PHP XML操作类 xml2array -- 含节点属性

1. 单向xml2array函数

 

function xml2array($contents, $get_attributes=1, $priority = 'tag') 
{
    if(!$contents) return array(); 

    if(!function_exists('xml_parser_create')) {
        //print "'xml_parser_create()' function not found!";
        return array();
    } 

    //Get the XML parser of PHP - PHP must have this module for the parser to work
    $parser = xml_parser_create('');
    xml_parser_set_option($parser, XML_OPTION_TARGET_ENCODING, "UTF-8"); # http://minutillo.com/steve/weblog/2004/6/17/php-xml-and-character-encodings-a-tale-of-sadness-rage-and-data-loss
    xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, 0);
    xml_parser_set_option($parser, XML_OPTION_SKIP_WHITE, 1);
    xml_parse_into_struct($parser, trim($contents), $xml_values);
    xml_parser_free($parser); 

    if(!$xml_values) return;//Hmm... 

    //Initializations
    $xml_array = array();
    $parents = array();
    $opened_tags = array();
    $arr = array(); 

    $current = &$xml_array; //Refference 

    //Go through the tags.
    $repeated_tag_index = array();//Multiple tags with same name will be turned into an array
    foreach($xml_values as $data) {
        unset($attributes,$value);//Remove existing values, or there will be trouble 

        //This command will extract these variables into the foreach scope
        // tag(string), type(string), level(int), attributes(array).
        extract($data);//We could use the array by itself, but this cooler. 

        $result = array();
        $attributes_data = array(); 

        if(isset($value)) {
            if($priority == 'tag') $result = $value;
            else $result['value'] = $value; //Put the value in a assoc array if we are in the 'Attribute' mode
        } 

        //Set the attributes too.
        if(isset($attributes) and $get_attributes) {
            foreach($attributes as $attr => $val) {
                if($priority == 'tag') $attributes_data[$attr] = $val;
                else $result['attr'][$attr] = $val; //Set all the attributes in a array called 'attr'
            }
        } 

        //See tag status and do the needed.
        if($type == "open") {//The starting of the tag '<tag>'
            $parent[$level-1] = &$current;
            if(!is_array($current) or (!in_array($tag, array_keys($current)))) { //Insert New tag
                $current[$tag] = $result;
                if($attributes_data) $current[$tag. '_attr'] = $attributes_data;
                $repeated_tag_index[$tag.'_'.$level] = 1; 

                $current = &$current[$tag]; 

            } else { //There was another element with the same tag name 

                if(isset($current[$tag][0])) {//If there is a 0th element it is already an array
                    $current[$tag][$repeated_tag_index[$tag.'_'.$level]] = $result;
                    $repeated_tag_index[$tag.'_'.$level]++;
                } else {//This section will make the value an array if multiple tags with the same name appear together
                    $current[$tag] = array($current[$tag],$result);//This will combine the existing item and the new item together to make an array
                    $repeated_tag_index[$tag.'_'.$level] = 2; 

                    if(isset($current[$tag.'_attr'])) { //The attribute of the last(0th) tag must be moved as well
                        $current[$tag]['0_attr'] = $current[$tag.'_attr'];
                        unset($current[$tag.'_attr']);
                    } 

                }
                $last_item_index = $repeated_tag_index[$tag.'_'.$level]-1;
                $current = &$current[$tag][$last_item_index];
            } 

        } elseif($type == "complete") { //Tags that ends in 1 line '<tag />'
            //See if the key is already taken.
            if(!isset($current[$tag])) { //New Key
                $current[$tag] = $result;
                $repeated_tag_index[$tag.'_'.$level] = 1;
                if($priority == 'tag' and $attributes_data) $current[$tag. '_attr'] = $attributes_data; 

            } else { //If taken, put all things inside a list(array)
                if(isset($current[$tag][0]) and is_array($current[$tag])) {//If it is already an array... 

                    // ...push the new element into that array.
                    $current[$tag][$repeated_tag_index[$tag.'_'.$level]] = $result; 

                    if($priority == 'tag' and $get_attributes and $attributes_data) {
                        $current[$tag][$repeated_tag_index[$tag.'_'.$level] . '_attr'] = $attributes_data;
                    }
                    $repeated_tag_index[$tag.'_'.$level]++; 

                } else { //If it is not an array...
                    $current[$tag] = array($current[$tag],$result); //...Make it an array using using the existing value and the new value
                    $repeated_tag_index[$tag.'_'.$level] = 1;
                    if($priority == 'tag' and $get_attributes) {
                        if(isset($current[$tag.'_attr'])) { //The attribute of the last(0th) tag must be moved as well 

                            $current[$tag]['0_attr'] = $current[$tag.'_attr'];
                            unset($current[$tag.'_attr']);
                        } 

                        if($attributes_data) {
                            $current[$tag][$repeated_tag_index[$tag.'_'.$level] . '_attr'] = $attributes_data;
                        }
                    }
                    $repeated_tag_index[$tag.'_'.$level]++; //0 and 1 index is already taken
                }
            } 

        } elseif($type == 'close') { //End of tag '</tag>'
            $current = &$parent[$level-1];
        }
    } 

    return($xml_array);
}

 

$priority设置为空的时候，可以获取所有节点属性值。

 

优点： 获取的节点属性不占用数组父级键。

缺点： $priority设置为tag时，获取节点属性值不太理想。

 

 

2. 双向xml2array和array2xml函数

 

<?php 

################################################################################### 
# xml2array: takes raw XML as a parameter (a string) 
# and returns an equivalent PHP data structure 
################################################################################### 
function & xml2array(&$xml,$attr=true){ 
    $xml_parser = &new XML(); 
	$xml_parser->attr = $attr; 
    $data = &$xml_parser->parse($xml); 
    $xml_parser->destruct(); 
    return $data; 
} 
################################################################################### 
# array2xml: serializes any PHP data structure into XML 
# Takes one parameter: the data to serialize. Must be an array. 
################################################################################### 
function & array2xml(&$data, $level = 0, $prior_key = NULL){ 
    if($level == 0){ ob_start(); echo '<?xml version="1.0" ?>',"\n"; } 
    while(list($key, $value) = each($data)) 
        if(!strpos($key, '_attr')) #if it's not an attribute 
            #we don't treat attributes by themselves, so for an empty element 
            # that has attributes you still need to set the element to NULL 

            if(is_array($value) and array_key_exists(0, $value)){ 
                array2xml($value, $level, $key); 
            }else{ 
                $tag = $prior_key ? $prior_key : $key; 
                echo str_repeat("\t", $level),'<',$tag; 
                if(array_key_exists($key.'_attr', $data)){ #if there's an attribute for this element 
                    while(list($attr_name, $attr_value) = each($data[$key.'_attr'])) 
                        echo ' ',$attr_name,'="',htmlspecialchars($attr_value),'"'; 
                    reset($data[$key.'_attr']); 
                } 

                if(is_null($value)) echo " />\n"; 
                elseif(!is_array($value)) echo '>',htmlspecialchars($value),"</$tag>\n"; 
                else echo ">\n",array2xml($value, $level+1),str_repeat("\t", $level),"</$tag>\n"; 
            } 
    reset($data); 
    if($level == 0){ $str = &ob_get_contents(); ob_end_clean(); return $str; } 
} 
################################################################################### 
# XML class: utility class to be used with PHP's XML handling functions 
################################################################################### 
class XML
{ 
    var $parser;   #a reference to the XML parser 
    var $document; #the entire XML structure built up so far 
    var $parent;   #a pointer to the current parent - the parent will be an array 
    var $stack;    #a stack of the most recent parent at each nesting level 
    var $last_opened_tag; #keeps track of the last tag opened. 
	var $attr = true;

    function XML()
	{ 
        $this->parser = &xml_parser_create(); 
        xml_parser_set_option(&$this->parser, XML_OPTION_CASE_FOLDING, false); 
        xml_set_object(&$this->parser, &$this); 
        xml_set_element_handler(&$this->parser, 'open','close'); 
        xml_set_character_data_handler(&$this->parser, 'data'); 
    } 
    function destruct(){ xml_parser_free(&$this->parser); } 
    function & parse(&$data)
	{ 
        $this->document = array(); 
        $this->stack    = array(); 
        $this->parent   = &$this->document; 
        return xml_parse(&$this->parser, &$data, true) ? $this->document : NULL; 
    } 
    function open(&$parser, $tag, $attributes)
	{ 
        $this->data = '';  
		#stores temporary cdata
        $this->last_opened_tag = $tag; 
		#if you've seen this tag before
        if(is_array($this->parent) and array_key_exists($tag,$this->parent))
		{  
		    #if the keys are numeric
			#this is the third or later instance of $tag we've come across 
			if(is_array($this->parent[$tag]) and array_key_exists(0,$this->parent[$tag])) $key = $this->count_numeric_items($this->parent[$tag]); 
            else
			{ 
                #this is the second instance of $tag that we've seen. shift around 
                if(array_key_exists($tag.'_attr',$this->parent))
				{ 
                    $arr = array('0_attr'=>&$this->parent[$tag.'_attr'], &$this->parent[$tag]); 
                    unset($this->parent[$tag.'_attr']); 
                }
				else $arr = array(&$this->parent[$tag]); 
                
                $this->parent[$tag] = &$arr; 
                $key = 1; 
            } 
            $this->parent = &$this->parent[$tag]; 
        }
		else $key = $tag; 

        if($attributes AND $this->attr) $this->parent[$key.'_attr'] = $attributes; 
        $this->parent  = &$this->parent[$key]; 
        $this->stack[] = &$this->parent; 
    } 
    function data(&$parser, $data)
	{ 
		#you don't need to store whitespace in between tags
        if($this->last_opened_tag != NULL) $this->data .= $data; 
    } 
    function close(&$parser, $tag)
	{ 
        if($this->last_opened_tag == $tag)
		{ 
            $this->parent = $this->data; 
            $this->last_opened_tag = NULL; 
        } 
        array_pop($this->stack); 
        if($this->stack) $this->parent = &$this->stack[count($this->stack)-1]; 
    } 
	function count_numeric_items(&$array)
	{ 
		return is_array($array) ? count(array_filter(array_keys($array), 'is_numeric')) : 0; 
	} 
} 

   

 

实例：

 

<?php
include('xml.php');
$data = xml2array($xml);
?> 

 

<?php
include('xml.php');
$xml = array2xml($data);
?> 

 

来源： http://keithdevens.com/software/phpxml

该类已根据来源代码做了修改。

 

如果$attr设置为false，输出的数组中将不包括节点属性值。

 

优点： 获取节点属性值较理想。

缺点： 获取的节点属性占用数组父级键