处理AI胡乱生成的乱摊子

vendor/golang.org/x/net/html/doc.go

@@ -104,7 +104,7 @@ tokenization, and tokenization and tree construction stages of the WHATWG HTML
 parsing specification respectively. While the tokenizer parses and normalizes
 individual HTML tokens, only the parser constructs the DOM tree from the
 tokenized HTML, as described in the tree construction stage of the
-specification, dynamically modifying or extending the docuemnt's DOM tree.
+specification, dynamically modifying or extending the document's DOM tree.
 
 If your use case requires semantically well-formed HTML documents, as defined by
 the WHATWG specification, the parser should be used rather than the tokenizer.

vendor/golang.org/x/net/html/render.go

@@ -194,9 +194,8 @@ func render1(w writer, n *Node) error {
 		}
 	}
 
-	// Render any child nodes.
-	switch n.Data {
-	case "iframe", "noembed", "noframes", "noscript", "plaintext", "script", "style", "xmp":
+	// Render any child nodes
+	if childTextNodesAreLiteral(n) {
 		for c := n.FirstChild; c != nil; c = c.NextSibling {
 			if c.Type == TextNode {
 				if _, err := w.WriteString(c.Data); err != nil {
@@ -213,7 +212,7 @@ func render1(w writer, n *Node) error {
 			// last element in the file, with no closing tag.
 			return plaintextAbort
 		}
-	default:
+	} else {
 		for c := n.FirstChild; c != nil; c = c.NextSibling {
 			if err := render1(w, c); err != nil {
 				return err
@@ -231,6 +230,27 @@ func render1(w writer, n *Node) error {
 	return w.WriteByte('>')
 }
 
+func childTextNodesAreLiteral(n *Node) bool {
+	// Per WHATWG HTML 13.3, if the parent of the current node is a style,
+	// script, xmp, iframe, noembed, noframes, or plaintext element, and the
+	// current node is a text node, append the value of the node's data
+	// literally. The specification is not explicit about it, but we only
+	// enforce this if we are in the HTML namespace (i.e. when the namespace is
+	// "").
+	// NOTE: we also always include noscript elements, although the
+	// specification states that they should only be rendered as such if
+	// scripting is enabled for the node (which is not something we track).
+	if n.Namespace != "" {
+		return false
+	}
+	switch n.Data {
+	case "iframe", "noembed", "noframes", "noscript", "plaintext", "script", "style", "xmp":
+		return true
+	default:
+		return false
+	}
+}
+
 // writeQuoted writes s to w surrounded by quotes. Normally it will use double
 // quotes, but if s contains a double quote, it will use single quotes.
 // It is used for writing the identifiers in a doctype declaration.

vendor/golang.org/x/net/html/token.go

@@ -910,10 +910,16 @@ func (z *Tokenizer) readTagAttrKey() {
 			return
 		}
 		switch c {
-		case ' ', '\n', '\r', '\t', '\f', '/':
-			z.pendingAttr[0].end = z.raw.end - 1
-			return
-		case '=', '>':
+		case '=':
+			if z.pendingAttr[0].start+1 == z.raw.end {
+				// WHATWG 13.2.5.32, if we see an equals sign before the attribute name
+				// begins, we treat it as a character in the attribute name and continue.
+				continue
+			}
+			fallthrough
+		case ' ', '\n', '\r', '\t', '\f', '/', '>':
+			// WHATWG 13.2.5.33 Attribute name state
+			// We need to reconsume the char in the after attribute name state to support the / character
 			z.raw.end--
 			z.pendingAttr[0].end = z.raw.end
 			return
@@ -932,6 +938,11 @@ func (z *Tokenizer) readTagAttrVal() {
 	if z.err != nil {
 		return
 	}
+	if c == '/' {
+		// WHATWG 13.2.5.34 After attribute name state
+		// U+002F SOLIDUS (/) - Switch to the self-closing start tag state.
+		return
+	}
 	if c != '=' {
 		z.raw.end--
 		return