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

This commit is contained in:
tobi 2025-03-06 15:36:58 +01:00
commit 22ce924129
47 changed files with 947 additions and 553 deletions

View file

@ -113,7 +113,7 @@ func normalizeContent(rawContent interface{}) string {
//
// TODO: sanitize differently based on mediaType.
// https://www.w3.org/TR/activitystreams-vocabulary/#dfn-mediatype
content = text.SanitizeToHTML(content)
content = text.SanitizeHTML(content)
content = text.MinifyHTML(content)
return content
}
@ -248,7 +248,7 @@ func NormalizeIncomingSummary(item WithSummary, rawJSON map[string]interface{})
// Summary should be HTML encoded:
// https://www.w3.org/TR/activitystreams-vocabulary/#dfn-summary
summary = text.SanitizeToHTML(summary)
summary = text.SanitizeHTML(summary)
summary = text.MinifyHTML(summary)
// Set normalized summary property from the raw string; this
@ -339,7 +339,7 @@ func NormalizeIncomingName(item WithName, rawJSON map[string]interface{}) {
//
// todo: We probably want to update this to allow
// *escaped* HTML markup, but for now just nuke it.
name = text.SanitizeToPlaintext(name)
name = text.RemoveHTML(name)
// Set normalized name property from the raw string; this
// will replace any existing name property on the item.
@ -369,7 +369,7 @@ func NormalizeIncomingValue(item WithValue, rawJSON map[string]interface{}) {
// Value often contains links or
// mentions or other little snippets.
// Sanitize to HTML to allow these.
value = text.SanitizeToHTML(value)
value = text.SanitizeHTML(value)
// Set normalized name property from the raw string; this
// will replace any existing value property on the item.