oss/miniflux-v2
oss/miniflux-v2
1
0
Fork 0
mirror of https://github.com/miniflux/v2.git synced 2025-07-22 17:18:37 +00:00
Code Wiki Activity

refactor(readability): various improvements and optimizations

Browse source 
- Replace a completely overkill regex
- Use `.Remove()` instead of a hand-rolled loop
- Use a strings.Builder instead of a bytes.NewBufferString
- Replace a call to Fprintf with string concatenation, as the latter are much
  faster
- Remove a superfluous cast
- Delay some computations
- Add some tests
This commit is contained in:
Julien Voisin 2024-12-13 04:41:56 +00:00 • committed by GitHub
parent 113abeea59
commit 6ad5ad0bb2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 84 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

61
internal/reader/readability/readability_test.go
View file

@ -100,3 +100,64 @@ func TestWithoutBaseURL(t *testing.T) {
t.Errorf(`Unexpected base URL, got %q instead of ""`, baseURL)
}
}
func TestRemoveStyleScript(t *testing.T) {
html := `
<html>
<head>
<title>Test</title>
<script src="tololo.js"></script>
</head>
<body>
<script src="tololo.js"></script>
<style>
h1 {color:red;}
p {color:blue;}
</style>
<article>Some content</article>
</body>
</html>`
want := `<div><div><article>Somecontent</article></div></div>`
_, content, err := ExtractContent(strings.NewReader(html))
if err != nil {
t.Fatal(err)
}
content = strings.ReplaceAll(content, "\n", "")
content = strings.ReplaceAll(content, " ", "")
content = strings.ReplaceAll(content, "\t", "")
if content != want {
t.Errorf(`Invalid content, got %s instead of %s`, content, want)
}
}
func TestRemoveBlacklist(t *testing.T) {
html := `
<html>
<head>
<title>Test</title>
</head>
<body>
<article class="super-ad">Some content</article>
<article class="g-plus-crap">Some other thing</article>
<article class="stuff popupbody">And more</article>
<article class="legit">Valid!</article>
</body>
</html>`
want := `<div><div><articleclass="legit">Valid!</article></div></div>`
_, content, err := ExtractContent(strings.NewReader(html))
if err != nil {
t.Fatal(err)
}
content = strings.ReplaceAll(content, "\n", "")
content = strings.ReplaceAll(content, " ", "")
content = strings.ReplaceAll(content, "\t", "")
if content != want {
t.Errorf(`Invalid content, got %s instead of %s`, content, want)
}
}