Skip to content

refactor(sanitizer): use a smarter approach wrt. SanitizeHTML #3831

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jvoisin wants to merge 1 commit into
base: main
Choose a base branch
from
Open

refactor(sanitizer): use a smarter approach wrt. SanitizeHTML #3831

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 17 additions & 2 deletions internal/reader/sanitizer/sanitizer.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,6 +202,16 @@ type SanitizerOptions struct {
OpenLinksInNewTab bool
}

// lastIndex returns the index of the last matching element e present in s.
func lastIndex[T comparable](s []T, e T) int {
for i := len(s) - 1; i >= 0; i-- {
if s[i] == e {
return i
}
}
return -1
}

func SanitizeHTML(baseURL, rawHTML string, sanitizerOptions *SanitizerOptions) string {
var tagStack []string
var parentTag string
Expand Down Expand Up @@ -278,8 +288,13 @@ func SanitizeHTML(baseURL, rawHTML string, sanitizerOptions *SanitizerOptions) s
}
case html.EndTagToken:
if len(blockedStack) == 0 {
if isValidTag(tagName) && slices.Contains(tagStack, tagName) {
buffer.WriteString("</" + tagName + ">")
if isValidTag(tagName) {
// We can't use a strict push/pop queue, as we might have things like <video><source></video>
// that are valid HTML.
if idx := lastIndex(tagStack, tagName); idx != -1 {
tagStack = tagStack[:idx]
buffer.WriteString("</" + tagName + ">")
}
}
} else {
if blockedStack[len(blockedStack)-1] == tagName {
Expand Down