southfox/miniflux
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 1 Wiki Activity Actions
miniflux/internal/reader/subscription/finder_test.go

349 lines
10 KiB
Go
Raw Normal View History

Replace copyright header with SPDX identifier
2023-06-19 23:42:47 +02:00
// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
// SPDX-License-Identifier: Apache-2.0
Add workaround to find YouTube channel feeds YouTube doesn't expose RSS links anymore for new-style URLs.
2020-08-02 20:24:02 +02:00
package subscription
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
import (
"strings"
"testing"
)
Add workaround to find YouTube channel feeds YouTube doesn't expose RSS links anymore for new-style URLs.
2020-08-02 20:24:02 +02:00
finder: Find feed from YouTube playlist The feed from a YouTube playlist page is derived in practically the same way as a feed from a YouTube channel page.
2024-03-30 09:05:50 +01:00
func TestFindYoutubePlaylistFeed(t *testing.T) {
scenarios := map[string]string{
"https://www.youtube.com/playlist?list=PLOOwEPgFWm_NHcQd9aCi5JXWASHO_n5uR": "https://www.youtube.com/feeds/videos.xml?playlist_id=PLOOwEPgFWm_NHcQd9aCi5JXWASHO_n5uR",
"https://www.youtube.com/playlist?list=PLOOwEPgFWm_N42HlCLhqyJ0ZBWr5K1QDM": "https://www.youtube.com/feeds/videos.xml?playlist_id=PLOOwEPgFWm_N42HlCLhqyJ0ZBWr5K1QDM",
}
for websiteURL, expectedFeedURL := range scenarios {
subscriptions, localizedError := NewSubscriptionFinder(nil).FindSubscriptionsFromYouTubePlaylistPage(websiteURL)
if localizedError != nil {
t.Fatalf(`Parsing a correctly formatted YouTube playlist page should not return any error: %v`, localizedError)
}
if len(subscriptions) != 1 {
t.Fatal(`Incorrect number of subscriptions returned`)
}
if subscriptions[0].URL != expectedFeedURL {
t.Errorf(`Unexpected Feed, got %s, instead of %s`, subscriptions[0].URL, expectedFeedURL)
}
}
}
Add workaround to find YouTube channel feeds YouTube doesn't expose RSS links anymore for new-style URLs.
2020-08-02 20:24:02 +02:00
func TestFindYoutubeChannelFeed(t *testing.T) {
scenarios := map[string]string{
"https://www.youtube.com/channel/UC-Qj80avWItNRjkZ41rzHyw": "https://www.youtube.com/feeds/videos.xml?channel_id=UC-Qj80avWItNRjkZ41rzHyw",
}
for websiteURL, expectedFeedURL := range scenarios {
Refactor feed discovery and avoid an extra HTTP request if the url provided is the feed
2023-10-23 01:07:06 +02:00
subscriptions, localizedError := NewSubscriptionFinder(nil).FindSubscriptionsFromYouTubeChannelPage(websiteURL)
if localizedError != nil {
t.Fatalf(`Parsing a correctly formatted YouTube channel page should not return any error: %v`, localizedError)
}
if len(subscriptions) != 1 {
t.Fatal(`Incorrect number of subscriptions returned`)
}
if subscriptions[0].URL != expectedFeedURL {
t.Errorf(`Unexpected Feed, got %s, instead of %s`, subscriptions[0].URL, expectedFeedURL)
Add workaround to find YouTube channel feeds YouTube doesn't expose RSS links anymore for new-style URLs.
2020-08-02 20:24:02 +02:00
}
}
}
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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>`
Regression: ensure all HTML documents are encoded in UTF-8 Fixes #2196
2023-12-02 01:27:18 +01:00
subscriptions, err := NewSubscriptionFinder(nil).FindSubscriptionsFromWebPage("http://example.org/", "text/html", strings.NewReader(htmlPage))
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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>`
Regression: ensure all HTML documents are encoded in UTF-8 Fixes #2196
2023-12-02 01:27:18 +01:00
subscriptions, err := NewSubscriptionFinder(nil).FindSubscriptionsFromWebPage("http://example.org/", "text/html", strings.NewReader(htmlPage))
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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>`
Regression: ensure all HTML documents are encoded in UTF-8 Fixes #2196
2023-12-02 01:27:18 +01:00
subscriptions, err := NewSubscriptionFinder(nil).FindSubscriptionsFromWebPage("http://example.org/", "text/html", strings.NewReader(htmlPage))
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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>`
Regression: ensure all HTML documents are encoded in UTF-8 Fixes #2196
2023-12-02 01:27:18 +01:00
subscriptions, err := NewSubscriptionFinder(nil).FindSubscriptionsFromWebPage("http://example.org/", "text/html", strings.NewReader(htmlPage))
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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 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>`
Regression: ensure all HTML documents are encoded in UTF-8 Fixes #2196
2023-12-02 01:27:18 +01:00
subscriptions, err := NewSubscriptionFinder(nil).FindSubscriptionsFromWebPage("http://example.org/", "text/html", strings.NewReader(htmlPage))
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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>`
Regression: ensure all HTML documents are encoded in UTF-8 Fixes #2196
2023-12-02 01:27:18 +01:00
subscriptions, err := NewSubscriptionFinder(nil).FindSubscriptionsFromWebPage("http://example.org/", "text/html", strings.NewReader(htmlPage))
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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/feed+json" title="JSON Feed">
</head>
<body>
</body>
</html>`
Regression: ensure all HTML documents are encoded in UTF-8 Fixes #2196
2023-12-02 01:27:18 +01:00
subscriptions, err := NewSubscriptionFinder(nil).FindSubscriptionsFromWebPage("http://example.org/", "text/html", strings.NewReader(htmlPage))
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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`)
}
}
Deduplicate feed URLs when parsing HTML document during discovery process Fixes #2232
2023-12-01 22:35:24 +01:00
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>`
Regression: ensure all HTML documents are encoded in UTF-8 Fixes #2196
2023-12-02 01:27:18 +01:00
subscriptions, err := NewSubscriptionFinder(nil).FindSubscriptionsFromWebPage("http://example.org/", "text/html", strings.NewReader(htmlPage))
Deduplicate feed URLs when parsing HTML document during discovery process Fixes #2232
2023-12-01 22:35:24 +01:00
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)
}
}
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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>`
Regression: ensure all HTML documents are encoded in UTF-8 Fixes #2196
2023-12-02 01:27:18 +01:00
subscriptions, err := NewSubscriptionFinder(nil).FindSubscriptionsFromWebPage("http://example.org/", "text/html", strings.NewReader(htmlPage))
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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>`
Regression: ensure all HTML documents are encoded in UTF-8 Fixes #2196
2023-12-02 01:27:18 +01:00
subscriptions, err := NewSubscriptionFinder(nil).FindSubscriptionsFromWebPage("http://example.org/", "text/html", strings.NewReader(htmlPage))
Ignore empty link when discovering feeds
2023-02-27 02:09:50 +01:00
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`)
}
}
Reference in a new issue Copy permalink