PHP XML Pull Parser with Array Iterator

Parsing Large XML file using PHP XML Reader

• Files


• demo.xmlArray.class.php


• svn-log.xml


• xmlArray.class.php

demo.xmlArray.class.php

<?php
include_once( 'xmlArray.class.php' );

$oxml = new XMLArray( 'svn-log.xml', 'logentry');
$ret = array();
foreach( $oxml as $k => $logentry )
{
 print_r( $logentry );
}
?>

$logentry = Array(
["logentry"] => Array(
["node"] => "logentry"
["atr"] => Array( ["revision"] => 43372 )
["value"] => Array(
["author"] => Array(
["0"] => Array(
["node"] => "author"
["atr"] =>
["value"] => Array( ["0"] => "user.name")
)
)
["date"] => Array(
["0"] => Array(
["node"] => "date"
["atr"] =>
["value"] => Array( ["0"] => "2009-11-25T06:02:34.092477Z" )
)
)
["msg"] => Array(
["0"] => Array(
["node"] => "msg"
["atr"] =>
["value"] => Array()
)
)
)
)
)

svn-log.xml

<?xml version="1.0"?>
<log>
 <logentry revision="58245">
  <author>User.Name</author>
  <date>2010-09-02T14:08:31.878082Z</date>
  <paths>
   <path kind="" action="A">/code/google/path/svnlog-xml.php</path>
   <path kind="" action="A">/code/google/path/svnlog.sh</path>
   <path kind="" action="A">/code/google/path/svndiff.sh</path>
   <path kind="" action="A">/code/google/path/xmlArray.class.php</path>
  </paths>
  <msg>added first time </msg>
 </logentry>
 <logentry revision="58244">
  <author>User.Name</author>
  <date>2010-09-02T14:07:16.389655Z</date>
  <paths>
   <path kind="" action="A">/code/google/path/svn-script</path>
  </paths>
  <msg>added first time </msg>
 </logentry>
 <logentry revision="58243">
  <author>User.Name</author>
  <date>2010-09-02T14:05:58.198520Z</date>
  <paths>
   <path kind="" action="M">/code/google/path/facebook/index.php</path>
  </paths>
  <msg>dd</msg>
 </logentry>
 <logentry revision="50577">
  <author>User.Name</author>
  <date>2010-03-26T07:24:53.579939Z</date>
  <paths>
   <path kind="" action="M">/code/google/path/facebook/comment.php</path>
  </paths>
  <msg>Add code to get users wall </msg>
 </logentry>
</log>

xmlArray.class.php

<?php
//
//text.xml
//-----------
//<locations><location><a q="qq">1</a><b></b></location><location><c>3</c><d>4</d></location><location><e>5</e><f a="aa" b="ab">6</f><g>7</g><g>77</g><hi><h>8</h><i>9A</i><i>9B</i><i>9C</i></hi></locations>
//
//$o = new XMLIArray( 'test.xml', 'location');
//$a=array();
//foreach( $o as $k => $v){
// $a[$k]=$v;
//}


class XMLArray implements Iterator
{
 protected $xmlFilePath;
 protected $oXR=null;
 protected $tag2Search;
 protected $arrCurent;
 protected $firstFound = false;
 protected $position = 0;
 protected $readCalled = false;

 public function __construct( $xmlFilePath,  $tag2Search , $skipCount=0)
 {
  $this->xmlFilePath = $xmlFilePath;
  $this->tag2Search = $tag2Search;

  $this->arrCurent = array();
  $this->oXR = new XMLReader();

  $this->oXR->open( $this->xmlFilePath );

  #$this->debug( 'START',1 );

  if( 0 < $skipCount )
  {
   for($iloop=0; $iloop <= $skipCount; $iloop++)
   {
    $this->arrCurent = $this->read( $this->tag2Search );
   }
  }
 }

 public function read( $tag2Search='' , $depth=0 )
 {
  $this->readCalled = true;

  if( '' == $tag2Search )
  {
   $tag2Search = $this->tag2Search;
  }

  $ret = array();
  $atr = false;

  $currNode = $this->oXR->name;

  while( $this->oXR->read() )
  {
   $val = $this->oXR->value;
   switch ($this->oXR->nodeType)
   {
    case XMLReader::ELEMENT:

     $currNode = $this->oXR->name;
     #$this->debug( $currNode . ' :: start');

     if( false == $this->firstFound )
     {
      if( $tag2Search == $currNode )
      {


       $this->firstFound = 1;
       $depth = $this->oXR->depth;
       #$this->debug( "\t {$currNode} :: Depth-Update => " . $depth );
      }
     }


     if( false == $this->firstFound )
     {

      continue;
     }

     $atr = $this->getAttr();
     #$this->debug( "\t {$currNode} :: atr   => {$atr} ");
     #$this->debug( "\t {$currNode} :: depth => {$depth}");
     #$this->debug( "\t {$currNode} :: oXR->depth => {$this->oXR->depth}");



     if( $depth < $this->oXR->depth )
     {
      $childVal = $this->read( $currNode, $this->oXR->depth);

      if( isset($ret[$tag2Search]['value']) )
      {
       $ret[$tag2Search]['value'][$currNode][] = array( 'node'=>$currNode, 'atr'=>$atr, 'value'=> $childVal);
      }
      else
      {
       $ret[$currNode][] = array(  'node'=>$currNode, 'atr'=>$atr,  'value'=> $childVal);
      }

     }
     else
     {
      $ret[$tag2Search] = array( 'node'=>$currNode, 'atr'=>$atr,  'value'=> '');

     }
     break;

    case XMLReader::TEXT:
    case XMLReader::CDATA:
    case XMLReader::WHITESPACE:

     if($this->firstFound )
     {
      return array( $val  );
     }
     break;

    case XMLReader::END_ELEMENT:

     $currNode = $this->oXR->name;

     if( $tag2Search == $currNode )
     {

      if( $tag2Search ==   $this->tag2Search)
      {
       $this->firstFound = false;
      }
      return $ret;
     }
     break;

    default:
     break;
   }
  }

  return false;
 }

 public function current()
 {
  if( false == $this->readCalled )
  {
   $this->arrCurent = $this->read();
  }

  $ret = $this->arrCurent ;
  $this->arrCurent = array();
  $this->arrCurent = $this->read();

  return $ret;
 }

 public function key()
 {
  return $this->position;
 }

 public function next()
 {
  ++$this->position;
 }

 public function rewind()
 {
  $this->position = 0;
 }

 public function valid()
 {
  if( false == $this->readCalled )
  {
   $this->arrCurent = $this->read();
  }
  return !empty( $this->arrCurent );
 }

 public function getAttr()
 {
  $atr=false;

  try
  {
   if( $this->oXR->hasAttributes )
   {
    $atr=array();

    while( $this->oXR->moveToNextAttribute() )
    {
     $atr[$this->oXR->name] = $this->oXR->value;
    }

    $this->oXR->moveToElement();
   }


  }
  catch( Exception $e )
  {
   $this->debug( 'Error' . var_export( $e, true ) );
  }

  //  print_r( $atr );
  //  $atr = var_export( $atr, true);
  //  $atr = str_replace( "\n", '',$atr );
  //  $atr = str_replace( "\t", '',$atr );
  //  $atr = str_replace( " ", '',$atr );

  return $atr;
 }

 protected function debug($s , $overWrite=false)
 {
  #echo "\n".$s;
  return ;
  if( $overWrite )
  {
   file_put_contents( 'log'.basename(__FILE__).'.log', "\n". $s  );
  }
  else
  {
   file_put_contents( 'log'.basename(__FILE__).'.log', "\n". $s , FILE_APPEND );
  }
 }
}
?>

Usefull Links:
http://php.net/manual/en/book.xmlreader.php
http://www.ibm.com/developerworks/library/x-pullparsingphp.html