.media-imdb.com/images/rock.jpg",
 111                 "title" => "The Rock (1996)",
 112                 "description" =>
 113                   "Directed by Michael Bay. With Sean Connery, Nicolas Cage, Ed Harris, John Spencer.",
 114                 "type" => "video.movie",
 115                 "url" => "http://example.com/ogp-missing-title"
 116               }}
 117   end
 118
 119   test "parses twitter card" do
 120     assert Parser.parse("http://example.com/twitter-card") ==
 121              {:ok,
 122               %{
 123                 "card" => "summary",
 124                 "site" => "@flickr",
 125                 "image" => "https://farm6.staticflickr.com/5510/14338202952_93595258ff_z.jpg",
 126                 "title" => "Small Island Developing States Photo Submission",
 127                 "description" => "View the album on Flickr.",
 128                 "url" => "http://example.com/twitter-card"
 129               }}
 130   end
 131
 132   test "parses OEmbed and filters HTML tags" do
 133     assert Parser.parse("http://example.com/oembed") ==
 134              {:ok,
 135               %{
 136                 "author_name" => "\u202E\u202D\u202Cbees\u202C",
 137                 "author_url" => "https://www.flickr.com/photos/bees/",
 138                 "cache_age" => 3600,
 139                 "flickr_type" => "photo",
 140                 "height" => "768",
 141                 "html" =>
 142                   "<a href=\"https://www.flickr.com/photos/bees/2362225867/\" title=\"Bacon Lollys by \u202E\u202D\u202Cbees\u202C, on Flickr\"><img src=\"https://farm4.staticflickr.com/3040/2362225867_4a87ab8baf_b.jpg\" width=\"1024\" height=\"768\" alt=\"Bacon Lollys\"/></a>",
 143                 "license" => "All Rights Reserved",
 144                 "license_id" => 0,
 145                 "provider_name" => "Flickr",
 146                 "provider_url" => "https://www.flickr.com/",
 147                 "thumbnail_height" => 150,
 148                 "thumbnail_url" =>
 149                   "https://farm4.staticflickr.com/3040/2362225867_4a87ab8baf_q.jpg",
 150                 "thumbnail_width" => 150,
 151                 "title" => "Bacon Lollys",
 152                 "type" => "photo",
 153                 "url" => "http://example.com/oembed",
 154                 "version" => "1.0",
 155                 "web_page" => "https://www.flickr.com/photos/bees/2362225867/",
 156                 "web_page_short_url" => "https://flic.kr/p/4AK2sc",
 157                 "width" => "1024"
 158               }}
 159   end
 160
 161   test "rejects invalid OGP data" do
 162     assert {:error, _} = Parser.parse("http://example.com/malformed")
 163   end
 164
 165   test "returns error if getting page was not successful" do
 166     assert {:error, :overload} = Parser.parse("http://example.com/error")
 167   end
 168
 169   test "does a HEAD request to check if the body is too large" do
 170     assert {:error, :body_too_large} = Parser.parse("http://example.com/huge-page")
 171   end
 172
 173   test "does a HEAD request to check if the body is html" do
 174     assert {:error, {:content_type, _}} = Parser.parse("http://example.com/pdf-file")
 175   end
 176 end