Fix #80268: loadHTML() truncates at NUL bytes

libxml2 has no particular issues parsing HTML strings with NUL bytes;
these just cause truncation of the current text content, but parsing
continues generally.  Since `::loadHTMLFile()` already supports NUL
bytes, `::loadHTML()` should as well.

Note that this is different from XML, which does not allow any NUL
bytes.

Closes phpGH-6368.

Author: cmb69

NEWS

@@ -11,6 +11,9 @@ PHP                                                                        NEWS
 - COM:
   . Fixed bug #62474 (com_event_sink crashes on certain arguments). (cmb)
 
+- DOM:
+  . Fixed bug #80268 (loadHTML() truncates at NUL bytes). (cmb)
+
 - IMAP:
   . Fixed bug #64076 (imap_sort() does not return FALSE on failure). (cmb)
   . Fixed bug #76618 (segfault on imap_reopen). (girgias)

ext/dom/document.c

@@ -2024,7 +2024,6 @@ static void dom_load_html(INTERNAL_FUNCTION_PARAMETERS, int mode) /* {{{ */
 		}
 		ctxt = htmlCreateFileParserCtxt(source, NULL);
 	} else {
-		source_len = xmlStrlen((xmlChar *) source);
 		if (ZEND_SIZE_T_INT_OVFL(source_len)) {
 			php_error_docref(NULL, E_WARNING, "Input string is too long");
 			RETURN_FALSE;

ext/dom/tests/bug80268.phpt

@@ -0,0 +1,24 @@
+--TEST--
+Bug #80268 (loadHTML() truncates at NUL bytes)
+--SKIPIF--
+<?php require_once('skipif.inc'); ?>
+--FILE--
+<?php
+$doc = new DOMDocument;
+$doc->loadHTML("<p>foo\0bar</p>");
+$html = $doc->saveHTML();
+var_dump(strpos($html, '<p>foo</p>') !== false);
+
+file_put_contents(__DIR__ . '/80268.html', "<p>foo\0bar</p>");
+$doc = new DOMDocument;
+$doc->loadHTMLFile(__DIR__ . '/80268.html');
+$html = $doc->saveHTML();
+var_dump(strpos($html, '<p>foo</p>') !== false);
+?>
+--CLEAN--
+<?php
+unlink(__DIR__ . '/80268.html');
+?>
+--EXPECT--
+bool(true)
+bool(true)