用 PHP5 轻松解析 XML

(编辑：jimmy 日期: 2024/11/19 浏览：3 次 )

用 sax 方式的时候，要自己构建3个函数，而且要直接用这三的函数来返回数据，要求较强的逻辑。在处理不同结构的 xml 的时候，还要重新进行构造这三个函数，麻烦！

用 dom 方式，倒是好些，但是他把每个节点都看作是一个 node,，操作起来要写好多的代码，麻烦！

网上有好多的开源的 xml 解析的类库，以前看过几个，但是心里总是觉得不踏实，感觉总是跟在别人的屁股后面。

这几天在搞 Java，挺累的，所以决定换换脑袋，写点 PHP 代码，为了防止以后 XML 解析过程再令我犯难，就花了一天的时间写了下面一个 XML 解析的类，于是就有了下面的东西。

实现方式是通过包装“sax方式的解析结果”来实现的。总的来说，对于我个人来说挺实用的，性能也还可以，基本上可以完成大多数的处理要求。

功能:
1\ 对基本的 XML 文件的节点进行查询 / 添加 / 修改 / 删除工作。
2\ 导出 XML 文件的所有数据到一个数组里面。
3\ 整个设计采用了 OO 方式,在操作结果集的时候，使用方法类似于 dom

缺点:
1\ 每个节点最好都带有一个id(看后面的例子)，每个“节点名字”=“节点的标签_节点的id”，如果这个 id 值没有设置，程序将自动给他产生一个 id，这个 id 就是这个节点在他的上级节点中的位置编号，从 0 开始。
2\ 查询某个节点的时候可以通过用“|”符号连接“节点名字”来进行。这些“节点名字”都是按顺序写好的上级节点的名字。

使用说明：
运行下面的例子，在执行结果页面上可以看到函数的使用说明

代码是通过 PHP5 来实现的，在 PHP4 中无法正常运行。

由于刚刚写完，所以没有整理文档，下面的例子演示的只是一部分的功能，代码不是很难，要是想知道更多的功能，可以研究研究源代码。

目录结构:

test.php
test.xml
xml / SimpleDocumentBase.php
xml / SimpleDocumentNode.php
xml / SimpleDocumentRoot.php
xml / SimpleDocumentParser.php 文件:test.xml

<?xml version="1.0" encoding="GB2312"?>
<shop>
<name>华联</name>
<address>北京长安街－9999号</address>
<desc>连锁超市</desc>
<cat id="food">
<goods id="food11">
 <name>food11</name>
 <price>12.90</price>
</goods>
<goods id="food12">
 <name>food12</name>
 <price>22.10</price>
 <desc creator="hahawen">好东西推荐</desc>
</goods>
</cat>
<cat>
<goods id="tel21">
 <name>tel21</name>
 <price>1290</price>
</goods>
</cat>
<cat id="coat">
<goods id="coat31">
 <name>coat31</name>
 <price>112</price>
</goods>
<goods id="coat32">
 <name>coat32</name>
 <price>45</price>
</goods>
</cat>
<special id="hot">
<goods>
 <name>hot41</name>
 <price>99</price>
</goods>
</special>
</shop>

文件:test.php

<?php
require_once "xml/SimpleDocumentParser.php";
require_once "xml/SimpleDocumentBase.php";
require_once "xml/SimpleDocumentRoot.php";
require_once "xml/SimpleDocumentNode.php"; $test = new SimpleDocumentParser();
$test->parse("test.xml");
$dom = $test->getSimpleDocument(); echo "<pre>"; echo "<hr>";
echo "下面是通过函数getSaveData()返回的整个xml数据的数组";
echo "<hr>";
print_r($dom->getSaveData()); echo "<hr>";
echo "下面是通过setValue()函数，给给根节点添加信息，添加后显示出结果xml文件的内容";
echo "<hr>";
$dom->setValue("telphone", "123456789");
echo htmlspecialchars($dom->getSaveXml()); echo "<hr>";
echo "下面是通过getNode()函数，返回某一个分类下的所有商品的信息";
echo "<hr>";
$obj = $dom->getNode("cat_food");
$nodeList = $obj->getNode();
foreach($nodeList as $node){
 $data = $node->getValue();
 echo "商品名：".$data[name]." ";
 print_R($data);
 print_R($node->getAttribute());
} echo "<hr>";
echo "下面是通过findNodeByPath()函数，返回某一商品的信息";
echo "<hr>";
$obj = $dom->findNodeByPath("cat_food|goods_food11");
if(!is_object($obj)){
 echo "该商品不存在";
}else{
 $data = $obj->getValue();
 echo "商品名：".$data[name]." ";
 print_R($data);
 print_R($obj->getAttribute());
} echo "<hr>";
echo "下面是通过setValue()函数，给商品\"food11\"添加属性, 然后显示添加后的结果";
echo "<hr>";
$obj = $dom->findNodeByPath("cat_food|goods_food11");
$obj->setValue("leaveword", array("value"=>"这个商品不错", "attrs"=>array("author"=>"hahawen", "date"=>date('Y-m-d'))));
echo htmlspecialchars($dom->getSaveXml()); echo "<hr>";
echo "下面是通过removeValue()/removeAttribute()函数，给商品\"food11\"改变和删除属性, 然后显示操作后的结果";
echo "<hr>";
$obj = $dom->findNodeByPath("cat_food|goods_food12");
$obj->setValue("name", "new food12");
$obj->removeValue("desc");
echo htmlspecialchars($dom->getSaveXml()); echo "<hr>";
echo "下面是通过createNode()函数，添加商品, 然后显示添加后的结果";
echo "<hr>";
$obj = $dom->findNodeByPath("cat_food");
$newObj = $obj->createNode("goods", array("id"=>"food13"));
$newObj->setValue("name", "food13");
$newObj->setValue("price", 100);
echo htmlspecialchars($dom->getSaveXml()); echo "<hr>";
echo "下面是通过removeNode()函数，删除商品, 然后显示删除后的结果";
echo "<hr>";
$obj = $dom->findNodeByPath("cat_food");
$obj->removeNode("goods_food12");
echo htmlspecialchars($dom->getSaveXml());
?> 文件:SimpleDocumentParser.php <?php
/**
*================================================
*
* @author hahawen(大龄青年) * @since 2004-12-04
* @copyright Copyright (c) 2004, NxCoder Group
*
*================================================
*/
/**
* class SimpleDocumentParser
* use SAX parse xml file, and build SimpleDocumentObject
* all this pachage's is work for xml file, and method is action as DOM.
*
* @package SmartWeb.common.xml
* @version 1.0
*/
class SimpleDocumentParser
{ private $domRootObject = null; private $currentNO = null;
 private $currentName = null;
 private $currentValue = null;
 private $currentAttribute = null; public
 function getSimpleDocument()
 {
 return $this->domRootObject;
 } public function parse($file)
 {
 $xmlParser = xml_parser_create();
 xml_parser_set_option($xmlParser,XML_OPTION_CASE_FOLDING,
 0);
 xml_parser_set_option($xmlParser,XML_OPTION_SKIP_WHITE, 1);
 xml_parser_set_option($xmlParser,
 XML_OPTION_TARGET_ENCODING, 'UTF-8');
 xml_set_object($xmlParser, $this); xml_set_element_handler($xmlParser, "startElement", "endElement");
 xml_set_character_data_handler($xmlParser,
 "characterData"); if (!xml_parse($xmlParser, file_get_contents($file))) die(sprintf("XML error: %s at line %d", xml_error_string(xml_get_error_code($xmlParser)),
 xml_get_current_line_number($xmlParser))); xml_parser_free($xmlParser); } private function startElement($parser, $name, $attrs)
 {
 $this->currentName = $name;
 $this->currentAttribute = $attrs;
 if($this->currentNO == null)
 {
 $this->domRootObject = new SimpleDocumentRoot($name); $this->currentNO = $this->domRootObject;
 }
 else
 {
 $this->currentNO = $this->currentNO->createNode($name, $attrs); }
 } private function endElement($parser, $name)
 {
 if($this->currentName==$name) {
 $tag = $this->currentNO->getSeq();
 $this->currentNO = $this->currentNO->getPNodeObject();
 if($this->currentAttribute!=null && sizeof($this->currentAttribute)>0)
 $this->currentNO->setValue($name, array('value'=>$this->currentValue, 'attrs'=>$this->currentAttribute));
 else
 $this->currentNO->setValue($name, $this->currentValue); $this->currentNO->removeNode($tag);
 }
 else
 {
 $this->currentNO = (is_a($this->currentNO, 'SimpleDocumentRoot'))? null:
 $this->currentNO->getPNodeObject();
 }
 } private function characterData($parser, $data)
 {
 $this->currentValue = iconv('UTF-8', 'GB2312', $data);
 }
 function __destruct()
 {
 unset($this->domRootObject);
 } }
?> 文件:SimpleDocumentBase.php <?php
/**
*=================================================
*
* @author hahawen(大龄青年)
* @since 2004-12-04
* @copyright Copyright (c) 2004, NxCoder Group
*
*=================================================
*/
/**
* abstract class SimpleDocumentBase
* base class for xml file parse
* all this pachage's is work for xml file, and method is action as DOM.
*
* 1\ add/update/remove data of xml file.
* 2\ explode data to array.
* 3\ rebuild xml file
*
* @package SmartWeb.common.xml
* @abstract
* @version 1.0
*/
abstract class SimpleDocumentBase
{ private $nodeTag = null; private $attributes = array();
 private $values =
 array(); private $nodes = array(); function __construct($nodeTag)
 {
 $this->nodeTag = $nodeTag;
 } public function getNodeTag()
 {
 return $this->nodeTag;
 } public function setValues($values){
 $this->values = $values;
 } public function setValue($name, $value)
 {
 $this->values[$name] = $value;
 } public function getValue($name=null)
 {
 return $name==null?
 $this->values: $this->values[$name];
 } public function removeValue($name)
 {
 unset($this->values["$name"]);
 } public function setAttributes($attributes){
 $this->attributes = $attributes;
 } public function setAttribute($name, $value)
 {
 $this->attributes[$name] = $value;
 } public function getAttribute($name=null)
 {
 return $name==null? $this->attributes:
 $this->attributes[$name];
 } public function removeAttribute($name)
 {
 unset($this->attributes["$name"]);
 } public function getNodesSize()
 {
 return sizeof($this->nodes);
 } protected function setNode($name, $nodeId)
 {
 $this->nodes[$name]
 = $nodeId;
 } public abstract function createNode($name, $attributes); public abstract function removeNode($name); public abstract function getNode($name=null); protected function getNodeId($name=null)
 {
 return $name==null? $this->nodes: $this->nodes[$name];
 } protected function createNodeByName($rootNodeObj, $name, $attributes, $pId)
 {
 $tmpObject = $rootNodeObj->createNodeObject($pId, $name, $attributes);
 $key = isset($attributes[id])?
 $name.'_'.$attributes[id]: $name.'_'.$this->getNodesSize();
 $this->setNode($key, $tmpObject->getSeq());
 return $tmpObject;
 } protected function removeNodeByName($rootNodeObj, $name)
 {
 $rootNodeObj->removeNodeById($this->getNodeId($name));
 if(sizeof($this->nodes)==1)
 $this->nodes = array();
 else
 unset($this->nodes[$name]);
 } protected function getNodeByName($rootNodeObj, $name=null)
 {
 if($name==null)
 {
 $tmpList = array();
 $tmpIds = $this->getNodeId();
 foreach($tmpIds as $key=>$id)
 $tmpList[$key] = $rootNodeObj->getNodeById($id);
 return $tmpList;
 }
 else
 {
 $id = $this->getNodeId($name);
 if($id===null)
 {
 $tmpIds = $this->getNodeId(); foreach($tmpIds as $tkey=>$tid)
 {
 if(strpos($key, $name)==0)
 {
 $id = $tid;
 break;
 }
 }
 }
 return $rootNodeObj->getNodeById($id);
 }
 } public function findNodeByPath($path)
 {
 $pos = strpos($path, '|');
 if($pos<=0)
 {
 return $this->getNode($path);
 }
 else
 { $tmpObj = $this->getNode(substr($path, 0,
 $pos)); return is_object($tmpObj)?
 $tmpObj->findNodeByPath(substr($path,
 $pos+1)):
 null;
 }
 } public function getSaveData()
 {
 $data = $this->values;
 if(sizeof($this->attributes)>0) $data[attrs] = $this->attributes;
 $nodeList = $this->getNode();
 if($nodeList==null) return $data;
 foreach($nodeList as $key=>$node)
 {
 $data[$key] = $node->getSaveData();
 } return $data;
 }
 public function getSaveXml($level=0)
 { $prefixSpace
 = str_pad("",
 $level, "\t");
 $str = "$prefixSpace<$this->nodeTag"; foreach($this->attributes as $key=>$value)
 $str .= " $key=\"$value\""; $str .= ">\r\n";
 foreach($this->values as $key=>$value){ if(is_array($value))
 {
 $str .= "$prefixSpace\t<$key"; foreach($value[attrs] as $attkey=>$attvalue) $str .= " $attkey=\"$attvalue\""; $tmpStr = $value[value];
 }
 else {
 $str .= "$prefixSpace\t<$key"; $tmpStr = $value;
 }
 $tmpStr = trim(trim($tmpStr, "\r\n")); $str .= ($tmpStr===null || $tmpStr==="")? " />\r\n": ">$tmpStr</$key>\r\n"; } foreach($this->getNode() as $node)
 $str .= $node->getSaveXml($level+1)."\r\n";
 $str .= "$prefixSpace</$this->nodeTag>"; return $str;
 } function __destruct()
 {
 unset($this->nodes, $this->attributes, $this->values); } }
?>
文件:SimpleDocumentRoot.php <?php
/**
*==============================================
*
* @author hahawen(大龄青年)
* @since 2004-12-04
* @copyright Copyright (c) 2004, NxCoder Group
*
*==============================================
*/
/**
* class SimpleDocumentRoot
* xml root class, include values/attributes/subnodes.
* all this pachage's is work for xml file, and method is action as DOM.
*
* @package SmartWeb.common.xml
* @version 1.0
*/ class SimpleDocumentRoot extends SimpleDocumentBase
{
 private $prefixStr = '';
 private $nodeLists = array(); function __construct($nodeTag)
 {
 parent::__construct($nodeTag);
 } public function createNodeObject($pNodeId, $name, $attributes)
 {
 $seq = sizeof($this->nodeLists);
 $tmpObject = new SimpleDocumentNode($this,
 $pNodeId, $name, $seq);
 $tmpObject->setAttributes($attributes); $this->nodeLists[$seq] = $tmpObject;
 return $tmpObject;
 } public function removeNodeById($id)
 {
 if(sizeof($this->nodeLists)==1)
 $this->nodeLists = array();
 else
 unset($this->nodeLists[$id]);
 } public function getNodeById($id)
 {
 return $this->nodeLists[$id];
 } public function createNode($name, $attributes)
 {
 return $this->createNodeByName($this, $name, $attributes, -1);
 } public function removeNode($name)
 {
 return $this->removeNodeByName($this, $name);
 } public function getNode($name=null)
 {
 return $this->getNodeByName($this, $name);
 } public function getSaveXml()
 {
 $prefixSpace = "";
 $str = $this->prefixStr."\r\n";
 return $str.parent::getSaveXml(0);
 }
}
?> 文件:SimpleDocumentNode.php <?php
/**
*===============================================
*
* @author hahawen(大龄青年)
* @since 2004-12-04
* @copyright Copyright (c) 2004, NxCoder Group
*
*===============================================
*/
/**
* class SimpleDocumentNode
* xml Node class, include values/attributes/subnodes.
* all this pachage's is work for xml file, and method is action as DOM.
*
* @package SmartWeb.common.xml
* @version 1.0
*/
class SimpleDocumentNode extends SimpleDocumentBase
{
 private $seq = null;
 private $rootObject = null;
 private $pNodeId = null; function __construct($rootObject, $pNodeId, $nodeTag, $seq)
 {
 parent::__construct($nodeTag);
 $this->rootObject = $rootObject;
 $this->pNodeId = $pNodeId;
 $this->seq = $seq;
 } public function getPNodeObject()
 {
 return ($this->pNodeId==-1)?
 $this->rootObject:
 $this->rootObject->getNodeById($this->pNodeId);
 } public function getSeq(){
 return $this->seq;
 } public function createNode($name, $attributes)
 {
 return $this->createNodeByName($this->rootObject,
 $name, $attributes,
 $this->getSeq());
 } public function removeNode($name)
 {
 return $this->removeNodeByName($this->rootObject, $name);
 }
 public function getNode($name=null)
 {
 return $this->getNodeByName($this->rootObject,
 $name);
 }
}
?>
下面是例子运行对结果

下面是通过函数getSaveData()返回的整个xml数据的数组

下面是通过setValue()函数，给给根节点添加信息，添加后显示出结果xml文件的内容

<?xml version="1.0" encoding="GB2312" ?>
<shop>
<name>华联</name>
<address>北京长安街－9999号</address>
<desc>连锁超市</desc>
<telphone>123456789</telphone>
<cat id="food">
<goods id="food11">
 <name>food11</name>
 <price>12.90</price>
</goods>
<goods id="food12">
 <name>food12</name>
 <price>22.10</price>
 <desc creator="hahawen">好东西推荐</desc>
</goods>
</cat>
<cat>
<goods id="tel21">
 <name>tel21</name>
 <price>1290</price>
</goods>
</cat>
<cat id="coat">
<goods id="coat31">
 <name>coat31</name>
 <price>112</price>
</goods>
<goods id="coat32">
 <name>coat32</name>
 <price>45</price>
</goods>
</cat>
<special id="hot">
<goods>
 <name>hot41</name>
 <price>99</price>
</goods>
</special>
</shop>

下面是通过getNode()函数，返回某一个分类下的所有商品的信息

商品名：food11
Array
(
    [name] => food11
    [price] => 12.90
)
Array
(
    [id] => food11
)
商品名：food12
Array
(
    [name] => food12
    [price] => 22.10
    [desc] => Array
        (
            [value] => 好东西推荐
            [attrs] => Array
                (
                    [creator] => hahawen
                )

        )

)
Array
(
    [id] => food12
)

下面是通过findNodeByPath()函数，返回某一商品的信息

商品名：food11
Array
(
    [name] => food11
    [price] => 12.90
)
Array
(
    [id] => food11
)

下面是通过setValue()函数，给商品"food11"添加属性, 然后显示添加后的结果

<?xml version="1.0" encoding="GB2312" ?>
<shop>
<name>华联</name>
<address>北京长安街－9999号</address>
<desc>连锁超市</desc>
<telphone>123456789</telphone>
<cat id="food">
<goods id="food11">
 <name>food11</name>
 <price>12.90</price>
 <leaveword author="hahawen" date="2004-12-05">这个商品不错</leaveword>
</goods>
<goods id="food12">
 <name>food12</name>
 <price>22.10</price>
 <desc creator="hahawen">好东西推荐</desc>
</goods>
</cat>
<cat>
<goods id="tel21">
 <name>tel21</name>
 <price>1290</price>
</goods>
</cat>
<cat id="coat">
<goods id="coat31">
 <name>coat31</name>
 <price>112</price>
</goods>
<goods id="coat32">
 <name>coat32</name>
 <price>45</price>
</goods>
</cat>
<special id="hot">
<goods>
 <name>hot41</name>
 <price>99</price>
</goods>
</special>
</shop>

下面是通过removeValue()/removeAttribute()函数，给商品"food11"改变和删除属性, 然后显示操作后的结果

<?xml version="1.0" encoding="GB2312" ?>
<shop>
<name>华联</name>
<address>北京长安街－9999号</address>
<desc>连锁超市</desc>
<telphone>123456789</telphone>
<cat id="food">
<goods id="food11">
 <name>food11</name>
 <price>12.90</price>
 <leaveword author="hahawen" date="2004-12-05">这个商品不错</leaveword>
</goods>
<goods id="food12">
 <name>new food12</name>
 <price>22.10</price>
</goods>
</cat>
<cat>
<goods id="tel21">
 <name>tel21</name>
 <price>1290</price>
</goods>
</cat>
<cat id="coat">
<goods id="coat31">
 <name>coat31</name>
 <price>112</price>
</goods>
<goods id="coat32">
 <name>coat32</name>
 <price>45</price>
</goods>
</cat>
<special id="hot">
<goods>
 <name>hot41</name>
 <price>99</price>
</goods>
</special>
</shop>

下面是通过createNode()函数，添加商品, 然后显示添加后的结果

<?xml version="1.0" encoding="GB2312" ?>
<shop>
<name>华联</name>
<address>北京长安街－9999号</address>
<desc>连锁超市</desc>
<telphone>123456789</telphone>
<cat id="food">
<goods id="food11">
 <name>food11</name>
 <price>12.90</price>
 <leaveword author="hahawen" date="2004-12-05">这个商品不错</leaveword>
</goods>
<goods id="food12">
 <name>new food12</name>
 <price>22.10</price>
</goods>
<goods id="food13">
 <name>food13</name>
 <price>100</price>
</goods>
</cat>
<cat>
<goods id="tel21">
 <name>tel21</name>
 <price>1290</price>
</goods>
</cat>
<cat id="coat">
<goods id="coat31">
 <name>coat31</name>
 <price>112</price>
</goods>
<goods id="coat32">
 <name>coat32</name>
 <price>45</price>
</goods>
</cat>
<special id="hot">
<goods>
 <name>hot41</name>
 <price>99</price>
</goods>
</special>
</shop>

下面是通过removeNode()函数，删除商品, 然后显示删除后的结果

<?xml version="1.0" encoding="GB2312" ?>
<shop>
<name>华联</name>
<address>北京长安街－9999号</address>
<desc>连锁超市</desc>
<telphone>123456789</telphone>
<cat id="food">
<goods id="food11">
 <name>food11</name>
 <price>12.90</price>
 <leaveword author="hahawen" date="2004-12-05">这个商品不错</leaveword>
</goods>
<goods id="food13">
 <name>food13</name>
 <price>100</price>
</goods>
</cat>
<cat>
<goods id="tel21">
 <name>tel21</name>
 <price>1290</price>
</goods>
</cat>
<cat id="coat">
<goods id="coat31">
 <name>coat31</name>
 <price>112</price>
</goods>
<goods id="coat32">
 <name>coat32</name>
 <price>45</price>
</goods>
</cat>
<special id="hot">
<goods>
 <name>hot41</name>
 <price>99</price>
</goods>
</special>
</shop>

上一篇：扩展你的 PHP 之入门篇
下一篇：PHP 已经成熟