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
|
package org.terst.feedreader.data
import org.junit.Assert.assertEquals
import org.junit.Assert.assertNull
import org.junit.Test
/**
* Finding the feed when what you were given is a site.
*
* Reported live: "Can't subscribe to https://heathercoxrichardson.substack.com/". Pasting a
* site's home page was the only thing to hand -- a site does not advertise its feed URL
* anywhere a reader can see, it advertises it in a <link rel="alternate"> that every other
* reader looks for and this one did not.
*/
class FeedDiscoveryTest {
/** Verbatim from the reported page, 2026-10-21. */
private val substackHead =
"""<!doctype html><html><head><title>Letters from an American</title>""" +
"""<link rel="alternate" type="application/rss+xml" href="/feed" """ +
"""title="Letters from an American"/></head><body>...</body></html>"""
@Test
fun `finds the feed a Substack home page advertises, resolved against the site`() {
assertEquals(
"https://heathercoxrichardson.substack.com/feed",
FeedDiscovery.findFeedUrl(substackHead, "https://heathercoxrichardson.substack.com/")
)
}
@Test
fun `finds an Atom feed too`() {
val html = """<link rel="alternate" type="application/atom+xml" href="/atom.xml">"""
assertEquals("https://example.com/atom.xml", FeedDiscovery.findFeedUrl(html, "https://example.com/"))
}
@Test
fun `keeps an absolute href as it stands`() {
val html = """<link rel="alternate" type="application/rss+xml" href="https://feeds.example.net/x.xml">"""
assertEquals("https://feeds.example.net/x.xml", FeedDiscovery.findFeedUrl(html, "https://example.com/blog/"))
}
@Test
fun `resolves a relative href against the page, not the site root`() {
val html = """<link rel="alternate" type="application/rss+xml" href="feed.xml">"""
assertEquals("https://example.com/blog/feed.xml", FeedDiscovery.findFeedUrl(html, "https://example.com/blog/"))
}
@Test
fun `copes with the attributes in any order and single quotes`() {
val html = """<link type='application/rss+xml' href='/rss' rel='alternate'>"""
assertEquals("https://example.com/rss", FeedDiscovery.findFeedUrl(html, "https://example.com"))
}
@Test
fun `prefers the first feed when a page advertises several`() {
val html =
"""<link rel="alternate" type="application/rss+xml" href="/feed" title="Posts">""" +
"""<link rel="alternate" type="application/rss+xml" href="/comments/feed" title="Comments">"""
assertEquals("https://example.com/feed", FeedDiscovery.findFeedUrl(html, "https://example.com/"))
}
@Test
fun `ignores an alternate link that is not a feed`() {
val html =
"""<link rel="alternate" hreflang="fr" href="/fr/">""" +
"""<link rel="alternate" type="application/json" href="/feed.json">"""
assertNull(FeedDiscovery.findFeedUrl(html, "https://example.com/"))
}
@Test
fun `a page with no feed at all reports nothing rather than guessing a path`() {
assertNull(FeedDiscovery.findFeedUrl("<html><head></head><body>hi</body></html>", "https://example.com/"))
}
@Test
fun `an http feed link is upgraded, since the app cannot fetch cleartext`() {
val html = """<link rel="alternate" type="application/rss+xml" href="http://example.com/feed">"""
assertEquals("https://example.com/feed", FeedDiscovery.findFeedUrl(html, "https://example.com/"))
}
@Test
fun `xml declaration means this was already a feed, so there is nothing to discover`() {
assertNull(FeedDiscovery.findFeedUrl("<?xml version=\"1.0\"?><rss><channel></channel></rss>", "https://x/f"))
}
}
|
