[feature] Parse content warning to HTML, serialize via client API as plaintext (#3876)

* [feature] Parse content warning as HTML, serialize via API to plaintext

* tidy up some cruft

* whoops

* oops

* i'm da joker baybee

* clemency muy lorde

* rename some of the text functions for clarity

* jiggle the opts

* fiddle de deee

* hopefully the last test fix i ever have to do in my beautiful life
This commit is contained in:
tobi
2025-03-07 15:04:34 +01:00
committed by GitHub
parent 424f62dd70
commit d8113c11e4
48 changed files with 985 additions and 635 deletions

View File

@@ -36,95 +36,18 @@ type SanitizeTestSuite struct {
}
func (suite *SanitizeTestSuite) TestSanitizeOutgoing() {
s := text.SanitizeToHTML(sanitizeOutgoing)
s := text.SanitizeHTML(sanitizeOutgoing)
suite.Equal(sanitizedOutgoing, s)
}
func (suite *SanitizeTestSuite) TestSanitizeHTML() {
s := text.SanitizeToHTML(sanitizeHTML)
s := text.SanitizeHTML(sanitizeHTML)
suite.Equal(sanitizedHTML, s)
}
func (suite *SanitizeTestSuite) TestSanitizeCaption1() {
dodgyCaption := "<script>console.log('haha!')</script>this is just a normal caption ;)"
sanitized := text.SanitizeToPlaintext(dodgyCaption)
suite.Equal("this is just a normal caption ;)", sanitized)
}
func (suite *SanitizeTestSuite) TestSanitizeCaption2() {
dodgyCaption := "<em>here's a LOUD caption</em>"
sanitized := text.SanitizeToPlaintext(dodgyCaption)
suite.Equal("here's a LOUD caption", sanitized)
}
func (suite *SanitizeTestSuite) TestSanitizeCaption3() {
dodgyCaption := ""
sanitized := text.SanitizeToPlaintext(dodgyCaption)
suite.Equal("", sanitized)
}
func (suite *SanitizeTestSuite) TestSanitizeCaption4() {
dodgyCaption := `
here is
a multi line
caption
with some newlines
`
sanitized := text.SanitizeToPlaintext(dodgyCaption)
suite.Equal("here is\na multi line\ncaption\nwith some newlines", sanitized)
}
func (suite *SanitizeTestSuite) TestSanitizeCaption5() {
// html-escaped: "<script>console.log('aha!')</script> hello world"
dodgyCaption := `&lt;script&gt;console.log(&apos;aha!&apos;)&lt;/script&gt; hello world`
sanitized := text.SanitizeToPlaintext(dodgyCaption)
suite.Equal("hello world", sanitized)
}
func (suite *SanitizeTestSuite) TestSanitizeCaption6() {
// html-encoded: "<script>console.log('aha!')</script> hello world"
dodgyCaption := `&lt;&#115;&#99;&#114;&#105;&#112;&#116;&gt;&#99;&#111;&#110;&#115;&#111;&#108;&#101;&period;&#108;&#111;&#103;&lpar;&apos;&#97;&#104;&#97;&excl;&apos;&rpar;&lt;&sol;&#115;&#99;&#114;&#105;&#112;&#116;&gt;&#32;&#104;&#101;&#108;&#108;&#111;&#32;&#119;&#111;&#114;&#108;&#100;`
sanitized := text.SanitizeToPlaintext(dodgyCaption)
suite.Equal("hello world", sanitized)
}
func (suite *SanitizeTestSuite) TestSanitizeCustomCSS() {
customCSS := `.toot .username {
color: var(--link_fg);
line-height: 2rem;
margin-top: -0.5rem;
align-self: start;
white-space: nowrap;
overflow: hidden;
text-overflow: ellipsis;
}`
sanitized := text.SanitizeToPlaintext(customCSS)
suite.Equal(customCSS, sanitized) // should be the same as it was before
}
func (suite *SanitizeTestSuite) TestSanitizeNaughtyCustomCSS1() {
// try to break out of <style> into <head> and change the document title
customCSS := "</style><title>pee pee poo poo</title><style>"
sanitized := text.SanitizeToPlaintext(customCSS)
suite.Empty(sanitized)
}
func (suite *SanitizeTestSuite) TestSanitizeNaughtyCustomCSS2() {
// try to break out of <style> into <head> and change the document title
customCSS := "pee pee poo poo</style><title></title><style>"
sanitized := text.SanitizeToPlaintext(customCSS)
suite.Equal("pee pee poo poo", sanitized)
}
func (suite *SanitizeTestSuite) TestSanitizeInlineImg() {
withInlineImg := "<p>Here's an inline image: <img class=\"fixed-size-img svelte-uci8eb\" aria-hidden=\"false\" alt=\"A black-and-white photo of an Oblique Strategy card. The card reads: 'Define an area as 'safe' and use it as an anchor'.\" title=\"A black-and-white photo of an Oblique Strategy card. The card reads: 'Define an area as 'safe' and use it as an anchor'.\" width=\"0\" height=\"0\" src=\"https://example.org/fileserver/01H7J83147QMCE17C0RS9P10Y9/attachment/small/01H7J8365XXRTCP6CAMGEM49ZE.jpg\" style=\"object-position: 50% 50%;\"></p>"
sanitized := text.SanitizeToHTML(withInlineImg)
sanitized := text.SanitizeHTML(withInlineImg)
suite.Equal(`<p>Here&#39;s an inline image: </p>`, sanitized)
}