discourse/spec/lib/retrieve_title_spec.rb
Dan Ungureanu 8e9cbe9db4
FIX: Do not raise if title cannot be crawled (#16247)
If the crawled page returned an error, `FinalDestination#safe_get`
yielded `nil` for `uri` and `chunk` arguments. Another problem is that
`get` did not handle the case when `safe_get` failed and did not return
the `location` and `set_cookie` headers.
2022-03-22 20:13:27 +02:00

167 lines
5.7 KiB
Ruby
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# frozen_string_literal: true
describe RetrieveTitle do
context "extract_title" do
it "will extract the value from the title tag" do
title = RetrieveTitle.extract_title(
"<html><title>My Cool Title</title></html>"
)
expect(title).to eq("My Cool Title")
end
it "will strip whitespace" do
title = RetrieveTitle.extract_title(
"<html><title> Another Title\n\n </title></html>"
)
expect(title).to eq("Another Title")
end
it "will pick og:title if title is missing" do
title = RetrieveTitle.extract_title(<<~HTML
<html>
<meta property="og:title" content="Good Title"
</html>
HTML
)
expect(title).to eq("Good Title")
end
it "will prefer the title over the opengraph tag" do
title = RetrieveTitle.extract_title(<<~HTML
<html>
<title>Good Title</title>
<meta property="og:title" content="Bad Title"
</html>
HTML
)
expect(title).to eq("Good Title")
end
it "will parse a YouTube url from javascript" do
title = RetrieveTitle.extract_title(<<~HTML
<html>
<title>YouTube</title>
<script>document.title = "Video Title";</script>
</html>
HTML
)
expect(title).to eq("Video Title")
end
end
context "crawl" do
it "can properly extract a title from a url" do
stub_request(:get, "https://brelksdjflaskfj.com/amazing")
.to_return(status: 200, body: "<html><title>very amazing</title>")
# we still resolve the IP address for every host
IPSocket.stubs(:getaddress).returns('100.2.3.4')
expect(RetrieveTitle.crawl("https://brelksdjflaskfj.com/amazing")).to eq("very amazing")
end
it "detects and uses encoding from Content-Type header" do
stub_request(:get, "https://brelksdjflaskfj.com/amazing")
.to_return(
status: 200,
body: "<html><title>fancy apostrophes </title>".dup.force_encoding('ASCII-8BIT'),
headers: { 'Content-Type' => 'text/html; charset="utf-8"' }
)
IPSocket.stubs(:getaddress).returns('100.2.3.4')
expect(RetrieveTitle.crawl("https://brelksdjflaskfj.com/amazing")).to eq("fancy apostrophes ")
stub_request(:get, "https://brelksdjflaskfj.com/amazing")
.to_return(
status: 200,
body: "<html><title>japanese こんにちは website</title>".encode('EUC-JP').force_encoding('ASCII-8BIT'),
headers: { 'Content-Type' => 'text/html;charset=euc-jp' }
)
IPSocket.stubs(:getaddress).returns('100.2.3.4')
expect(RetrieveTitle.crawl("https://brelksdjflaskfj.com/amazing")).to eq("japanese こんにちは website")
end
it "can follow redirect" do
stub_request(:get, "http://foobar.com/amazing").
to_return(status: 301, body: "", headers: { "location" => "https://wikipedia.com/amazing" })
stub_request(:get, "https://wikipedia.com/amazing").
to_return(status: 200, body: "<html><title>very amazing</title>", headers: {})
IPSocket.stubs(:getaddress).returns('100.2.3.4')
expect(RetrieveTitle.crawl("http://foobar.com/amazing")).to eq("very amazing")
end
it "returns empty title if redirect uri is in blacklist" do
SiteSetting.blocked_onebox_domains = "wikipedia.com"
stub_request(:get, "http://foobar.com/amazing")
.to_return(status: 301, body: "", headers: { "location" => "https://wikipedia.com/amazing" })
stub_request(:get, "https://wikipedia.com/amazing")
.to_return(status: 200, body: "<html><title>very amazing</title>", headers: {})
expect(RetrieveTitle.crawl("http://foobar.com/amazing")).to eq(nil)
end
it "doesn't return title if a blocked domain is encountered anywhere in the redirect chain" do
SiteSetting.blocked_onebox_domains = "wikipedia.com"
stub_request(:get, "http://foobar.com/amazing")
.to_return(status: 301, body: "", headers: { "location" => "https://wikipedia.com/amazing" })
stub_request(:get, "https://wikipedia.com/amazing")
.to_return(status: 301, body: "", headers: { "location" => "https://cat.com/meow" })
stub_request(:get, "https://cat.com/meow")
.to_return(status: 200, body: "<html><title>very amazing</title>", headers: {})
expect(RetrieveTitle.crawl("http://foobar.com/amazing")).to be_blank
end
it "doesn't return title if the Discourse-No-Onebox header == 1" do
stub_request(:get, "https://cat.com/meow/no-onebox")
.to_return(
status: 200,
body: "<html><title>discourse stay away</title>",
headers: { "Discourse-No-Onebox" => "1" }
)
expect(RetrieveTitle.crawl("https://cat.com/meow/no-onebox")).to be_blank
end
it "doesn't return a title if response is unsuccessful" do
stub_request(:get, "https://example.com").to_return(status: 404, body: "")
expect(RetrieveTitle.crawl("https://example.com")).to eq(nil)
end
end
context 'fetch_title' do
it "does not parse broken title tag" do
# webmock does not do chunks
stub_request(:get, "https://en.wikipedia.org/wiki/Internet").
to_return(status: 200, body: "<html><head><title>Internet - Wikipedia</ti" , headers: {})
title = RetrieveTitle.fetch_title("https://en.wikipedia.org/wiki/Internet")
expect(title).to eq(nil)
end
it "can parse correct title tag" do
# webmock does not do chunks
stub_request(:get, "https://en.wikipedia.org/wiki/Internet").
to_return(status: 200, body: "<html><head><title>Internet - Wikipedia</title>" , headers: {})
title = RetrieveTitle.fetch_title("https://en.wikipedia.org/wiki/Internet")
expect(title).to eq("Internet - Wikipedia")
end
end
end