mirror of
https://github.com/discourse/discourse.git
synced 2024-12-18 13:23:52 +08:00
558e9dd310
* FIX: Inline onebox should use encoding from Content-Type header when present * Use Regexp.last_match(1) Signed-off-by: OsamaSayegh <asooomaasoooma90@gmail.com>
94 lines
2.8 KiB
Ruby
94 lines
2.8 KiB
Ruby
# frozen_string_literal: true
|
||
|
||
require 'rails_helper'
|
||
|
||
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 from an 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
|
||
end
|
||
end
|