aboutsummaryrefslogtreecommitdiff
path: root/test/pleroma/web/rich_media/parser_test.exs
blob: 3fcb5c8089b7da80d887ab05e45eb98f06052bcd (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
# Pleroma: A lightweight social networking server
# Copyright © 2017-2022 Pleroma Authors <https://pleroma.social/>
# SPDX-License-Identifier: AGPL-3.0-only

defmodule Pleroma.Web.RichMedia.ParserTest do
  use Pleroma.DataCase

  alias Pleroma.Web.RichMedia.Parser

  import Tesla.Mock

  setup do
    mock_global(fn env -> apply(HttpRequestMock, :request, [env]) end)
  end

  test "returns error when no metadata present" do
    assert {:error, _} = Parser.parse("https://example.com/empty")
  end

  test "doesn't just add a title" do
    assert {:error, {:invalid_metadata, _}} = Parser.parse("https://example.com/non-ogp")
  end

  test "parses ogp" do
    assert Parser.parse("https://example.com/ogp") ==
             {:ok,
              %{
                "image" => "http://ia.media-imdb.com/images/rock.jpg",
                "title" => "The Rock",
                "description" =>
                  "Directed by Michael Bay. With Sean Connery, Nicolas Cage, Ed Harris, John Spencer.",
                "type" => "video.movie",
                "url" => "https://example.com/ogp"
              }}
  end

  test "falls back to <title> when ogp:title is missing" do
    assert Parser.parse("https://example.com/ogp-missing-title") ==
             {:ok,
              %{
                "image" => "http://ia.media-imdb.com/images/rock.jpg",
                "title" => "The Rock (1996)",
                "description" =>
                  "Directed by Michael Bay. With Sean Connery, Nicolas Cage, Ed Harris, John Spencer.",
                "type" => "video.movie",
                "url" => "https://example.com/ogp-missing-title"
              }}
  end

  test "parses twitter card" do
    assert Parser.parse("https://example.com/twitter-card") ==
             {:ok,
              %{
                "card" => "summary",
                "site" => "@flickr",
                "image" => "https://farm6.staticflickr.com/5510/14338202952_93595258ff_z.jpg",
                "title" => "Small Island Developing States Photo Submission",
                "description" => "View the album on Flickr.",
                "url" => "https://example.com/twitter-card"
              }}
  end

  test "parses OEmbed and filters HTML tags" do
    assert Parser.parse("https://example.com/oembed") ==
             {:ok,
              %{
                "author_name" => "\u202E\u202D\u202Cbees\u202C",
                "author_url" => "https://www.flickr.com/photos/bees/",
                "cache_age" => 3600,
                "flickr_type" => "photo",
                "height" => "768",
                "html" =>
                  "<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>",
                "license" => "All Rights Reserved",
                "license_id" => 0,
                "provider_name" => "Flickr",
                "provider_url" => "https://www.flickr.com/",
                "thumbnail_height" => 150,
                "thumbnail_url" =>
                  "https://farm4.staticflickr.com/3040/2362225867_4a87ab8baf_q.jpg",
                "thumbnail_width" => 150,
                "title" => "Bacon Lollys",
                "type" => "photo",
                "url" => "https://example.com/oembed",
                "version" => "1.0",
                "web_page" => "https://www.flickr.com/photos/bees/2362225867/",
                "web_page_short_url" => "https://flic.kr/p/4AK2sc",
                "width" => "1024"
              }}
  end

  test "rejects invalid OGP data" do
    assert {:error, _} = Parser.parse("https://example.com/malformed")
  end

  test "returns error if getting page was not successful" do
    assert {:error, :overload} = Parser.parse("https://example.com/error")
  end

  test "does a HEAD request to check if the body is too large" do
    assert {:error, :body_too_large} = Parser.parse("https://example.com/huge-page")
  end

  test "does a HEAD request to check if the body is html" do
    assert {:error, {:content_type, _}} = Parser.parse("https://example.com/pdf-file")
  end

  test "refuses to crawl incomplete URLs" do
    url = "example.com/ogp"
    assert :error == Parser.parse(url)
  end

  test "refuses to crawl malformed URLs" do
    url = "example.com[]/ogp"
    assert :error == Parser.parse(url)
  end

  test "refuses to crawl URLs of private network from posts" do
    [
      "http://127.0.0.1:4000/notice/9kCP7VNyPJXFOXDrgO",
      "https://10.111.10.1/notice/9kCP7V",
      "https://172.16.32.40/notice/9kCP7V",
      "https://192.168.10.40/notice/9kCP7V",
      "https://pleroma.local/notice/9kCP7V"
    ]
    |> Enum.each(fn url ->
      assert :error == Parser.parse(url)
    end)
  end
end