$xml = <<<XML
<!DOCTYPE foo PUBLIC "-//FOO/BAR" "http://example.com/foobar">
<foo>bar&fooz;</foo>
XML;
$dtd = <<<DTD
<!ELEMENT foo (#PCDATA)>
<!ENTITY % fooentity PUBLIC
"-//FOO/ENTITY"
"fooentity.ent">
%fooentity;
DTD;
$entity = <<<ENT
<!ENTITY fooz "baz">
ENT;
libxml_set_external_entity_loader(function ($public, $system, $context) use($dtd, $entity) {
static $first = true;
var_dump($public);
var_dump($system);
var_dump($context);
$f = fopen("php://temp", "r+");
fwrite($f, $first ? $dtd : $entity);
$first = false;
rewind($f);
return $f;
});
$dd = new DOMDocument();
$dd->substituteEntities = true;
$dd->resolveExternals = true;
$r = $dd->loadXML($xml);
var_dump($dd->validate());
echo "Done.\n";
public function __construct()
{
libxml_set_external_entity_loader(function ($public, $system, $context) {
$catalogDir = __DIR__ . '/../../../xml-catalog/';
switch ($public) {
case '-//W3C//DTD XHTML 1.0 Strict//EN':
return $catalogDir . 'xhtml1-strict.dtd';
case '-//W3C//ENTITIES Latin 1 for XHTML//EN':
return $catalogDir . 'xhtml-lat1.ent';
case '-//W3C//ENTITIES Symbols for XHTML//EN':
return $catalogDir . 'xhtml-symbol.ent';
case '-//W3C//ENTITIES Special for XHTML//EN':
return $catalogDir . 'xhtml-special.ent';
default:
return $system;
}
});
}
/**
* Validate dom document
*
* @param \DOMDocument $dom
* @param string $schema Absolute schema file path or URN
* @param string $errorFormat
* @return array of errors
* @throws \Exception
*/
public static function validateDomDocument(
\DOMDocument $dom,
$schema,
$errorFormat = self::ERROR_FORMAT_DEFAULT
) {
if (!self::$urnResolver) {
self::$urnResolver = new UrnResolver();
}
$schema = self::$urnResolver->getRealPath($schema);
libxml_use_internal_errors(true);
libxml_set_external_entity_loader([self::$urnResolver, 'registerEntityLoader']);
try {
$result = $dom->schemaValidate($schema);
$errors = [];
if (!$result) {
$validationErrors = libxml_get_errors();
if (count($validationErrors)) {
foreach ($validationErrors as $error) {
$errors[] = self::_renderErrorMessage($error, $errorFormat);
}
} else {
$errors[] = 'Unknown validation error';
}
}
} catch (\Exception $exception) {
libxml_use_internal_errors(false);
throw $exception;
}
libxml_set_external_entity_loader(null);
libxml_use_internal_errors(false);
return $errors;
}
<?php
$xml = <<<XML
<!DOCTYPE foo PUBLIC "-//FOO/BAR" "http://example.com/foobar">
<foo>bar</foo>
XML;
$dtd = <<<DTD
<!ELEMENT foo (#PCDATA)>
DTD;
libxml_set_external_entity_loader(function ($public, $system, $context) use($dtd) {
var_dump($public);
var_dump($system);
var_dump($context);
$f = fopen("php://temp", "r+");
fwrite($f, $dtd);
rewind($f);
return $f;
});
$dd = new DOMDocument();
$r = $dd->loadXML($xml);
var_dump($dd->validate());
echo "Done.\n";
<?php
chdir(__DIR__);
$xml = <<<XML
<!DOCTYPE foo PUBLIC "-//FOO/BAR" "foobar.dtd">
<foo>bar</foo>
XML;
$dtd = <<<DTD
<!ELEMENT foo (#PCDATA)>
DTD;
libxml_set_external_entity_loader(function ($public, $system, $context) {
var_dump($public, $system);
return null;
});
$dd = new DOMDocument();
$r = $dd->loadXML($xml);
var_dump($dd->validate());
libxml_set_external_entity_loader(NULL);
file_put_contents(__DIR__ . "/foobar.dtd", $dtd);
var_dump($dd->validate());
echo "Done.\n";
error_reporting(0);
@unlink(__DIR__ . "/foobar.dtd");
<?php
$xml = <<<XML
<!DOCTYPE foo PUBLIC "-//FOO/BAR" "http://example.com/foobar">
<foo>bar</foo>
XML;
$dd = new DOMDocument();
$r = $dd->loadXML($xml);
var_dump(libxml_set_external_entity_loader([]));
var_dump(libxml_set_external_entity_loader());
var_dump(libxml_set_external_entity_loader(function () {
}, 2));
var_dump(libxml_set_external_entity_loader(function ($a, $b, $c, $d) {
}));
var_dump($dd->validate());
echo "Done.\n";
<?php
/**
* @link http://stackoverflow.com/questions/13865149/speeding-up-xml-schema-validations-of-a-batch-of-xml-files-against-the-same-xml
*/
$mapping = ['http://www.w3.org/2002/08/xhtml/xhtml1-transitional.xsd' => 'schema/xhtml1-transitional.xsd', 'http://www.w3.org/2001/xml.xsd' => 'schema/xml.xsd'];
libxml_set_external_entity_loader(function ($public, $system, $context) use($mapping) {
if (is_file($system)) {
return $system;
}
if (isset($mapping[$system])) {
return __DIR__ . '/' . $mapping[$system];
}
$message = sprintf("Failed to load external entity: Public: %s; System: %s; Context: %s", var_export($public, 1), var_export($system, 1), strtr(var_export($context, 1), [" (\n " => '(', "\n " => '', "\n" => '']));
throw new RuntimeException($message);
});
$data_dom = new DOMDocument();
$data_dom->load('test-data.xml');
$data_dom->xinclude();
// Multiple validations using the schemaValidate method.
for ($attempt = 1; $attempt <= 3; $attempt++) {
$start = time();
echo "schemaValidate: Attempt #{$attempt} returns ";
if (!$data_dom->schemaValidate('test-schema.xsd')) {
echo "Invalid!";
} else {
echo "Valid!";
}
$end = time();
echo " in " . ($end - $start) . " seconds.\n";
}
/**
* Validate dom document
*
* @param \DOMDocument $dom
* @param string $schema Absolute schema file path or URN
* @param string $errorFormat
* @return array of errors
* @throws \Exception
*/
public static function validateDomDocument(\DOMDocument $dom, $schema, $errorFormat = self::ERROR_FORMAT_DEFAULT)
{
if (!function_exists('libxml_set_external_entity_loader')) {
return [];
}
if (!self::$urnResolver) {
self::$urnResolver = new UrnResolver();
}
$schema = self::$urnResolver->getRealPath($schema);
libxml_use_internal_errors(true);
libxml_set_external_entity_loader([self::$urnResolver, 'registerEntityLoader']);
$errors = [];
try {
$result = $dom->schemaValidate($schema);
if (!$result) {
$errors = self::getXmlErrors($errorFormat);
}
} catch (\Exception $exception) {
libxml_use_internal_errors(false);
throw $exception;
}
libxml_set_external_entity_loader(null);
libxml_use_internal_errors(false);
return $errors;
}