p2: widen document fence for space and zero-width

Strip U+200B–U+200D, U+2060, U+FEFF before fencing. Match (?i)<\s*/?\s*document so </ document> cannot sit outside the frame.
2026-09-23 00:09:14 -07:00
parent ff87a04f94
commit a992216ec0
2 changed files with 17 additions and 2 deletions
@@ -577,11 +577,15 @@ func min(a, b int) int {
 	return b
 }

-var documentTag = regexp.MustCompile(`(?i)</?document`)
+var (
+	documentTag = regexp.MustCompile(`(?i)<\s*/?\s*document`)
+	zwChars     = regexp.MustCompile("[\u200b\u200c\u200d\u2060\ufeff]")
+)

 func fenceDocument(s string) string {
+	s = zwChars.ReplaceAllString(s, "")
 	return documentTag.ReplaceAllStringFunc(s, func(m string) string {
-		if len(m) >= 2 && m[1] == '/' {
+		if strings.Contains(m, "/") {
 			return "&lt;/document"
 		}
 		return "&lt;document"