Skip to content

Fix serialization of entity references in attributes #13884

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.

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

Merged
merged 1 commit into from
Apr 5, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
18 changes: 13 additions & 5 deletions ext/dom/html5_serializer.c
Original file line number Diff line number Diff line change
Expand Up @@ -196,13 +196,21 @@ static zend_result dom_html5_serialize_element_start(dom_html5_serialize_context
TRY(ctx->write_string(ctx->application_data, (const char *) attr->name));
}
}

TRY(ctx->write_string_len(ctx->application_data, "=\"", strlen("=\"")));
xmlChar *content = xmlNodeGetContent((const xmlNode *) attr);
if (content != NULL) {
zend_result result = dom_html5_escape_string(ctx, (const char *) content, true);
xmlFree(content);
TRY(result);

for (xmlNodePtr child = attr->children; child != NULL; child = child->next) {
if (child->type == XML_TEXT_NODE) {
if (child->content != NULL) {
TRY(dom_html5_escape_string(ctx, (const char *) child->content, true));
}
} else if (child->type == XML_ENTITY_REF_NODE) {
TRY(ctx->write_string_len(ctx->application_data, "&", strlen("&")));
TRY(dom_html5_escape_string(ctx, (const char *) child->name, true));
TRY(ctx->write_string_len(ctx->application_data, ";", strlen(";")));
}
}

TRY(ctx->write_string_len(ctx->application_data, "\"", strlen("\"")));
}

Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
--TEST--
Serialize entity reference within attribute
--EXTENSIONS--
dom
--FILE--
<?php

$xml = DOM\XMLDocument::createFromString(<<<XML
<!DOCTYPE root [
<!ENTITY foo "foo">
]>
<root><el x="&foo;bar&foo;"/></root>
XML);

$el = $xml->documentElement->firstChild;
echo $xml->saveXML(), "\n";

$html = DOM\HTMLDocument::createEmpty();
$html->append($html->importNode($el, true));
echo $html->saveHTML(), "\n";

?>
--EXPECT--
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root [
<!ENTITY foo "foo">
]>
<root><el x="&foo;bar&foo;"/></root>
<el x="&foo;bar&foo;"></el>
28 changes: 20 additions & 8 deletions ext/dom/xml_serializer.c
Original file line number Diff line number Diff line change
Expand Up @@ -542,17 +542,32 @@ static zend_always_inline int dom_xml_serialize_text_node(xmlOutputBufferPtr out
return dom_xml_common_text_serialization(out, (const char *) text->content, false);
}

static int dom_xml_serialize_attribute_node_value(xmlOutputBufferPtr out, xmlAttrPtr attr)
{
TRY(xmlOutputBufferWriteString(out, (const char *) attr->name));
TRY(xmlOutputBufferWrite(out, strlen("=\""), "=\""));
for (xmlNodePtr child = attr->children; child != NULL; child = child->next) {
if (child->type == XML_TEXT_NODE) {
if (child->content != NULL) {
TRY(dom_xml_common_text_serialization(out, (const char *) child->content, true));
}
} else if (child->type == XML_ENTITY_REF_NODE) {
TRY(xmlOutputBufferWrite(out, strlen("&"), "&"));
TRY(dom_xml_common_text_serialization(out, (const char *) child->name, true));
TRY(xmlOutputBufferWrite(out, strlen(";"), ";"));
}
}
return xmlOutputBufferWrite(out, strlen("\""), "\"");
}

/* Spec says to do nothing, but that's inconsistent/wrong, see https://github.com/w3c/DOM-Parsing/issues/28 */
static int dom_xml_serialize_attribute_node(xmlOutputBufferPtr out, xmlNodePtr attr)
{
if (attr->ns != NULL && attr->ns->prefix != NULL) {
TRY(xmlOutputBufferWriteString(out, (const char *) attr->ns->prefix));
TRY(xmlOutputBufferWrite(out, strlen(":"), ":"));
}
TRY(xmlOutputBufferWriteString(out, (const char *) attr->name));
TRY(xmlOutputBufferWrite(out, strlen("=\""), "=\""));
TRY(dom_xml_common_text_serialization(out, (const char *) dom_get_attribute_value((xmlAttrPtr) attr), true));
return xmlOutputBufferWrite(out, strlen("\""), "\"");
return dom_xml_serialize_attribute_node_value(out, (xmlAttrPtr) attr);
}

/* https://w3c.github.io/DOM-Parsing/#dfn-xml-serializing-a-comment-node */
Expand Down Expand Up @@ -730,10 +745,7 @@ static int dom_xml_serialize_attributes(
* => N/A */

/* 3.9. Append the following strings to result, in the order listed: */
TRY(xmlOutputBufferWriteString(out, (const char *) attr->name));
TRY(xmlOutputBufferWrite(out, strlen("=\""), "=\""));
TRY(dom_xml_common_text_serialization(out, (const char *) dom_get_attribute_value(attr), true));
TRY(xmlOutputBufferWrite(out, strlen("\""), "\""));
dom_xml_serialize_attribute_node_value(out, attr);
}

/* 4. Return the value of result.
Expand Down