github-mirror/discourse
2
0
Fork 0
mirror of https://github.com/discourse/discourse.git synced 2025-06-01 01:55:46 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

DEV: Apply syntax_tree formatting to spec/*

Browse Source
This commit is contained in:
David Taylor
2023-01-09 11:18:21 +00:00
parent 0cf6421716
commit cb932d6ee1
907 changed files with 58693 additions and 45909 deletions
Download Patch File Download Diff File Expand all files Collapse all files

159
spec/lib/retrieve_title_spec.rb
View File

@ -3,52 +3,45 @@
RSpec.describe RetrieveTitle do
describe ".extract_title" do
it "will extract the value from the title tag" do
title = RetrieveTitle.extract_title(
"<html><title>My Cool Title</title></html>"
)
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>"
)
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
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
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
title = RetrieveTitle.extract_title(<<~HTML)
<html>
<title>YouTube</title>
<script>document.title = "Video Title";</script>
</html>
HTML
)
expect(title).to eq("Video Title")
end
@ -67,56 +60,85 @@ RSpec.describe RetrieveTitle do
describe ".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>")
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')
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"' }
)
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 ’’’")
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' }
)
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")
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, "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: {})
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')
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, "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: {})
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
@ -124,25 +146,40 @@ RSpec.describe RetrieveTitle do
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, "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://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: {})
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" }
)
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
@ -172,11 +209,15 @@ RSpec.describe RetrieveTitle do
end
end
describe '.fetch_title' do
describe ".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: {})
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)
@ -184,8 +225,12 @@ RSpec.describe RetrieveTitle do
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: {})
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")