logo

news_parse_ex

news_parse_ex_test.exs (6581B)

    

  1. # NewsParseEx: RSS/Atom parser
  2. # Copyright © 2022-2023 Haelwenn (lanodan) Monnier <contact+news_parse_ex@hacktivis.me>
  3. # SPDX-License-Identifier: AGPL-3.0-only
  5. defmodule NewsParseExTest do
  6.   use ExUnit.Case, async: true
  8.   alias NewsParseEx.XML
  10.   doctest NewsParseEx
  12.   describe "Parses Atom Feed Document" do
  13.     test "basic Atom feed" do
  14.       feed = ~s[<?xml version="1.0" encoding="utf-8"?>
  15. <feed xmlns="http://www.w3.org/2005/Atom">
  16. 	<title>Test Title</title>
  17. 	<id>https://example.org/feed/</id>
  18. 	<updated>2021-11-01T16:09:55Z</updated>
  19. </feed>]
  21.       {:ok, parsed} = NewsParseEx.parse(feed)
  22.       assert(parsed.title == "Test Title")
  23.       assert(parsed.description == nil)
  24.       assert(parsed.id == "https://example.org/feed/")
  25.       assert(parsed.last_update == ~U[2021-11-01 16:09:55Z])
  26.       assert(parsed.entries == [])
  27.     end
  29.     test "Gitlab atom feed" do
  30.       feed = File.read!("test/fixtures/gitlab/wlroots-2022-12-27.atom")
  32.       {:ok, parsed} = NewsParseEx.parse(feed)
  33.       assert(parsed.title == "wlroots tags")
  34.       assert(parsed.description == nil)
  35.       assert(parsed.id == "https://gitlab.freedesktop.org/wlroots/wlroots/-/tags")
  36.       assert(parsed.last_update == ~U[2021-11-01T16:09:55Z])
  38.       assert(length(parsed.entries) == 20)
  40.       entry_0 = Enum.at(parsed.entries, 0)
  42.       assert(
  43.         Map.get(entry_0, :id) == "https://gitlab.freedesktop.org/wlroots/wlroots/-/tags/0.16.1"
  44.       )
  46.       assert(Map.get(entry_0, :description) |> String.split("\n") |> length == 37)
  48.       assert(
  49.         Map.get(entry_0, :link) == "https://gitlab.freedesktop.org/wlroots/wlroots/-/tags/0.16.1"
  50.       )
  52.       assert(Map.get(entry_0, :updated) == ~U[2022-12-25T15:56:39Z])
  53.       assert(Map.get(entry_0, :published) == nil)
  54.       assert(Map.get(entry_0, :title) == "0.16.1")
  55.     end
  57.     test "RFC4287 brief, single-entry Atom Feed Document" do
  58.       feed = File.read!("test/fixtures/rfc4287/brief_single_entry.atom")
  60.       {:ok, parsed} = NewsParseEx.parse(feed)
  61.       assert(parsed.title == "Example Feed")
  62.       assert(parsed.description == nil)
  63.       assert(parsed.id == "urn:uuid:60a76c80-d399-11d9-b93C-0003939e0af6")
  64.       assert(parsed.last_update == ~U[2003-12-13T18:30:02Z])
  66.       assert(
  67.         parsed.entries == [
  68.           %{
  69.             id: "urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a",
  70.             description: "Some text.",
  71.             link: "http://example.org/2003/12/13/atom03",
  72.             updated: ~U[2003-12-13T18:30:02Z],
  73.             title: "Atom-Powered Robots Run Amok"
  74.           }
  75.         ]
  76.       )
  77.     end
  79.     test "RFC4287 more extensive, single-entry Atom Feed Document" do
  80.       feed = File.read!("test/fixtures/rfc4287/extensive_single_entry.atom")
  82.       {:ok, parsed} = NewsParseEx.parse(feed)
  83.       assert(parsed.title == "dive into mark")
  84.       assert(parsed.description == nil)
  85.       assert(parsed.id == "tag:example.org,2003:3")
  86.       assert(parsed.last_update == ~U[2005-07-31T12:29:29Z])
  88.       # 2003-12-13 08:29:29-04:00
  89.       published = %DateTime{
  90.         year: 2003,
  91.         month: 12,
  92.         day: 13,
  93.         hour: 08,
  94.         minute: 29,
  95.         second: 29,
  96.         std_offset: 0,
  97.         utc_offset: -4 * 60 * 60,
  98.         time_zone: "Etc/UTC-4",
  99.         zone_abbr: "-04"
  100.       }
  102.       assert(
  103.         [
  104.           %{
  105.             title: "Atom draft-07 snapshot",
  106.             link: "http://example.org/2005/04/02/atom",
  107.             id: "tag:example.org,2003:3.2397",
  108.             updated: ~U[2005-07-31 12:29:29Z],
  109.             published: ^published,
  110.             content: {:xhtml, _content},
  111.             description: ""
  112.           }
  113.         ] = parsed.entries
  114.       )
  115.     end
  116.   end
  118.   describe "Parses Atom title" do
  119.     setup do
  120.       %{feed: ~s[<?xml version="1.0" encoding="utf-8"?>
  121. <feed xmlns="http://www.w3.org/2005/Atom">
  122. 	{{title}}
  123. 	<id>https://example.org/feed/</id>
  124. 	<updated>2021-11-01T16:09:55Z</updated>
  125. </feed>]}
  126.     end
  128.     test "plain text", %{feed: feed} do
  129.       {:ok, parsed} =
  130.         feed
  131.         |> String.replace("{{title}}", ~s{<title type="text">Less: &lt;</title>})
  132.         |> NewsParseEx.parse()
  134.       assert(parsed.title == "Less: <")
  135.     end
  137.     test "HTML", %{feed: feed} do
  138.       {:ok, parsed} =
  139.         feed
  140.         |> String.replace(
  141.           "{{title}}",
  142.           ~s{<title type="html">Less: &lt;em> &amp;lt; &lt;/em></title>}
  143.         )
  144.         |> NewsParseEx.parse()
  146.       assert(
  147.         parsed.title ==
  148.           {:html, [{:xmlText, [title: 2, feed: 1], 1, [], 'Less: <em> &lt; </em>', :text}]}
  149.       )
  150.     end
  152.     test "XHTML xhtml:div", %{feed: feed} do
  153.       title = ~s{<title type="xhtml" xmlns:xhtml="http://www.w3.org/1999/xhtml">
  154.   <xhtml:div>
  155.     Less: <xhtml:em> &lt; </xhtml:em>
  156.   </xhtml:div>
  157. </title>}
  159.       {:ok, parsed} =
  160.         feed
  161.         |> String.replace("{{title}}", title)
  162.         |> NewsParseEx.parse()
  164.       assert({:xhtml, [title]} = parsed.title)
  165.       assert(XML.string_from_doc(title) == "Less: \n   <")
  166.     end
  168.     test "XHTML div", %{feed: feed} do
  169.       title = ~s{<title type="xhtml" xmlns:xhtml="http://www.w3.org/1999/xhtml">
  170.   <div xmlns="http://www.w3.org/1999/xhtml">
  171.     Less: <em> &lt; </em>
  172.   </div>
  173. </title>}
  175.       {:ok, parsed} =
  176.         feed
  177.         |> String.replace("{{title}}", title)
  178.         |> NewsParseEx.parse()
  180.       assert({:xhtml, [title]} = parsed.title)
  181.       assert(XML.string_from_doc(title) == "Less: \n   <")
  182.     end
  183.   end
  185.   describe "Parses RSS Document" do
  186.     test "git.sr.ht tags" do
  187.       feed = File.read!("test/fixtures/git.sr.ht/pkgconf-2022-12-27.rss")
  189.       {:ok, parsed} = NewsParseEx.parse(feed)
  190.       assert(parsed.title == "~kaniini/pkgconf refs")
  191.       assert(parsed.description == "Git refs for ~kaniini/pkgconf")
  192.       assert(parsed.id == "https://git.sr.ht/~kaniini/pkgconf/refs")
  193.       assert(parsed.last_update == nil)
  195.       assert(length(parsed.entries) == 20)
  197.       # Sat, 30 May 2020 19:17:12 -0600
  198.       # #DateTime<2020-05-30 19:17:12-06:00 -06 Etc/UTC-6>
  199.       published = %DateTime{
  200.         year: 2020,
  201.         month: 05,
  202.         day: 30,
  203.         hour: 19,
  204.         minute: 17,
  205.         second: 12,
  206.         std_offset: 0,
  207.         utc_offset: -6 * 60 * 60,
  208.         time_zone: "Etc/UTC-6",
  209.         zone_abbr: "-06"
  210.       }
  212.       assert(
  213.         Enum.at(parsed.entries, 0) == %{
  214.           id: "https://git.sr.ht/~kaniini/pkgconf/refs/pkgconf-1.7.3",
  215.           title: "pkgconf-1.7.3",
  216.           description: "pkgconf 1.7.3.",
  217.           link: "https://git.sr.ht/~kaniini/pkgconf/refs/pkgconf-1.7.3",
  218.           published: published
  219.         }
  220.       )
  221.     end
  222.   end
  223. end