LBP
/
miniflux_v2
镜像来自 https://github.com/miniflux/v2.git


			
				
					
						
						
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512
							// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
// SPDX-License-Identifier: Apache-2.0

package subscription

import (
	"testing"
)

func TestFindYoutubeFeed(t *testing.T) {
	type testResult struct {
		websiteURL     string
		feedURLs       []string
		discoveryError bool
	}

	scenarios := []testResult{
		// Video URL
		{
			websiteURL: "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
			feedURLs:   []string{},
		},
		// Video URL with position argument
		{
			websiteURL: "https://www.youtube.com/watch?v=dQw4w9WgXcQ&t=1",
			feedURLs:   []string{},
		},
		// Video URL with position argument
		{
			websiteURL: "https://www.youtube.com/watch?t=1&v=dQw4w9WgXcQ",
			feedURLs:   []string{},
		},
		// Channel URL
		{
			websiteURL: "https://www.youtube.com/channel/UC-Qj80avWItNRjkZ41rzHyw",
			feedURLs: []string{
				"https://www.youtube.com/feeds/videos.xml?channel_id=UC-Qj80avWItNRjkZ41rzHyw",
				"https://www.youtube.com/feeds/videos.xml?playlist_id=UULF-Qj80avWItNRjkZ41rzHyw",
				"https://www.youtube.com/feeds/videos.xml?playlist_id=UUSH-Qj80avWItNRjkZ41rzHyw",
				"https://www.youtube.com/feeds/videos.xml?playlist_id=UULV-Qj80avWItNRjkZ41rzHyw",
			},
		},
		// Channel URL with name
		{
			websiteURL: "https://www.youtube.com/@ABCDEFG",
			feedURLs:   []string{},
		},
		// Playlist URL
		{
			websiteURL: "https://www.youtube.com/playlist?list=PLOOwEPgFWm_NHcQd9aCi5JXWASHO_n5uR",
			feedURLs:   []string{"https://www.youtube.com/feeds/videos.xml?playlist_id=PLOOwEPgFWm_NHcQd9aCi5JXWASHO_n5uR"},
		},
		// Playlist URL with video ID
		{
			websiteURL: "https://www.youtube.com/watch?v=dQw4w9WgXcQ&list=PLOOwEPgFWm_N42HlCLhqyJ0ZBWr5K1QDM",
			feedURLs:   []string{"https://www.youtube.com/feeds/videos.xml?playlist_id=PLOOwEPgFWm_N42HlCLhqyJ0ZBWr5K1QDM"},
		},
		// Playlist URL with video ID and index argument
		{
			websiteURL: "https://www.youtube.com/watch?v=6IutBmRJNLk&list=PLOOwEPgFWm_NHcQd9aCi5JXWASHO_n5uR&index=4",
			feedURLs:   []string{"https://www.youtube.com/feeds/videos.xml?playlist_id=PLOOwEPgFWm_NHcQd9aCi5JXWASHO_n5uR"},
		},
		// Empty playlist ID parameter
		{
			websiteURL: "https://www.youtube.com/playlist?list=",
			feedURLs:   []string{},
		},
		// Non-Youtube URL
		{
			websiteURL: "https://www.example.com/channel/UC-Qj80avWItNRjkZ41rzHyw",
			feedURLs:   []string{},
		},
		// Invalid URL
		{
			websiteURL:     "https://example|org/",
			feedURLs:       []string{},
			discoveryError: true,
		},
	}

	for _, scenario := range scenarios {
		subscriptions, localizedError := NewSubscriptionFinder(nil).findSubscriptionsFromYouTube(scenario.websiteURL)
		if scenario.discoveryError {
			if localizedError == nil {
				t.Fatalf(`Parsing an invalid URL should return an error`)
			}
		}

		if len(scenario.feedURLs) == 0 {
			if len(subscriptions) > 0 {
				t.Fatalf(`Parsing an invalid URL should not return any subscription: %q -> %v`, scenario.websiteURL, subscriptions)
			}
		} else {
			if localizedError != nil {
				t.Fatalf(`Parsing a correctly formatted YouTube playlist or channel page should not return any error: %v`, localizedError)
			}

			if len(subscriptions) != len(scenario.feedURLs) {
				t.Fatalf(`Incorrect number of subscriptions returned, expected %d, got %d`, len(scenario.feedURLs), len(subscriptions))
			}

			for i := range scenario.feedURLs {
				if subscriptions[i].URL != scenario.feedURLs[i] {
					t.Errorf(`Unexpected feed, got %s, instead of %s`, subscriptions[i].URL, scenario.feedURLs[i])
				}
			}
		}
	}
}

func TestParseWebPageWithRssFeed(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link href="http://example.org/rss" rel="alternate" type="application/rss+xml" title="Some Title">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 1 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}

	if subscriptions[0].Title != "Some Title" {
		t.Errorf(`Incorrect subscription title: %q`, subscriptions[0].Title)
	}

	if subscriptions[0].URL != "http://example.org/rss" {
		t.Errorf(`Incorrect subscription URL: %q`, subscriptions[0].URL)
	}

	if subscriptions[0].Type != "rss" {
		t.Errorf(`Incorrect subscription type: %q`, subscriptions[0].Type)
	}
}

func TestParseWebPageWithAtomFeed(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link href="http://example.org/atom.xml" rel="alternate" type="application/atom+xml" title="Some Title">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 1 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}

	if subscriptions[0].Title != "Some Title" {
		t.Errorf(`Incorrect subscription title: %q`, subscriptions[0].Title)
	}

	if subscriptions[0].URL != "http://example.org/atom.xml" {
		t.Errorf(`Incorrect subscription URL: %q`, subscriptions[0].URL)
	}

	if subscriptions[0].Type != "atom" {
		t.Errorf(`Incorrect subscription type: %q`, subscriptions[0].Type)
	}
}

func TestParseWebPageWithJSONFeed(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link href="http://example.org/feed.json" rel="alternate" type="application/feed+json" title="Some Title">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 1 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}

	if subscriptions[0].Title != "Some Title" {
		t.Errorf(`Incorrect subscription title: %q`, subscriptions[0].Title)
	}

	if subscriptions[0].URL != "http://example.org/feed.json" {
		t.Errorf(`Incorrect subscription URL: %q`, subscriptions[0].URL)
	}

	if subscriptions[0].Type != "json" {
		t.Errorf(`Incorrect subscription type: %q`, subscriptions[0].Type)
	}
}

func TestParseWebPageWithOldJSONFeedMimeType(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link href="http://example.org/feed.json" rel="alternate" type="application/json" title="Some Title">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 1 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}

	if subscriptions[0].Title != "Some Title" {
		t.Errorf(`Incorrect subscription title: %q`, subscriptions[0].Title)
	}

	if subscriptions[0].URL != "http://example.org/feed.json" {
		t.Errorf(`Incorrect subscription URL: %q`, subscriptions[0].URL)
	}

	if subscriptions[0].Type != "json" {
		t.Errorf(`Incorrect subscription type: %q`, subscriptions[0].Type)
	}
}

func TestParseWebPageWithJSONFeedWpJsonIgnored(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link rel="https://api.w.org/" href="https://example.org/wp-json/" />
			<link rel="alternate" title="JSON" type="application/json" href="https://example.org/wp-json/wp/v2/posts/123456" />
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 0 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}
}

func TestParseWebPageWithRelativeFeedURL(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link href="/feed.json" rel="alternate" type="application/feed+json" title="Some Title">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 1 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}

	if subscriptions[0].Title != "Some Title" {
		t.Errorf(`Incorrect subscription title: %q`, subscriptions[0].Title)
	}

	if subscriptions[0].URL != "http://example.org/feed.json" {
		t.Errorf(`Incorrect subscription URL: %q`, subscriptions[0].URL)
	}

	if subscriptions[0].Type != "json" {
		t.Errorf(`Incorrect subscription type: %q`, subscriptions[0].Type)
	}
}

func TestParseWebPageWithEmptyTitle(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link href="/feed.json" rel="alternate" type="application/feed+json">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 1 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}

	if subscriptions[0].Title != "http://example.org/feed.json" {
		t.Errorf(`Incorrect subscription title: %q`, subscriptions[0].Title)
	}

	if subscriptions[0].URL != "http://example.org/feed.json" {
		t.Errorf(`Incorrect subscription URL: %q`, subscriptions[0].URL)
	}

	if subscriptions[0].Type != "json" {
		t.Errorf(`Incorrect subscription type: %q`, subscriptions[0].Type)
	}
}

func TestParseWebPageWithMultipleFeeds(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link href="http://example.org/atom.xml" rel="alternate" type="application/atom+xml" title="Atom Feed">
			<link href="http://example.org/feed.json" rel="alternate" type="application/json" title="JSON Feed">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 2 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}
}

func TestParseWebPageWithDuplicatedFeeds(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link href="http://example.org/feed.xml" rel="alternate" type="application/rss+xml" title="Feed A">
			<link href="http://example.org/feed.xml" rel="alternate" type="application/rss+xml" title="Feed B">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 1 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}

	if subscriptions[0].Title != "Feed A" {
		t.Errorf(`Incorrect subscription title: %q`, subscriptions[0].Title)
	}

	if subscriptions[0].URL != "http://example.org/feed.xml" {
		t.Errorf(`Incorrect subscription URL: %q`, subscriptions[0].URL)
	}

	if subscriptions[0].Type != "rss" {
		t.Errorf(`Incorrect subscription type: %q`, subscriptions[0].Type)
	}
}

func TestParseWebPageWithEmptyFeedURL(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link href rel="alternate" type="application/feed+json" title="Some Title">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 0 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}
}

func TestParseWebPageWithNoHref(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link rel="alternate" type="application/feed+json" title="Some Title">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	subscriptions, err := NewSubscriptionFinder(nil).findSubscriptionsFromWebPage("http://example.org/", doc)
	if err != nil {
		t.Fatalf(`Parsing a correctly formatted HTML page should not return any error: %v`, err)
	}

	if len(subscriptions) != 0 {
		t.Fatal(`Incorrect number of subscriptions returned`)
	}
}

func TestFindCanonicalURL(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
			<link rel="canonical" href="https://example.org/canonical-page">
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	canonicalURL := NewSubscriptionFinder(nil).findCanonicalURL("https://example.org/page", "http://example.org", doc)
	if canonicalURL != "https://example.org/canonical-page" {
		t.Errorf(`Unexpected canonical URL, got %q, expected %q`, canonicalURL, "https://example.org/canonical-page")
	}
}

func TestFindCanonicalURLNotFound(t *testing.T) {
	htmlPage := `
	<!doctype html>
	<html>
		<head>
		</head>
		<body>
		</body>
	</html>`
	doc, shouldNeverHappenErr := parseHTMLDocument("text/html", []byte(htmlPage))
	if shouldNeverHappenErr != nil {
		t.Fatalf(`Unable to parse the HTML: %v`, shouldNeverHappenErr)
	}

	canonicalURL := NewSubscriptionFinder(nil).findCanonicalURL("https://example.org/page", "https://example.org", doc)
	if canonicalURL != "https://example.org/page" {
		t.Errorf(`Expected effective URL when canonical not found, got %q`, canonicalURL)
	}
}