Работа в реальном времени с большими объемами xml данных

$xml = simplexml_load_file("price.xml");
echo "<table border='1'>n";

foreach ($xml->xpath('/DocumentElement/price') as $producs) { ?> 
    <tr>
        <td><?php echo $producs->name; ?></td>
        <td><?php echo $producs->company; ?></td>
        <td><?php echo $producs->city; ?></td>
        <td><?php echo $producs->amount ?></td>
    </tr> 
<?
}
echo "</table>n";

$doc = new DOMDocument();
$doc->load( 'books.xml' );
 
$books = $doc->getElementsByTagName( "book" );
foreach( $books as $book )
{
$authors = $book->getElementsByTagName( "author" );
$author = $authors->item(0)->nodeValue;
 
$publishers = $book->getElementsByTagName( "publisher" );
$publisher = $publishers->item(0)->nodeValue;
 
$titles = $book->getElementsByTagName( "title" );
$title = $titles->item(0)->nodeValue;
 
echo "$title - $author - $publishern";

class Simple_Parser 
{
    var $parser;
    var $error_code;
    var $error_string;
    var $current_line;
    var $current_column;
    var $data = array();
    var $datas = array();
    
    function parse($data)
    {
        $this->parser = xml_parser_create('UTF-8');
        xml_set_object($this->parser, $this);
        xml_parser_set_option($this->parser, XML_OPTION_SKIP_WHITE, 1);
        xml_set_element_handler($this->parser, 'tag_open', 'tag_close');
        xml_set_character_data_handler($this->parser, 'cdata');
        if (!xml_parse($this->parser, $data))
        {
            $this->data = array();
            $this->error_code = xml_get_error_code($this->parser);
            $this->error_string = xml_error_string($this->error_code);
            $this->current_line = xml_get_current_line_number($this->parser);
            $this->current_column = xml_get_current_column_number($this->parser);
        }
        else
        {
            $this->data = $this->data['child'];
        }
        xml_parser_free($this->parser);
    }

    function tag_open($parser, $tag, $attribs)
    {
        $this->data['child'][$tag][] = array('data' => '', 'attribs' => $attribs, 'child' => array());
        $this->datas[] =& $this->data;
        $this->data =& $this->data['child'][$tag][count($this->data['child'][$tag])-1];
    }

    function cdata($parser, $cdata)
    {
        $this->data['data'] .= $cdata;
    }

    function tag_close($parser, $tag)
    {
        $this->data =& $this->datas[count($this->datas)-1];
        array_pop($this->datas);
    }
}

$xml_parser = new Simple_Parser;
$xml_parser->parse('<foo><bar>test</bar></foo>');

<?php
<?php
Class StoreXMLReader
{
	
	private $reader;
	private $tag;
	
	// if $ignoreDepth == 1 then will parse just first level, else parse 2th level too
	
	private function parseBlock($name, $ignoreDepth = 1) {
		if ($this->reader->name == $name && $this->reader->nodeType == XMLReader::ELEMENT) {
			$result = array();
			while (!($this->reader->name == $name && $this->reader->nodeType == XMLReader::END_ELEMENT)) {
				//echo $this->reader->name. ' - '.$this->reader->nodeType." - ".$this->reader->depth."n";
				switch ($this->reader->nodeType) {
					case 1:
						if ($this->reader->depth > 3 && !$ignoreDepth) {
							$result[$nodeName] = (isset($result[$nodeName]) ? $result[$nodeName] : array());
							while (!($this->reader->name == $nodeName && $this->reader->nodeType == XMLReader::END_ELEMENT)) {
								$resultSubBlock = $this->parseBlock($this->reader->name, 1);
								
								if (!empty($resultSubBlock))
									$result[$nodeName][] = $resultSubBlock;
								
								unset($resultSubBlock);
								$this->reader->read();
							}
						}
						$nodeName = $this->reader->name;
						if ($this->reader->hasAttributes) {
							$attributeCount = $this->reader->attributeCount;
							
							for ($i = 0; $i < $attributeCount; $i++) {
								$this->reader->moveToAttributeNo($i);
								$result['attr'][$this->reader->name] = $this->reader->value;
							}
							$this->reader->moveToElement();
						}
						break;
					
					case 3:
					case 4:
						$result[$nodeName] = $this->reader->value;
						$this->reader->read();
						break;
				}
				
				$this->reader->read();
			}
			return $result;
		}
	}

	public function parse($filename) {
		
		if (!$filename) return array();
		
		$this->reader = new XMLReader();
		$this->reader->open($filename);
		
		// begin read XML
		while ($this->reader->read()) {
			
			if ($this->reader->name == 'store_categories') {
			// while not found end tag read blocks
			while (!($this->reader->name == 'store_categories' && $this->reader->nodeType == XMLReader::END_ELEMENT)) {
				$store_category = $this->parseBlock('store_category');
				
				/*
					Do some code
				*/
				
				$this->reader->read();
			}
			
			$this->reader->read();
		}
			
		} // while
	} // func
}

$xmlr = new StoreXMLReader();
$r = $xmlr->parse('example.xml');

<?php
$xmlWriter = new XMLWriter();
$xmlWriter->openMemory();
$xmlWriter->startDocument('1.0', 'UTF-8');
$xmlWriter->startElement('shop');
for ($i=0; $i<=1000000; ++$i) {
    $productId = uniqid();

    $xmlWriter->startElement('product');
    $xmlWriter->writeElement('id', $productId);
    $xmlWriter->writeElement('name', 'Some product name. ID:' . $productId);
    $xmlWriter->endElement();
    // Flush XML in memory to file every 1000 iterations
    if (0 == $i%1000) {
        file_put_contents('example.xml', $xmlWriter->flush(true), FILE_APPEND);
    }
}
$xmlWriter->endElement();
// Final flush to make sure we haven't missed anything
file_put_contents('example.xml', $xmlWriter->flush(true), FILE_APPEND);

1

gVim can open extremely large files without trouble.

XMLMax will open your 100MB file in a treeview in under 5 seconds and will handle any size or structure xml file. It also has a number of options to split it up for you. YOu mentioned wanting to see the structure: if you create an index, the index file, which is a plain text utf-8 file, has a list at the end of all the unique paths in the xml file.

2

IntelliJIDEA can open big files (read-only mode)

$xml = simplexml_load_file("price.xml");
echo "<table border='1'>n";

foreach ($xml->xpath('/DocumentElement/price') as $producs) { ?> 
    <tr>
        <td><?php echo $producs->name; ?></td>
        <td><?php echo $producs->company; ?></td>
        <td><?php echo $producs->city; ?></td>
        <td><?php echo $producs->amount ?></td>
    </tr> 
<?
}
echo "</table>n";

$doc = new DOMDocument();
$doc->load( 'books.xml' );
 
$books = $doc->getElementsByTagName( "book" );
foreach( $books as $book )
{
$authors = $book->getElementsByTagName( "author" );
$author = $authors->item(0)->nodeValue;
 
$publishers = $book->getElementsByTagName( "publisher" );
$publisher = $publishers->item(0)->nodeValue;
 
$titles = $book->getElementsByTagName( "title" );
$title = $titles->item(0)->nodeValue;
 
echo "$title - $author - $publishern";

class Simple_Parser 
{
    var $parser;
    var $error_code;
    var $error_string;
    var $current_line;
    var $current_column;
    var $data = array();
    var $datas = array();
    
    function parse($data)
    {
        $this->parser = xml_parser_create('UTF-8');
        xml_set_object($this->parser, $this);
        xml_parser_set_option($this->parser, XML_OPTION_SKIP_WHITE, 1);
        xml_set_element_handler($this->parser, 'tag_open', 'tag_close');
        xml_set_character_data_handler($this->parser, 'cdata');
        if (!xml_parse($this->parser, $data))
        {
            $this->data = array();
            $this->error_code = xml_get_error_code($this->parser);
            $this->error_string = xml_error_string($this->error_code);
            $this->current_line = xml_get_current_line_number($this->parser);
            $this->current_column = xml_get_current_column_number($this->parser);
        }
        else
        {
            $this->data = $this->data['child'];
        }
        xml_parser_free($this->parser);
    }

    function tag_open($parser, $tag, $attribs)
    {
        $this->data['child'][$tag][] = array('data' => '', 'attribs' => $attribs, 'child' => array());
        $this->datas[] =& $this->data;
        $this->data =& $this->data['child'][$tag][count($this->data['child'][$tag])-1];
    }

    function cdata($parser, $cdata)
    {
        $this->data['data'] .= $cdata;
    }

    function tag_close($parser, $tag)
    {
        $this->data =& $this->datas[count($this->datas)-1];
        array_pop($this->datas);
    }
}

$xml_parser = new Simple_Parser;
$xml_parser->parse('<foo><bar>test</bar></foo>');

<?php
<?php
Class StoreXMLReader
{
	
	private $reader;
	private $tag;
	
	// if $ignoreDepth == 1 then will parse just first level, else parse 2th level too
	
	private function parseBlock($name, $ignoreDepth = 1) {
		if ($this->reader->name == $name && $this->reader->nodeType == XMLReader::ELEMENT) {
			$result = array();
			while (!($this->reader->name == $name && $this->reader->nodeType == XMLReader::END_ELEMENT)) {
				//echo $this->reader->name. ' - '.$this->reader->nodeType." - ".$this->reader->depth."n";
				switch ($this->reader->nodeType) {
					case 1:
						if ($this->reader->depth > 3 && !$ignoreDepth) {
							$result[$nodeName] = (isset($result[$nodeName]) ? $result[$nodeName] : array());
							while (!($this->reader->name == $nodeName && $this->reader->nodeType == XMLReader::END_ELEMENT)) {
								$resultSubBlock = $this->parseBlock($this->reader->name, 1);
								
								if (!empty($resultSubBlock))
									$result[$nodeName][] = $resultSubBlock;
								
								unset($resultSubBlock);
								$this->reader->read();
							}
						}
						$nodeName = $this->reader->name;
						if ($this->reader->hasAttributes) {
							$attributeCount = $this->reader->attributeCount;
							
							for ($i = 0; $i < $attributeCount; $i++) {
								$this->reader->moveToAttributeNo($i);
								$result['attr'][$this->reader->name] = $this->reader->value;
							}
							$this->reader->moveToElement();
						}
						break;
					
					case 3:
					case 4:
						$result[$nodeName] = $this->reader->value;
						$this->reader->read();
						break;
				}
				
				$this->reader->read();
			}
			return $result;
		}
	}

	public function parse($filename) {
		
		if (!$filename) return array();
		
		$this->reader = new XMLReader();
		$this->reader->open($filename);
		
		// begin read XML
		while ($this->reader->read()) {
			
			if ($this->reader->name == 'store_categories') {
			// while not found end tag read blocks
			while (!($this->reader->name == 'store_categories' && $this->reader->nodeType == XMLReader::END_ELEMENT)) {
				$store_category = $this->parseBlock('store_category');
				
				/*
					Do some code
				*/
				
				$this->reader->read();
			}
			
			$this->reader->read();
		}
			
		} // while
	} // func
}

$xmlr = new StoreXMLReader();
$r = $xmlr->parse('example.xml');

<?php
$xmlWriter = new XMLWriter();
$xmlWriter->openMemory();
$xmlWriter->startDocument('1.0', 'UTF-8');
$xmlWriter->startElement('shop');
for ($i=0; $i<=1000000; ++$i) {
    $productId = uniqid();

    $xmlWriter->startElement('product');
    $xmlWriter->writeElement('id', $productId);
    $xmlWriter->writeElement('name', 'Some product name. ID:' . $productId);
    $xmlWriter->endElement();
    // Flush XML in memory to file every 1000 iterations
    if (0 == $i%1000) {
        file_put_contents('example.xml', $xmlWriter->flush(true), FILE_APPEND);
    }
}
$xmlWriter->endElement();
// Final flush to make sure we haven't missed anything
file_put_contents('example.xml', $xmlWriter->flush(true), FILE_APPEND);

Боюсь только утилиты вроде less могут открывать такие файлы для просмотра..
Что же до преобразования, то попробуйте saxon с какими-нибудь жуткими параметрами запуска, чтобы памяти хватило.

Notepad2

1. Мне нужно спарсить большие XML файлы размером от ~ 500 до ~ 1700 мб.

   Собственно я и юзаю XMLReader

   7.     include_once ‘inc/Misc.php’;
   8.     include_once ‘inc/Database.php’;
   10.     $files = array(‘xml/large_file.xml’);
   14.     foreach($files as $file) {
   18.         echo ‘Filesize: ‘.convert(filesize($file)).«n«;
   19.         echo ‘Start parsing…’.«n«;
   22.         $reader = new XMLReader();
   27.         while ($reader->read()) {
   28.             switch ($reader->nodeType) {
   29.                 case (XMLREADER::ELEMENT):
   30.                 if ($reader->localName == «element-name») {                    
   31.                         $dom = new DomDocument();
   32.                         $n = $dom->importNode($reader->expand(),true);
   35.                         $tess->file_big->insert($sxe);          
   36.                         echo «Insert done! «; benchmark();                     

   все нормально сначала… парсится потихоньку файл и вставляются нужные мне данные, но постепенно растет потребление памяти и пока не заканчиваются ресурсы только парсится. То есть я взял файл на 400 метров и пока его парсило то израсходовало 2000 метров оперативки и все ресурсы кончились и скрипт остановился.

   Как быть с большими файлами ? ~ 500 до ~ 1700 мб. поможет ли тут XML Parser ? да и как им нормально парсить то что мне надо как в моем скрипте выше, примеров толковых нет… Еще варианты может есть ?

2. 
   

   Gromo
   Активный пользователь

   С нами с:

   24 май 2010

   Сообщения:

   2.786

   Симпатии:

   2

   Адрес:

   Ташкент

   Awilum
   решение «в лоб» — загонять файл в базу для более удобной работы, построчно считывая файл в память и обрабатывая каждую строку отдельно — грубо говоря, писать собственный парсер для большого файла.

   Держать в памяти 2 Гб файл XML в виде объектной структуры — это нереально.

3. 
   

   Psih
   Активный пользователь

   Команда форума
   Модератор

   Поскольку сам по себе парсинг работает, то явно всё в память не грузится. Насколько я знаю XMLReader потоковый.

   Проблема в том, что в таких случаях надо забочитстя об очисте памяти, т.е. делать unset переменным, которые больше не нужны.
   Ну и желательно использовать PHP 5.3+ в включённым сборщиком мусора.

5. дело в том что у меня могут повторяться названия элементов и количество как оказалось тоже вот например

   4. <party-name>Guess? IP Holder L.P.</party-name>
   7. <postcode>90021</postcode>

   и сработает только один флажок state

6. 
   

   Psih
   Активный пользователь

   Команда форума
   Модератор

   С SAX парсером не подскажу — я с ним работал, но давненько. А вот XMLReader скрипт вполне есть куда улучшить.

   3. // Try to enable garbage collection on 5.3+
   9. include_once ‘inc/Misc.php’;
   10. include_once ‘inc/Database.php’;
   11. $files = array(‘xml/large_file.xml’);
   13. foreach($files as $file) {
   16.     echo ‘Filesize: ‘.convert(filesize($file)).«n«;
   17.     echo ‘Start parsing…’.«n«;
   20.     $reader = new XMLReader();
   23.     while ($reader->read()) {
   24.         switch ($reader->nodeType) {
   25.             case (XMLREADER::ELEMENT):
   26.                 if ($reader->localName == «element-name») {
   27.                     $dom = new DomDocument();
   28.                     $n = $dom->importNode($reader->expand(),true);
   32.                     * Database insert? What is $tess and what’s inside it?
   35.                     $tess->file_big->insert($sxe);
   36.                     echo «Insert done! «; benchmark();
   45.     // Delete the object to free memory

7. да это mongoDB почему то течет. уже сделал и так, но все равно течет с каждой вставкой

   1.              case (XMLREADER::ELEMENT):
   2.                  if ($reader->localName == «case-file») {
   3.                      $dom = new DomDocument();
   4.                      $n = $dom->importNode($reader->expand(),true);
   6.                      $sxe = simplexml_import_dom($n);
   8.                      * Database insert? What is $tess and what’s inside it?
   11.                      //$tess->file_big->insert($sxe);
   14.                      $tess = $mongo->selectDB(‘tess’);         
   15.                      $tess->file_big->insert($sxe);
   18.                      echo «Insert done! «; benchmark();
   20.                      unset($n, $dom, $sxe, $mongo, $tess);                    

8. хотя в варианте с САКСОМ такой утечки не наблюдаю. а тут прям с каждой вставкой оперативка отжирается.

   без этого

   $mongo = new Mongo();
   $tess = $mongo->selectDB(‘tess’);
   $tess->file_big->insert($sxe);

   норм а с этой вставкой сильно жрутся ресурсы и не очищаются.

9. 
   

   Psih
   Активный пользователь

   Команда форума
   Модератор

   Awilum
   А вы забываете закрыть соединение с MongoDB — ресурс то кушается с каждым новым объектом. Бережнее надо, бережнее.

10. 1.              case (XMLREADER::ELEMENT):
    2.                  if ($reader->localName == «case-file») {
    3.                      $dom = new DomDocument();
    4.                      $n = $dom->importNode($reader->expand(),true);
    6.                      $sxe = simplexml_import_dom($n);
    8.                      * Database insert? What is $tess and what’s inside it?
    11.                      //$tess->file_big->insert($sxe);
    14.                      $tess = $mongo->selectDB(‘tess’);         
    15.                      $tess->file_big->insert($sxe);
    19.                      echo «Insert done! «; benchmark();
    21.                      unset($n, $dom, $sxe, $mongo, $tess);                    

    потребление памяти все растет с каждой вставкой. тут уже и unset и close есть.

11. 
    

    Psih
    Активный пользователь

    Команда форума
    Модератор

    Awilum
    Могу покопаться на досуге, но нужен приличный XML файл и скрипт, которым вы его парсите. Только тестировать буду на PHP 5.3 а не 5.2 (под 7-ку нету нормальных толковых версий 5.2). У 5.2 есть проблемы с памятью и их решить нереально иногда.

13. 
    

    Psih
    Активный пользователь

    Команда форума
    Модератор

    Вы мне, пожайлуста, перешлите всё же все файлы скрипта — Misc.php, Database.php — может проблема утечек вообще где-то в них. Тут нужно всё пересматривать, а не отдельные части

    Эх, надо будет ещё MongoDB поставить себе…

14. утром тестил в холостую без вставки ничего не жрало, а со вставкой жрало. Щас чего то пофиг как: и так и так жрет зараза (что в холостую что со вставкой) жесть какая та.

15. Database.php и Misc.php можно не брать во внимание оно и без них жрет

    Database.php

    4.     $tess = $mongo->selectDB(‘tess’);          

    Misc.php

    5.       * Convert bytes in ‘kb’,’mb’,’gb’,’tb’,’pb’
    6.       * @param integer $size Data to convert
    9.     function convert($size) {
    10.         $unit=array(‘b’,’kb’,’mb’,’gb’,’tb’,’pb’);
    11.         return @round($size/pow(1024,($i=floor(log($size,1024)))),2).’ ‘.$unit[$i];
    17.      * @param boolean $render Displays the result of the function in the browser or not
    19.     function getMemoryUsage($render=true) {
    20.         if (function_exists(‘memory_get_usage’)) {
    21.             $memory_usage = memory_get_usage();
    22.         } else if (substr(PHP_OS,0,3) == ‘WIN’) {
    23.             // Windows 2000 workaround
    25.             exec(‘pslist ‘ . getmypid() , $output);
    26.             $memory_usage = trim(substr($output[8],38,10));
    31.             printf(‘Memory usage: ‘.convert($memory_usage));
    40.      * @global integer $start_time Start time value
    41.      * @param boolean $render Displays the result of the function in the browser or not
    43.     function getElapsedTime($render=true) {
    45.         $result_time = microtime(true) — $start_time;
    46.         if($render) printf(«Elapsed time %.3f seconds»,$result_time); else return sprintf(«%.3f», $result_time);
    54.         getMemoryUsage(); echo » — «; getElapsedTime(); echo «n»;

    4.  // Try to enable garbage collection on 5.3+
    5.  if (function_exists(‘gc_enable’) && !gc_enabled()) {
    9.  $files = array(‘xml/apc101231-42.xml’);
    11.  foreach($files as $file) {
    13.      echo ‘Filename: ‘.basename($file).»n»;
    14.      //echo ‘Filesize: ‘.convert(filesize($file)).»n»;
    15.      echo ‘Start parsing…’.»n»;
    18.      $reader = new XMLReader();
    21.      while ($reader->read()) {
    22.          switch ($reader->nodeType) {          
    23.              case (XMLREADER::ELEMENT):
    24.                  if ($reader->localName == «case-file») {
    25.                      $dom = new DomDocument();
    26.                      $n = $dom->importNode($reader->expand(),true);
    28.                      $sxe = simplexml_import_dom($n);
    31.                      $tess = $mongo->selectDB(‘tess’);          
    32.                      $tess->file_big->insert($sxe);
    38.                      //unset($n, $dom, $sxe, $mongo, $tess);                    
    47.      // Delete the object to free memory

19. $reader->open($file,’LIBXML_PARSEHUGE’);

    потребление памяти растет.

20. 
    

    Psih
    Активный пользователь

    Команда форума
    Модератор

    Awilum
    Эээ, ну вы хоть читайте мануал и параметры для функций то…

    $reader->open($file, null, LIBXML_PARSEHUGE);

    либо как советуют в комментах к XMLReader::read():

    $xmlreader->open($uri, null, 1<<19);

21. $reader->open($file, null, ‘LIBXML_PARSEHUGE’);
    Warning: XMLReader:pen() expects parameter 3 to be long

    $reader->open($file, null, LIBXML_PARSEHUGE);
    Notice: Use of undefined constant LIBXML_PARSEHUGE — assumed ‘LIBXML_PARSEHUGE’

22. 1. while ($reader->read()) {

    а это место течь не может ? потому что больше некуда смотреть, так как что в холостую что нет одинаково.

    прологировал

    1.          while ($reader->read()) {   
    3.              switch ($reader->nodeType) {          
    4.                  case (XMLREADER::ELEMENT):                  
    5.                      if ($reader->localName == «case-file») {
    7.                          logAdd(‘case-file found’);
    9.                          $dom = new DomDocument();
    10.                          $n = $dom->importNode($reader->expand(),true);
    12.                          $sxe = simplexml_import_dom($n);
    14.                          logAdd(‘case-file in $sxe’);
    17.                          $mongo->$db->$collection->insert($sxe);                           
    27.                          logAdd(‘Clear the memory’);

    не вижу ни каких проблем, но процесс расходует память.

23. я уже и так сделал. но все равно у процесса растет память! жесть. то ли действительно этот ридер копит весь файл и по этому потребление растет.

    3.     $start_time = microtime(true);
    11.      // Try to enable garbage collection on 5.3+
    12.     if (function_exists(‘gc_enable’) && !gc_enabled()) {       
    21.     $files = array(/*’xml/apc101231-42.xml’,*/
    24.      foreach($files as $file) {
    26.          echo ‘Filename: ‘.basename($file).»n»;
    27.          echo ‘Start parsing…’.»n»;
    31.          $reader = new XMLReader();
    35.          if(!($fp = fopen($file, «r»)));
    37.          while ($data = fread($fp, 4096)) {
    43.          //while ($reader->read()) {     
    45.              switch ($reader->nodeType) {          
    46.                  case (XMLREADER::ELEMENT):                  
    47.                      if ($reader->localName == «case-file») {
    49.                          logAdd(‘case-file found’);
    51.                          $dom = new DomDocument();
    52.                          $n = $dom->importNode($reader->expand(),true);
    54.                          $sxe = simplexml_import_dom($n);
    56.                          logAdd(‘case-file in $sxe’);
    59.                          //$mongo->$db->$collection->insert($sxe);                         
    69.                          logAdd(‘Clear the memory’);
    81.          // Delete the object to free memory

24. 
    

    Psih
    Активный пользователь

    Команда форума
    Модератор

    Awilum
    Сегодня будет вечером время, попробую разобраться. Но если память так и кушаться будет — надо будет смотреть базу багов PHP и репортить, если такового нету.

25. Скачал исходник php что бы посмотреть как же все такие устроен этот ридер.

    $Id: php_xmlreader.c 306939 2011-01-01 02:19:59Z felipe $

    11. #include «ext/standard/info.h»
    12. #include «php_xmlreader.h»
    14. #include «ext/dom/xml_common.h»
    18. zend_class_entry *xmlreader_class_entry;
    20. static zend_object_handlers xmlreader_object_handlers;
    22. static HashTable xmlreader_prop_handlers;
    24. typedef int (*xmlreader_read_int_t)(xmlTextReaderPtr reader);
    25. typedef unsigned char *(*xmlreader_read_char_t)(xmlTextReaderPtr reader);
    26. typedef const unsigned char *(*xmlreader_read_const_char_t)(xmlTextReaderPtr reader);
    27. typedef int (*xmlreader_write_t)(xmlreader_object *obj, zval *newval TSRMLS_DC);
    29. typedef unsigned char *(*xmlreader_read_one_char_t)(xmlTextReaderPtr reader, const unsigned char *);
    31. typedef struct _xmlreader_prop_handler {
    32.     xmlreader_read_int_t read_int_func;
    33.     xmlreader_read_const_char_t read_char_func;
    34.     xmlreader_write_t write_func;
    36. } xmlreader_prop_handler;
    38. #define XMLREADER_LOAD_STRING 0
    39. #define XMLREADER_LOAD_FILE 1
    41. /* {{{ xmlreader_register_prop_handler */
    42. static void xmlreader_register_prop_handler(HashTable *prop_handler, char *name, xmlreader_read_int_t read_int_func, xmlreader_read_const_char_t read_char_func, int rettype TSRMLS_DC)
    44.     xmlreader_prop_handler hnd;
    46.     hnd.read_char_func = read_char_func;
    47.     hnd.read_int_func = read_int_func;
    49.     zend_hash_add(prop_handler, name, strlen(name)+1, &hnd, sizeof(xmlreader_prop_handler), NULL);
    53. /* {{{ xmlreader_property_reader */
    54. static int xmlreader_property_reader(xmlreader_object *obj, xmlreader_prop_handler *hnd, zval **retval TSRMLS_DC)
    56.     const xmlChar *retchar = NULL;
    60.         if (hnd->read_char_func) {
    61.             retchar = hnd->read_char_func(obj->ptr);
    63.             if (hnd->read_int_func) {
    64.                 retint = hnd->read_int_func(obj->ptr);
    66.                     php_error_docref(NULL TSRMLS_CC, E_WARNING, «Internal libxml error returned»);
    78.                 ZVAL_STRING(*retval, (char *) retchar, 1);
    80.                 ZVAL_EMPTY_STRING(*retval);
    84.             ZVAL_BOOL(*retval, retint);
    87.             ZVAL_LONG(*retval, retint);
    97. /* {{{ xmlreader_get_property_ptr_ptr */
    98. zval **xmlreader_get_property_ptr_ptr(zval *object, zval *member TSRMLS_DC)
    103.     xmlreader_prop_handler *hnd;
    104.     zend_object_handlers *std_hnd;
    107.     if (member->type != IS_STRING) {
    109.         zval_copy_ctor(&tmp_member);
    110.         convert_to_string(&tmp_member);
    114.     obj = (xmlreader_object *)zend_objects_get_address(object TSRMLS_CC);
    116.     if (obj->prop_handler != NULL) {
    117.         ret = zend_hash_find(obj->prop_handler, Z_STRVAL_P(member), Z_STRLEN_P(member)+1, (void **) &hnd);
    120.         std_hnd = zend_get_std_object_handlers();
    121.         retval = std_hnd->get_property_ptr_ptr(object, member TSRMLS_CC);
    124.     if (member == &tmp_member) {
    131. /* {{{ xmlreader_read_property */
    132. zval *xmlreader_read_property(zval *object, zval *member, int type TSRMLS_DC)
    137.     xmlreader_prop_handler *hnd;
    138.     zend_object_handlers *std_hnd;
    141.     if (member->type != IS_STRING) {
    143.         zval_copy_ctor(&tmp_member);
    144.         convert_to_string(&tmp_member);
    149.     obj = (xmlreader_object *)zend_objects_get_address(object TSRMLS_CC);
    151.     if (obj->prop_handler != NULL) {
    152.         ret = zend_hash_find(obj->prop_handler, Z_STRVAL_P(member), Z_STRLEN_P(member)+1, (void **) &hnd);
    155.         ret = xmlreader_property_reader(obj, hnd, &retval TSRMLS_CC);
    157.             /* ensure we’re creating a temporary variable */
    158.             Z_SET_REFCOUNT_P(retval, 0);
    160.             retval = EG(uninitialized_zval_ptr);
    163.         std_hnd = zend_get_std_object_handlers();
    164.         retval = std_hnd->read_property(object, member, type TSRMLS_CC);
    167.     if (member == &tmp_member) {
    174. /* {{{ xmlreader_write_property */
    175. void xmlreader_write_property(zval *object, zval *member, zval *value TSRMLS_DC)
    179.     xmlreader_prop_handler *hnd;
    180.     zend_object_handlers *std_hnd;
    183.     if (member->type != IS_STRING) {
    185.         zval_copy_ctor(&tmp_member);
    186.         convert_to_string(&tmp_member);
    191.     obj = (xmlreader_object *)zend_objects_get_address(object TSRMLS_CC);
    193.     if (obj->prop_handler != NULL) {
    194.         ret = zend_hash_find((HashTable *)obj->prop_handler, Z_STRVAL_P(member), Z_STRLEN_P(member)+1, (void **) &hnd);
    197.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Cannot write to read-only property»);
    199.         std_hnd = zend_get_std_object_handlers();
    200.         std_hnd->write_property(object, member, value TSRMLS_CC);
    203.     if (member == &tmp_member) {
    209. /* {{{ _xmlreader_get_valid_file_path */
    210. /* _xmlreader_get_valid_file_path and _xmlreader_get_relaxNG should be made a
    211.     common function in libxml extension as code is common to a few xml extensions */
    212. char *_xmlreader_get_valid_file_path(char *source, char *resolved_path, int resolved_path_len  TSRMLS_DC) {
    219.     escsource = xmlURIEscapeStr((xmlChar *)source, (xmlChar *)»:»);
    220.     xmlParseURIReference(uri, (const char *)escsource);
    223.     if (uri->scheme != NULL) {
    224.         /* absolute file uris — libxml only supports localhost or empty host */
    225.         if (strncasecmp(source, «file:///»,8) == 0) {
    232.         } else if (strncasecmp(source, «file://localhost/»,17) == 0) {
    244.     if ((uri->scheme == NULL || isFileUri)) {
    245.         if (!VCWD_REALPATH(source, resolved_path) && !expand_filepath(source, resolved_path TSRMLS_CC)) {
    249.         file_dest = resolved_path;
    258. #ifdef LIBXML_SCHEMAS_ENABLED
    259. /* {{{ _xmlreader_get_relaxNG */
    260. static xmlRelaxNGPtr _xmlreader_get_relaxNG(char *source, int source_len, int type,
    261.                                             xmlRelaxNGValidityErrorFunc error_func,
    262.                                             xmlRelaxNGValidityWarningFunc warn_func TSRMLS_DC)
    265.     xmlRelaxNGParserCtxtPtr parser = NULL;
    267.     char resolved_path[MAXPATHLEN + 1];
    270.     case XMLREADER_LOAD_FILE:
    271.         valid_file = _xmlreader_get_valid_file_path(source, resolved_path, MAXPATHLEN  TSRMLS_CC);
    275.         parser = xmlRelaxNGNewParserCtxt(valid_file);
    277.     case XMLREADER_LOAD_STRING:
    278.         parser = xmlRelaxNGNewMemParserCtxt(source, source_len);
    279.         /* If loading from memory, we need to set the base directory for the document
    280.            but it is not apparent how to do that for schema’s */
    290.     if (error_func || warn_func) {
    291.         xmlRelaxNGSetParserErrors(parser,
    292.             (xmlRelaxNGValidityErrorFunc) error_func,
    293.             (xmlRelaxNGValidityWarningFunc) warn_func,
    296.     sptr = xmlRelaxNGParse(parser);
    297.     xmlRelaxNGFreeParserCtxt(parser);
    304. static const zend_module_dep xmlreader_deps[] = {
    305.     ZEND_MOD_REQUIRED(«libxml»)
    309. /* {{{ xmlreader_module_entry
    311. zend_module_entry xmlreader_module_entry = {
    312.     STANDARD_MODULE_HEADER_EX, NULL,
    317.     PHP_MSHUTDOWN(xmlreader),
    321.     «0.1», /* Replace with version number for your extension */
    322.     STANDARD_MODULE_PROPERTIES
    326. #ifdef COMPILE_DL_XMLREADER
    327. ZEND_GET_MODULE(xmlreader)
    330. /* {{{ xmlreader_objects_clone */
    331. void xmlreader_objects_clone(void *object, void **object_clone TSRMLS_DC)
    337. /* {{{ xmlreader_free_resources */
    338. static void xmlreader_free_resources(xmlreader_object *intern) {
    341.             xmlFreeParserInputBuffer(intern->input);
    346.             xmlFreeTextReader(intern->ptr);
    349. #ifdef LIBXML_SCHEMAS_ENABLED
    351.             xmlRelaxNGFree((xmlRelaxNGPtr) intern->schema);
    359. /* {{{ xmlreader_objects_free_storage */
    360. void xmlreader_objects_free_storage(void *object TSRMLS_DC)
    362.     xmlreader_object *intern = (xmlreader_object *)object;
    364.     zend_object_std_dtor(&intern->std TSRMLS_CC);
    366.     xmlreader_free_resources(intern);
    372. /* {{{ xmlreader_objects_new */
    373. zend_object_value xmlreader_objects_new(zend_class_entry *class_type TSRMLS_DC)
    375.     zend_object_value retval;
    376.     xmlreader_object *intern;
    379.     intern = emalloc(sizeof(xmlreader_object));
    380.     memset(&intern->std, 0, sizeof(zend_object));
    384.     intern->prop_handler = &xmlreader_prop_handlers;
    386.     zend_object_std_init(&intern->std, class_type TSRMLS_CC);
    387.     zend_hash_copy(intern->std.properties, &class_type->default_properties, (copy_ctor_func_t) zval_add_ref, (void *) &tmp, sizeof(zval *));
    388.     retval.handle = zend_objects_store_put(intern, (zend_objects_store_dtor_t)zend_objects_destroy_object, (zend_objects_free_object_storage_t) xmlreader_objects_free_storage, xmlreader_objects_clone TSRMLS_CC);
    389.     intern->handle = retval.handle;
    390.     retval.handlers = &xmlreader_object_handlers;
    395. /* {{{ php_xmlreader_string_arg */
    396. static void php_xmlreader_string_arg(INTERNAL_FUNCTION_PARAMETERS, xmlreader_read_one_char_t internal_function) {
    400.     xmlreader_object *intern;
    403.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «s», &name, &name_len) == FAILURE) {
    408.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Argument cannot be an empty string»);
    414.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    415.     if (intern && intern->ptr) {
    416.         retchar = (char *)internal_function(intern->ptr, (const unsigned char *)name);
    419.         RETVAL_STRING(retchar, 1);
    428. /* {{{ php_xmlreader_no_arg */
    429. static void php_xmlreader_no_arg(INTERNAL_FUNCTION_PARAMETERS, xmlreader_read_int_t internal_function) {
    432.     xmlreader_object *intern;
    436.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    437.     if (intern && intern->ptr) {
    438.         retval = internal_function(intern->ptr);
    448. #if LIBXML_VERSION >= 20620
    449. /* {{{ php_xmlreader_no_arg_string */
    450. static void php_xmlreader_no_arg_string(INTERNAL_FUNCTION_PARAMETERS, xmlreader_read_char_t internal_function) {
    453.     xmlreader_object *intern;
    457.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    458.     if (intern && intern->ptr) {
    459.         retchar = (char *)internal_function(intern->ptr);
    462.         RETVAL_STRING(retchar, 1);
    472. /* {{{ php_xmlreader_set_relaxng_schema */
    473. static void php_xmlreader_set_relaxng_schema(INTERNAL_FUNCTION_PARAMETERS, int type) {
    474. #ifdef LIBXML_SCHEMAS_ENABLED
    476.     int source_len = 0, retval = -1;
    477.     xmlreader_object *intern;
    478.     xmlRelaxNGPtr schema = NULL;
    481.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «s!», &source, &source_len) == FAILURE) {
    485.     if (source != NULL && !source_len) {
    486.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Schema data source is required»);
    492.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    493.     if (intern && intern->ptr) {
    495.             schema =  _xmlreader_get_relaxNG(source, source_len, type, NULL, NULL TSRMLS_CC);
    497.                 retval = xmlTextReaderRelaxNGSetSchema(intern->ptr, schema);
    500.             /* unset the associated relaxNG context and schema if one exists */
    501.             retval = xmlTextReaderRelaxNGSetSchema(intern->ptr, NULL);
    506.                 xmlRelaxNGFree((xmlRelaxNGPtr) intern->schema);
    515.     php_error_docref(NULL TSRMLS_CC, E_WARNING, «Unable to set schema. This must be set prior to reading or schema contains errors.»);
    519.     php_error_docref(NULL TSRMLS_CC, E_WARNING, «No Schema support built into libxml.»);
    526. /* {{{ proto boolean XMLReader::close()
    527. Closes xmlreader — current frees resources until xmlTextReaderClose is fixed in libxml */
    528. PHP_METHOD(xmlreader, close)
    531.     xmlreader_object *intern;
    534.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    535.     /* libxml is segfaulting in versions up to 2.6.8 using xmlTextReaderClose so for
    536.     now we will free the whole reader when close is called as it would get rebuilt on
    538.     xmlreader_free_resources(intern);
    544. /* {{{ proto string XMLReader::getAttribute(string name)
    545. Get value of an attribute from current element */
    546. PHP_METHOD(xmlreader, getAttribute)
    548.     php_xmlreader_string_arg(INTERNAL_FUNCTION_PARAM_PASSTHRU, xmlTextReaderGetAttribute);
    552. /* {{{ proto string XMLReader::getAttributeNo(int index)
    553. Get value of an attribute at index from current element */
    554. PHP_METHOD(xmlreader, getAttributeNo)
    559.     xmlreader_object *intern;
    561.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «l», &attr_pos) == FAILURE) {
    567.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    568.     if (intern && intern->ptr) {
    569.         retchar = (char *)xmlTextReaderGetAttributeNo(intern->ptr, attr_pos);
    572.         RETVAL_STRING(retchar, 1);
    581. /* {{{ proto string XMLReader::getAttributeNs(string name, string namespaceURI)
    582. Get value of a attribute via name and namespace from current element */
    583. PHP_METHOD(xmlreader, getAttributeNs)
    586.     int name_len = 0, ns_uri_len = 0;
    587.     xmlreader_object *intern;
    588.     char *name, *ns_uri, *retchar = NULL;
    590.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «ss», &name, &name_len, &ns_uri, &ns_uri_len) == FAILURE) {
    594.     if (name_len == 0 || ns_uri_len == 0) {
    595.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Attribute Name and Namespace URI cannot be empty»);
    601.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    602.     if (intern && intern->ptr) {
    603.         retchar = (char *)xmlTextReaderGetAttributeNs(intern->ptr, (xmlChar *)name, (xmlChar *)ns_uri);
    606.         RETVAL_STRING(retchar, 1);
    615. /* {{{ proto boolean XMLReader::getParserProperty(int property)
    616. Indicates whether given property (one of the parser option constants) is set or not on parser */
    617. PHP_METHOD(xmlreader, getParserProperty)
    622.     xmlreader_object *intern;
    624.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «l», &property) == FAILURE) {
    630.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    631.     if (intern && intern->ptr) {
    632.         retval = xmlTextReaderGetParserProp(intern->ptr,property);
    635.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Invalid parser property»);
    643. /* {{{ proto boolean XMLReader::isValid()
    644. Returns boolean indicating if parsed document is valid or not.
    645. Must set XMLREADER_LOADDTD or XMLREADER_VALIDATE parser option prior to the first call to read
    646. or this method will always return FALSE */
    647. PHP_METHOD(xmlreader, isValid)
    649.     php_xmlreader_no_arg(INTERNAL_FUNCTION_PARAM_PASSTHRU, xmlTextReaderIsValid);
    653. /* {{{ proto string XMLReader::lookupNamespace(string prefix)
    654. Return namespaceURI for associated prefix on current node */
    655. PHP_METHOD(xmlreader, lookupNamespace)
    657.     php_xmlreader_string_arg(INTERNAL_FUNCTION_PARAM_PASSTHRU, xmlTextReaderLookupNamespace);
    661. /* {{{ proto boolean XMLReader::moveToAttribute(string name)
    662. Positions reader at specified attribute — Returns TRUE on success and FALSE on failure */
    663. PHP_METHOD(xmlreader, moveToAttribute)
    666.     int name_len = 0, retval;
    667.     xmlreader_object *intern;
    670.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «s», &name, &name_len) == FAILURE) {
    675.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Attribute Name is required»);
    681.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    682.     if (intern && intern->ptr) {
    683.         retval = xmlTextReaderMoveToAttribute(intern->ptr, (xmlChar *)name);
    693. /* {{{ proto boolean XMLReader::moveToAttributeNo(int index)
    694. Positions reader at attribute at spcecified index.
    695. Returns TRUE on success and FALSE on failure */
    696. PHP_METHOD(xmlreader, moveToAttributeNo)
    701.     xmlreader_object *intern;
    703.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «l», &attr_pos) == FAILURE) {
    709.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    710.     if (intern && intern->ptr) {
    711.         retval = xmlTextReaderMoveToAttributeNo(intern->ptr, attr_pos);
    721. /* {{{ proto boolean XMLReader::moveToAttributeNs(string name, string namespaceURI)
    722. Positions reader at attribute spcified by name and namespaceURI.
    723. Returns TRUE on success and FALSE on failure */
    724. PHP_METHOD(xmlreader, moveToAttributeNs)
    727.     int name_len=0, ns_uri_len=0, retval;
    728.     xmlreader_object *intern;
    731.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «ss», &name, &name_len, &ns_uri, &ns_uri_len) == FAILURE) {
    735.     if (name_len == 0 || ns_uri_len == 0) {
    736.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Attribute Name and Namespace URI cannot be empty»);
    742.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    743.     if (intern && intern->ptr) {
    744.         retval = xmlTextReaderMoveToAttributeNs(intern->ptr, (xmlChar *)name, (xmlChar *)ns_uri);
    754. /* {{{ proto boolean XMLReader::moveToElement()
    755. Moves the position of the current instance to the node that contains the current Attribute node. */
    756. PHP_METHOD(xmlreader, moveToElement)
    758.     php_xmlreader_no_arg(INTERNAL_FUNCTION_PARAM_PASSTHRU, xmlTextReaderMoveToElement);
    762. /* {{{ proto boolean XMLReader::moveToFirstAttribute()
    763. Moves the position of the current instance to the first attribute associated with the current node. */
    764. PHP_METHOD(xmlreader, moveToFirstAttribute)
    766.     php_xmlreader_no_arg(INTERNAL_FUNCTION_PARAM_PASSTHRU, xmlTextReaderMoveToFirstAttribute);
    770. /* {{{ proto boolean XMLReader::moveToNextAttribute()
    771. Moves the position of the current instance to the next attribute associated with the current node. */
    772. PHP_METHOD(xmlreader, moveToNextAttribute)
    774.     php_xmlreader_no_arg(INTERNAL_FUNCTION_PARAM_PASSTHRU, xmlTextReaderMoveToNextAttribute);
    778. /* {{{ proto boolean XMLReader::read()
    779. Moves the position of the current instance to the next node in the stream. */
    780. PHP_METHOD(xmlreader, read)
    784.     xmlreader_object *intern;
    787.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    788.     if (intern != NULL && intern->ptr != NULL) {
    789.         retval = xmlTextReaderRead(intern->ptr);
    791.             php_error_docref(NULL TSRMLS_CC, E_WARNING, «An Error Occured while reading»);
    798.     php_error_docref(NULL TSRMLS_CC, E_WARNING, «Load Data before trying to read»);
    803. /* {{{ proto boolean XMLReader::next([string localname])
    804. Moves the position of the current instance to the next node in the stream. */
    805. PHP_METHOD(xmlreader, next)
    809.     xmlreader_object *intern;
    812.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «|s», &name, &name_len) == FAILURE) {
    817.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    818.     if (intern != NULL && intern->ptr != NULL) {
    819. #if LIBXML_VERSION <= 20617
    820.         /* Bug in libxml prevents a next in certain cases when positioned on end of element */
    821.         if (xmlTextReaderNodeType(intern->ptr) == XML_READER_TYPE_END_ELEMENT) {
    822.             retval = xmlTextReaderRead(intern->ptr);
    825.         retval = xmlTextReaderNext(intern->ptr);
    826.         while (name != NULL && retval == 1) {
    827.             if (xmlStrEqual(xmlTextReaderConstLocalName(intern->ptr), (xmlChar *)name)) {
    830.             retval = xmlTextReaderNext(intern->ptr);
    833.             php_error_docref(NULL TSRMLS_CC, E_WARNING, «An Error Occured while reading»);
    840.     php_error_docref(NULL TSRMLS_CC, E_WARNING, «Load Data before trying to read»);
    845. /* {{{ proto boolean XMLReader::open(string URI [, string encoding [, int options]])
    846. Sets the URI that the the XMLReader will parse. */
    847. PHP_METHOD(xmlreader, open)
    850.     int source_len = 0, encoding_len = 0;
    852.     xmlreader_object *intern = NULL;
    853.     char *source, *valid_file = NULL;
    855.     char resolved_path[MAXPATHLEN + 1];
    856.     xmlTextReaderPtr reader = NULL;
    858.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «s|s!l», &source, &source_len, &encoding, &encoding_len, &options) == FAILURE) {
    864.         if (! instanceof_function(Z_OBJCE_P(id), xmlreader_class_entry TSRMLS_CC)) {
    867.             intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    868.             xmlreader_free_resources(intern);
    873.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Empty string supplied as input»);
    877.     valid_file = _xmlreader_get_valid_file_path(source, resolved_path, MAXPATHLEN  TSRMLS_CC);
    880.         reader = xmlReaderForFile(valid_file, encoding, options);
    884.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Unable to open source data»);
    889.         object_init_ex(return_value, xmlreader_class_entry);
    890.         intern = (xmlreader_object *)zend_objects_get_address(return_value TSRMLS_CC);
    902. /* Not Yet Implemented in libxml — functions exist just not coded
    903. PHP_METHOD(xmlreader, resetState)
    909. #if LIBXML_VERSION >= 20620
    910. /* {{{ proto string XMLReader::readInnerXml()
    911. Reads the contents of the current node, including child nodes and markup. */
    912. PHP_METHOD(xmlreader, readInnerXml)
    914.     php_xmlreader_no_arg_string(INTERNAL_FUNCTION_PARAM_PASSTHRU, xmlTextReaderReadInnerXml);
    918. /* {{{ proto boolean XMLReader::readOuterXml()
    919. Reads the contents of the current node, including child nodes and markup. */
    920. PHP_METHOD(xmlreader, readOuterXml)
    922.     php_xmlreader_no_arg_string(INTERNAL_FUNCTION_PARAM_PASSTHRU, xmlTextReaderReadOuterXml);
    926. /* {{{ proto boolean XMLReader::readString()
    927. Reads the contents of an element or a text node as a string. */
    928. PHP_METHOD(xmlreader, readString)
    930.     php_xmlreader_no_arg_string(INTERNAL_FUNCTION_PARAM_PASSTHRU, xmlTextReaderReadString);
    934. /* {{{ proto boolean XMLReader::setSchema(string filename)
    935. Use W3C XSD schema to validate the document as it is processed. Activation is only possible before the first Read(). */
    936. PHP_METHOD(xmlreader, setSchema)
    938. #ifdef LIBXML_SCHEMAS_ENABLED
    940.     int source_len = 0, retval = -1;
    941.     xmlreader_object *intern;
    944.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «s!», &source, &source_len) == FAILURE) {
    948.     if (source != NULL && !source_len) {
    949.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Schema data source is required»);
    955.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    956.     if (intern && intern->ptr) {
    957.         retval = xmlTextReaderSchemaValidate(intern->ptr, source);
    964.     php_error_docref(NULL TSRMLS_CC, E_WARNING, «Unable to set schema. This must be set prior to reading or schema contains errors.»);
    968.     php_error_docref(NULL TSRMLS_CC, E_WARNING, «No Schema support built into libxml.»);
    976. /* {{{ proto boolean XMLReader::setParserProperty(int property, boolean value)
    977. Sets parser property (one of the parser option constants).
    978. Properties must be set after open() or XML() and before the first read() is called */
    979. PHP_METHOD(xmlreader, setParserProperty)
    985.     xmlreader_object *intern;
    987.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «lb», &property, &value) == FAILURE) {
    993.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    994.     if (intern && intern->ptr) {
    995.         retval = xmlTextReaderSetParserProp(intern->ptr,property, value);
    998.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Invalid parser property»);
    1006. /* {{{ proto boolean XMLReader::setRelaxNGSchema(string filename)
    1007. Sets the string that the the XMLReader will parse. */
    1008. PHP_METHOD(xmlreader, setRelaxNGSchema)
    1010.     php_xmlreader_set_relaxng_schema(INTERNAL_FUNCTION_PARAM_PASSTHRU, XMLREADER_LOAD_FILE);
    1014. /* {{{ proto boolean XMLReader::setRelaxNGSchemaSource(string source)
    1015. Sets the string that the the XMLReader will parse. */
    1016. PHP_METHOD(xmlreader, setRelaxNGSchemaSource)
    1018.     php_xmlreader_set_relaxng_schema(INTERNAL_FUNCTION_PARAM_PASSTHRU, XMLREADER_LOAD_STRING);
    1024.             xmlTextReaderSetSchema  (xmlTextReaderPtr reader,
    1028. /* {{{ proto boolean XMLReader::XML(string source [, string encoding [, int options]])
    1029. Sets the string that the the XMLReader will parse. */
    1030. PHP_METHOD(xmlreader, XML)
    1033.     int source_len = 0, encoding_len = 0;
    1035.     xmlreader_object *intern = NULL;
    1036.     char *source, *uri = NULL, *encoding = NULL;
    1037.     int resolved_path_len, ret = 0;
    1038.     char *directory=NULL, resolved_path[MAXPATHLEN];
    1039.     xmlParserInputBufferPtr inputbfr;
    1042.     if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, «s|s!l», &source, &source_len, &encoding, &encoding_len, &options) == FAILURE) {
    1047.     if (id != NULL && ! instanceof_function(Z_OBJCE_P(id), xmlreader_class_entry TSRMLS_CC)) {
    1051.         intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    1052.         xmlreader_free_resources(intern);
    1056.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Empty string supplied as input»);
    1060.     inputbfr = xmlParserInputBufferCreateMem(source, source_len, XML_CHAR_ENCODING_NONE);
    1063. /* Get the URI of the current script so that we can set the base directory in libxml */
    1065.         directory = VCWD_GETCWD(resolved_path, MAXPATHLEN);
    1067.         directory = VCWD_GETWD(resolved_path);
    1070.             resolved_path_len = strlen(resolved_path);
    1071.             if (resolved_path[resolved_path_len — 1] != DEFAULT_SLASH) {
    1072.                 resolved_path[resolved_path_len] = DEFAULT_SLASH;
    1073.                 resolved_path[++resolved_path_len] = »;
    1075.             uri = (char *) xmlCanonicPath((const xmlChar *) resolved_path);
    1077.         reader = xmlNewTextReader(inputbfr, uri);
    1082. #if LIBXML_VERSION >= 20628
    1083.             ret = xmlTextReaderSetup(reader, NULL, uri, encoding, options);
    1087.                     object_init_ex(return_value, xmlreader_class_entry);
    1088.                     intern = (xmlreader_object *)zend_objects_get_address(return_value TSRMLS_CC);
    1092.                 intern->input = inputbfr;
    1100.         xmlFreeParserInputBuffer(inputbfr);
    1102.     php_error_docref(NULL TSRMLS_CC, E_WARNING, «Unable to load source data»);
    1107. /* {{{ proto boolean XMLReader::expand()
    1108. Moves the position of the current instance to the next node in the stream. */
    1109. PHP_METHOD(xmlreader, expand)
    1112.     zval *id, *rv = NULL, *basenode = NULL;
    1114.     xmlreader_object *intern;
    1117.     php_libxml_node_object *domobj = NULL;
    1119.     if (zend_parse_method_parameters(ZEND_NUM_ARGS() TSRMLS_CC, getThis(), «O|O!», &id, xmlreader_class_entry, &basenode, dom_node_class_entry) == FAILURE) {
    1124.         NODE_GET_OBJ(node, basenode, xmlNodePtr, domobj);
    1128.     intern = (xmlreader_object *)zend_object_store_get_object(id TSRMLS_CC);
    1130.     if (intern && intern->ptr) {
    1131.         node = xmlTextReaderExpand(intern->ptr);
    1134.             php_error_docref(NULL TSRMLS_CC, E_WARNING, «An Error Occured while expanding «);
    1137.             nodec = xmlDocCopyNode(node, docp, 1);
    1139.                 php_error_docref(NULL TSRMLS_CC, E_NOTICE, «Cannot expand this node type»);
    1142.                 DOM_RET_OBJ(rv, nodec, &ret, (dom_object *)domobj);
    1146.         php_error_docref(NULL TSRMLS_CC, E_WARNING, «Load Data before trying to expand»);
    1150.     php_error(E_WARNING, «DOM support is not enabled»);
    1156. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_close, 0)
    1159. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_getAttribute, 0)
    1163. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_getAttributeNo, 0)
    1167. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_getAttributeNs, 0)
    1169.     ZEND_ARG_INFO(0, namespaceURI)
    1172. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_getParserProperty, 0)
    1173.     ZEND_ARG_INFO(0, property)
    1176. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_isValid, 0)
    1179. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_lookupNamespace, 0)
    1183. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_moveToAttribute, 0)
    1187. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_moveToAttributeNo, 0)
    1191. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_moveToAttributeNs, 0)
    1193.     ZEND_ARG_INFO(0, namespaceURI)
    1196. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_moveToElement, 0)
    1199. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_moveToFirstAttribute, 0)
    1202. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_moveToNextAttribute, 0)
    1205. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_read, 0)
    1208. ZEND_BEGIN_ARG_INFO_EX(arginfo_xmlreader_next, 0, 0, 0)
    1209.     ZEND_ARG_INFO(0, localname)
    1212. ZEND_BEGIN_ARG_INFO_EX(arginfo_xmlreader_open, 0, 0, 1)
    1214.     ZEND_ARG_INFO(0, encoding)
    1215.     ZEND_ARG_INFO(0, options)
    1218. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_readInnerXml, 0)
    1221. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_readOuterXml, 0)
    1224. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_readString, 0)
    1227. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_setSchema, 0)
    1228.     ZEND_ARG_INFO(0, filename)
    1231. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_setParserProperty, 0)
    1232.     ZEND_ARG_INFO(0, property)
    1236. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_setRelaxNGSchema, 0)
    1237.     ZEND_ARG_INFO(0, filename)
    1240. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_setRelaxNGSchemaSource, 0)
    1244. ZEND_BEGIN_ARG_INFO_EX(arginfo_xmlreader_XML, 0, 0, 1)
    1246.     ZEND_ARG_INFO(0, encoding)
    1247.     ZEND_ARG_INFO(0, options)
    1250. ZEND_BEGIN_ARG_INFO(arginfo_xmlreader_expand, 0)
    1254. static const zend_function_entry xmlreader_functions[] = {
    1255.     PHP_ME(xmlreader, close, arginfo_xmlreader_close, ZEND_ACC_PUBLIC)
    1256.     PHP_ME(xmlreader, getAttribute, arginfo_xmlreader_getAttribute, ZEND_ACC_PUBLIC)
    1257.     PHP_ME(xmlreader, getAttributeNo, arginfo_xmlreader_getAttributeNo, ZEND_ACC_PUBLIC)
    1258.     PHP_ME(xmlreader, getAttributeNs, arginfo_xmlreader_getAttributeNs, ZEND_ACC_PUBLIC)
    1259.     PHP_ME(xmlreader, getParserProperty, arginfo_xmlreader_getParserProperty, ZEND_ACC_PUBLIC)
    1260.     PHP_ME(xmlreader, isValid, arginfo_xmlreader_isValid, ZEND_ACC_PUBLIC)
    1261.     PHP_ME(xmlreader, lookupNamespace, arginfo_xmlreader_lookupNamespace, ZEND_ACC_PUBLIC)
    1262.     PHP_ME(xmlreader, moveToAttributeNo, arginfo_xmlreader_moveToAttributeNo, ZEND_ACC_PUBLIC)
    1263.     PHP_ME(xmlreader, moveToAttribute, arginfo_xmlreader_moveToAttribute, ZEND_ACC_PUBLIC)
    1264.     PHP_ME(xmlreader, moveToAttributeNs, arginfo_xmlreader_moveToAttributeNs, ZEND_ACC_PUBLIC)
    1265.     PHP_ME(xmlreader, moveToElement, arginfo_xmlreader_moveToElement, ZEND_ACC_PUBLIC)
    1266.     PHP_ME(xmlreader, moveToFirstAttribute, arginfo_xmlreader_moveToFirstAttribute, ZEND_ACC_PUBLIC)
    1267.     PHP_ME(xmlreader, moveToNextAttribute, arginfo_xmlreader_moveToNextAttribute, ZEND_ACC_PUBLIC)
    1268.     PHP_ME(xmlreader, open, arginfo_xmlreader_open, ZEND_ACC_PUBLIC|ZEND_ACC_ALLOW_STATIC)
    1269.     PHP_ME(xmlreader, read, arginfo_xmlreader_read, ZEND_ACC_PUBLIC)
    1270.     PHP_ME(xmlreader, next, arginfo_xmlreader_next, ZEND_ACC_PUBLIC)
    1271. #if LIBXML_VERSION >= 20620
    1272.     PHP_ME(xmlreader, readInnerXml, arginfo_xmlreader_readInnerXml, ZEND_ACC_PUBLIC)
    1273.     PHP_ME(xmlreader, readOuterXml, arginfo_xmlreader_readOuterXml, ZEND_ACC_PUBLIC)
    1274.     PHP_ME(xmlreader, readString, arginfo_xmlreader_readString, ZEND_ACC_PUBLIC)
    1275.     PHP_ME(xmlreader, setSchema, arginfo_xmlreader_setSchema, ZEND_ACC_PUBLIC)
    1277. /* Not Yet Implemented though defined in libxml as of 2.6.9dev
    1278.     PHP_ME(xmlreader, resetState, NULL, ZEND_ACC_PUBLIC)
    1280.     PHP_ME(xmlreader, setParserProperty, arginfo_xmlreader_setParserProperty, ZEND_ACC_PUBLIC)
    1281.     PHP_ME(xmlreader, setRelaxNGSchema, arginfo_xmlreader_setRelaxNGSchema, ZEND_ACC_PUBLIC)
    1282.     PHP_ME(xmlreader, setRelaxNGSchemaSource, arginfo_xmlreader_setRelaxNGSchemaSource, ZEND_ACC_PUBLIC)
    1283.     PHP_ME(xmlreader, XML, arginfo_xmlreader_XML, ZEND_ACC_PUBLIC|ZEND_ACC_ALLOW_STATIC)
    1284.     PHP_ME(xmlreader, expand, arginfo_xmlreader_expand, ZEND_ACC_PUBLIC)
    1288. /* {{{ PHP_MINIT_FUNCTION
    1290. PHP_MINIT_FUNCTION(xmlreader)
    1295.     memcpy(&xmlreader_object_handlers, zend_get_std_object_handlers(), sizeof(zend_object_handlers));
    1296.     xmlreader_object_handlers.read_property = xmlreader_read_property;
    1297.     xmlreader_object_handlers.write_property = xmlreader_write_property;
    1298.     xmlreader_object_handlers.get_property_ptr_ptr = xmlreader_get_property_ptr_ptr;
    1300.     INIT_CLASS_ENTRY(ce, «XMLReader», xmlreader_functions);
    1301.     ce.create_object = xmlreader_objects_new;
    1302.     xmlreader_class_entry = zend_register_internal_class(&ce TSRMLS_CC);
    1304.     zend_hash_init(&xmlreader_prop_handlers, 0, NULL, NULL, 1);
    1305.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «attributeCount», xmlTextReaderAttributeCount, NULL, IS_LONG TSRMLS_CC);
    1306.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «baseURI», NULL, xmlTextReaderConstBaseUri, IS_STRING TSRMLS_CC);
    1307.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «depth», xmlTextReaderDepth, NULL, IS_LONG TSRMLS_CC);
    1308.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «hasAttributes», xmlTextReaderHasAttributes, NULL, IS_BOOL TSRMLS_CC);
    1309.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «hasValue», xmlTextReaderHasValue, NULL, IS_BOOL TSRMLS_CC);
    1310.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «isDefault», xmlTextReaderIsDefault, NULL, IS_BOOL TSRMLS_CC);
    1311.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «isEmptyElement», xmlTextReaderIsEmptyElement, NULL, IS_BOOL TSRMLS_CC);
    1312.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «localName», NULL, xmlTextReaderConstLocalName, IS_STRING TSRMLS_CC);
    1313.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «name», NULL, xmlTextReaderConstName, IS_STRING TSRMLS_CC);
    1314.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «namespaceURI», NULL, xmlTextReaderConstNamespaceUri, IS_STRING TSRMLS_CC);
    1315.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «nodeType», xmlTextReaderNodeType, NULL, IS_LONG TSRMLS_CC);
    1316.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «prefix», NULL, xmlTextReaderConstPrefix, IS_STRING TSRMLS_CC);
    1317.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «value», NULL, xmlTextReaderConstValue, IS_STRING TSRMLS_CC);
    1318.     xmlreader_register_prop_handler(&xmlreader_prop_handlers, «xmlLang», NULL, xmlTextReaderConstXmlLang, IS_STRING TSRMLS_CC);
    1320.     /* Constants for NodeType — cannot define common types to share with dom as there are differences in these types */
    1322.     REGISTER_XMLREADER_CLASS_CONST_LONG(«NONE», XML_READER_TYPE_NONE);
    1323.     REGISTER_XMLREADER_CLASS_CONST_LONG(«ELEMENT»,  XML_READER_TYPE_ELEMENT);
    1324.     REGISTER_XMLREADER_CLASS_CONST_LONG(«ATTRIBUTE»,    XML_READER_TYPE_ATTRIBUTE);
    1325.     REGISTER_XMLREADER_CLASS_CONST_LONG(«TEXT», XML_READER_TYPE_TEXT);
    1326.     REGISTER_XMLREADER_CLASS_CONST_LONG(«CDATA»,    XML_READER_TYPE_CDATA);
    1327.     REGISTER_XMLREADER_CLASS_CONST_LONG(«ENTITY_REF»,   XML_READER_TYPE_ENTITY_REFERENCE);
    1328.     REGISTER_XMLREADER_CLASS_CONST_LONG(«ENTITY»,   XML_READER_TYPE_ENTITY);
    1329.     REGISTER_XMLREADER_CLASS_CONST_LONG(«PI»,   XML_READER_TYPE_PROCESSING_INSTRUCTION);
    1330.     REGISTER_XMLREADER_CLASS_CONST_LONG(«COMMENT»,  XML_READER_TYPE_COMMENT);
    1331.     REGISTER_XMLREADER_CLASS_CONST_LONG(«DOC»,  XML_READER_TYPE_DOCUMENT);
    1332.     REGISTER_XMLREADER_CLASS_CONST_LONG(«DOC_TYPE», XML_READER_TYPE_DOCUMENT_TYPE);
    1333.     REGISTER_XMLREADER_CLASS_CONST_LONG(«DOC_FRAGMENT», XML_READER_TYPE_DOCUMENT_FRAGMENT);
    1334.     REGISTER_XMLREADER_CLASS_CONST_LONG(«NOTATION», XML_READER_TYPE_NOTATION);
    1335.     REGISTER_XMLREADER_CLASS_CONST_LONG(«WHITESPACE»,   XML_READER_TYPE_WHITESPACE);
    1336.     REGISTER_XMLREADER_CLASS_CONST_LONG(«SIGNIFICANT_WHITESPACE»,   XML_READER_TYPE_SIGNIFICANT_WHITESPACE);
    1337.     REGISTER_XMLREADER_CLASS_CONST_LONG(«END_ELEMENT»,  XML_READER_TYPE_END_ELEMENT);
    1338.     REGISTER_XMLREADER_CLASS_CONST_LONG(«END_ENTITY»,   XML_READER_TYPE_END_ENTITY);
    1339.     REGISTER_XMLREADER_CLASS_CONST_LONG(«XML_DECLARATION»,  XML_READER_TYPE_XML_DECLARATION);
    1341.     /* Constants for Parser options */
    1342.     REGISTER_XMLREADER_CLASS_CONST_LONG(«LOADDTD»,  XML_PARSER_LOADDTD);
    1343.     REGISTER_XMLREADER_CLASS_CONST_LONG(«DEFAULTATTRS», XML_PARSER_DEFAULTATTRS);
    1344.     REGISTER_XMLREADER_CLASS_CONST_LONG(«VALIDATE», XML_PARSER_VALIDATE);
    1345.     REGISTER_XMLREADER_CLASS_CONST_LONG(«SUBST_ENTITIES»,   XML_PARSER_SUBST_ENTITIES);
    1347.     /* Constants for Errors when loading — not yet used until we implement custom error handling
    1348.     REGISTER_XMLREADER_CLASS_CONST_LONG(«VALIDITY_WARNING»,     XML_PARSER_SEVERITY_VALIDITY_WARNING,   CONST_CS | CONST_PERSISTENT);
    1349.     REGISTER_XMLREADER_CLASS_CONST_LONG(«VALIDITY_ERROR»,       XML_PARSER_SEVERITY_VALIDITY_ERROR,     CONST_CS | CONST_PERSISTENT);
    1350.     REGISTER_XMLREADER_CLASS_CONST_LONG(«WARNING»,              XML_PARSER_SEVERITY_WARNING,            CONST_CS | CONST_PERSISTENT);
    1351.     REGISTER_XMLREADER_CLASS_CONST_LONG(«ERROR»,                XML_PARSER_SEVERITY_ERROR,              CONST_CS | CONST_PERSISTENT);
    1358. /* {{{ PHP_MSHUTDOWN_FUNCTION
    1360. PHP_MSHUTDOWN_FUNCTION(xmlreader)
    1362.     zend_hash_destroy(&xmlreader_prop_handlers);
    1367. /* {{{ PHP_MINFO_FUNCTION
    1369. PHP_MINFO_FUNCTION(xmlreader)
    1371.     php_info_print_table_start();
    1373.         php_info_print_table_row(2, «XMLReader», «enabled»);
    1375.     php_info_print_table_end();
    1384.  * vim600: noet sw=4 ts=4 fdm=marker
    1385.  * vim<600: noet sw=4 ts=4