xdiff_string_patch
<?php
/**
* XML to Associative Array Class
*
* Usage:
* $domObj = new xmlToArrayParser($xml);
* $domArr = $domObj->array;
*
* if($domObj->parse_error) echo $domObj->get_xml_error();
* else print_r($domArr);
*
* On Success:
* eg. $domArr['top']['element2']['attrib']['var2'] => val2
*
* On Error:
* eg. Error Code [76] "Mismatched tag", at char 58 on line 3
*/
/**
* Convert an xml file or string to an associative array (including the tag attributes):
* $domObj = new xmlToArrayParser($xml);
* $elemVal = $domObj->array['element']
* Or: $domArr=$domObj->array; $elemVal = $domArr['element'].
*
* @version 2.0
* @param Str $xml file/string.
*/
class xmlToArrayParser {
/** The array created by the parser can be assigned to any variable: $anyVarArr = $domObj->array.*/
public $array = array();
public $parse_error = false;
private $parser;
private $pointer;
/** Constructor: $domObj = new xmlToArrayParser($xml); */
public function __construct($xml) {
$this->pointer =& $this->array;
$this->parser = xml_parser_create("UTF-8");
xml_set_object($this->parser, $this);
xml_parser_set_option($this->parser, XML_OPTION_CASE_FOLDING, false);
xml_set_element_handler($this->parser, "tag_open", "tag_close");
xml_set_character_data_handler($this->parser, "cdata");
$this->parse_error = xml_parse($this->parser, ltrim($xml))? false : true;
}
/** Free the parser. */
public function __destruct() { xml_parser_free($this->parser);}
/** Get the xml error if an an error in the xml file occured during parsing. */
public function get_xml_error() {
if($this->parse_error) {
$errCode = xml_get_error_code ($this->parser);
$thisError = "Error Code [". $errCode ."] \"<strong style='color:red;'>" . xml_error_string($errCode)."</strong>\",
at char ".xml_get_current_column_number($this->parser) . "
on line ".xml_get_current_line_number($this->parser)."";
}else $thisError = $this->parse_error;
return $thisError;
}
private function tag_open($parser, $tag, $attributes) {
$this->convert_to_array($tag, 'attrib');
$idx=$this->convert_to_array($tag, 'cdata');
if(isset($idx)) {
$this->pointer[$tag][$idx] = Array('@idx' => $idx,'@parent' => &$this->pointer);
$this->pointer =& $this->pointer[$tag][$idx];
}else {
$this->pointer[$tag] = Array('@parent' => &$this->pointer);
$this->pointer =& $this->pointer[$tag];
}
if (!empty($attributes)) { $this->pointer['attrib'] = $attributes; }
}
/** Adds the current elements content to the current pointer[cdata] array. */
private function cdata($parser, $cdata) { $this->pointer['cdata'] = trim($cdata); }
private function tag_close($parser, $tag) {
$current = & $this->pointer;
if(isset($this->pointer['@idx'])) {unset($current['@idx']);}
$this->pointer = & $this->pointer['@parent'];
unset($current['@parent']);
if(isset($current['cdata']) && count($current) == 1) { $current = $current['cdata'];}
else if(empty($current['cdata'])) {unset($current['cdata']);}
}
/** Converts a single element item into array(element[0]) if a second element of the same name is encountered. */
private function convert_to_array($tag, $item) {
if(isset($this->pointer[$tag][$item])) {
$content = $this->pointer[$tag];
$this->pointer[$tag] = array((0) => $content);
$idx = 1;
}else if (isset($this->pointer[$tag])) {
$idx = count($this->pointer[$tag]);
if(!isset($this->pointer[$tag][0])) {
foreach ($this->pointer[$tag] as $key => $value) {
unset($this->pointer[$tag][$key]);
$this->pointer[$tag][0][$key] = $value;
}}}else $idx = null;
return $idx;
}
}
?>
This is supplimental information for the "class xmlToArrayParser".
This is a fully functional error free, extensively tested php class unlike the posts that follow it.
Key phrase: Fully functional, fully tested, error free XML To Array parser.
<?php
/**
* class xmlToArrayParser
*
Notes:
1. 'attrib' and 'cdata' are keys added to the array when the element contains both attributes and content.
2. Ignores content that is not in between it's own set of tags.
3. Don't know if it recognizes processing instructions nor do I know about processing instructions.
<\?some_pi some_attr="some_value"?> This is the same as a document declaration.
4. Empty elements are not included unless they have attributes.
5. Version 2.0, Dec. 2, 2011, added xml error reporting.
Usage:
$domObj = new xmlToArrayParser($xml);
$elemVal = $domObj->array['element']
Or assign the entire array to its own variable:
$domArr = $domObj->array;
$elemVal = $domArr['element']
Example:
$xml = '<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<top>
<element1>element content 1</element1>
<element2 var2="val2" />
<element3 var3="val3" var4="val4">element content 3</element3>
<element3 var5="val5">element content 4</element3>
<element3 var6="val6" />
<element3>element content 7</element3>
</top>';
$domObj = new xmlToArrayParser($xml);
$domArr = $domObj->array;
if($domObj->parse_error) echo $domObj->get_xml_error();
else print_r($domArr);
On Success:
$domArr['top']['element1'] => element content 1
$domArr['top']['element2']['attrib']['var2'] => val2
$domArr['top']['element3']['0']['attrib']['var3'] => val3
$domArr['top']['element3']['0']['attrib']['var4'] => val4
$domArr['top']['element3']['0']['cdata'] => element content 3
$domArr['top']['element3']['1']['attrib']['var5'] => val5
$domArr['top']['element3']['1']['cdata'] => element content 4
$domArr['top']['element3']['2']['attrib']['var6'] => val6
$domArr['top']['element3']['3'] => element content 7
On Error:
Error Code [76] "Mismatched tag", at char 58 on line 3
*
*/
?>
CLXVI. Funciones de intérprete XML
Introducción
Acerca de XML
XML (eXtensible Markup Language) es un formato de información para el intercambio de documentos estructurado en la "Web" Es un estándar definido por el consorcio de la "World Wide Web" (W3C). Se puede encontrar información sobre XML y tecnologís relacionadas en http://www.w3.org/XML/.
Instalación
Esta extensión usa expat, que se puede encontrar en http://www.jclark.com/xml/expat.html. El Makefile que viene con expat no crea una biblioteca por defecto, se puede usar esta regla de make para eso:
libexpat.a: $(OBJS) ar -rc $@ $(OBJS) ranlib $@ |
Nota que si se usa Apache-1.3.7 o posterior, ya tienes la biblioteca requerida expat. Simplemente, configura PHP usando --with-xml (sin ninguna ruta adicional) y usará automáticamente la biblioteca expat incluida en Apache.
En UNIX, ejecuta configure con la opción --with-xml. La biblioteca expat debería ser instalada en algún lugar donde el compilador pueda encontrarlo. Si se compila PHP como un módulo para Apache 1.3.9 o posterior, PHP automáticamente usará la biblioteca integrada expat de Apache. Puede necesitar establecer CPPFLAGS y LDFLAGS en su entorno antes de ejecutar "configure" si se ha instalado expat en algún lugar exótico.
Compila PHP. ¡Ta-tam! Ya debería estar.
Sobre Esta Extensión
Esta extensión de PHP implementa soporte para expat de James Clarkin en PHP. Este conjunto de herramientas permite interpretar, pero no validar, documentos XML. Soporta tres codificaciones de caracteres fuente, también proporcionados por PHP: US-ASCII, ISO-8859-1 y UTF-8. UTF-16 no está soportado.
Esta extensión permite crear intérpretes de XML y definir entonces gestores para diferentes eventos XML. Cada intérprete XML tiene también unos cuantos parámetros que se pueden ajustar.
Los gestores de eventos XML definidos son:
Tabla 1. Gestores de XML soportados
| Función PHP para establecer gestor | Descripción del evento |
|---|---|
| xml_set_element_handler() | Los eventos de elemento ("element") se producen cuando el intérprete XML encuentra etiquetas de comienzo o fin. Hay gestores separados para etiquetas de comienzo y etiquetas de fin. |
| xml_set_character_data_handler() | La información de caracteres es, por definición, todo el contenido no "marcado" de los documentos XML, incluidos los espacios en blanco entre etiquetas. Nota que el intérprete XML no añade o elimina ningún espacio en blanco, depende de la aplicación (de ti) decidir si el espacio en blanco es significativo. |
| xml_set_processing_instruction_handler() | Los programadores de PHP deberían estar ya familiarizados con las instrucciones de procesado (PI). <?php ?> es una instrucción de procesado, donde php se denomina el "objetivo de procesado". El manejo de éstos es específico a cada aplicación, salvo que todos los objetivos PI que comienzan con "XML" están reservados. |
| xml_set_default_handler() | Todo lo que no va a otro gestor, va al gestor por defecto. Se tendrán en el gestor por defecto cosas como las declaraciones de tipos de documento y XML. |
| xml_set_unparsed_entity_decl_handler() | Este gestor se llamará para la declaración de una entidad no analizada (NDATA). |
| xml_set_notation_decl_handler() | Este gestor se llama para la declaración de una anotación. |
| xml_set_external_entity_ref_handler() | Este gestor se llama cuando el intérprete XML encuentra una referencia a una entidad general interpretada externa. Puede ser una referencia a un archivo o URL, por ejemplo. Ver el ejemplo de entidad externa para demostración. |
Case Folding
Las funciones manejadoras de elementos pueden tomar sus nombres de elementos "case-folded". Case-folding se define en el estándar XML como "un proceso aplicado a una secuencia de caracteres, en el cual aquellos identificados como sin-mayúsculas son reemplazados por sus equivalentes en mayúsculas". En otras palabras, cuando se trata de XML, case-folding simplemente significa poner en mayúsculas.
Por defecto, todos los nombres de elementos que se pasan a las funciones gestoras estan "pasados a mayúsculas". Esta conducta puede ser observada y controlada por el analizador XML con las funciones xml_parser_get_option() y xml_parser_set_option(), respectivamente.
Códigos de Error
Las siguientes constantes se definen para códigos de error XML (como los devuelve xml_parse()):
| XML_ERROR_NONE |
| XML_ERROR_NO_MEMORY |
| XML_ERROR_SYNTAX |
| XML_ERROR_NO_ELEMENTS |
| XML_ERROR_INVALID_TOKEN |
| XML_ERROR_UNCLOSED_TOKEN |
| XML_ERROR_PARTIAL_CHAR |
| XML_ERROR_TAG_MISMATCH |
| XML_ERROR_DUPLICATE_ATTRIBUTE |
| XML_ERROR_JUNK_AFTER_DOC_ELEMENT |
| XML_ERROR_PARAM_ENTITY_REF |
| XML_ERROR_UNDEFINED_ENTITY |
| XML_ERROR_RECURSIVE_ENTITY_REF |
| XML_ERROR_ASYNC_ENTITY |
| XML_ERROR_BAD_CHAR_REF |
| XML_ERROR_BINARY_ENTITY_REF |
| XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF |
| XML_ERROR_MISPLACED_XML_PI |
| XML_ERROR_UNKNOWN_ENCODING |
| XML_ERROR_INCORRECT_ENCODING |
| XML_ERROR_UNCLOSED_CDATA_SECTION |
| XML_ERROR_EXTERNAL_ENTITY_HANDLING |
Codificación de caracteres
La extension XML de PHP soporta el conjunto de caracteres Unicode a través de diferentes codificaciones de caracteres. Hay dos tipos de codificaciones de caracteres, coficación de fuente y codificación de destino. La representación interna de PHP del documento está siempre codificada con UTF-8.
La codificación de fuente se hace cuando un documento XML es interpretado. Al crear un intérprete XML , se puede especificar una codificación de fuente (esta codificación no se puede cambiar má tarde durante el tiempo de vida del intérprete XML). Las codificaciones de fuente soportadas son ISO-8859-1, US-ASCII y UTF-8. Las dos primeras son codificaciones de byte-único, lo que significa que cada carácter se representa por un solo byte. UTF-8 puede codificar caracteres compuestos por un número variable de bits (hasta 21) en de uno a cuatro bytes. La codificación fuente por defecto usada por PHP es ISO-8859-1.
La codificación de destino se hace cuando PHP pasa datos a las funciones gestoras XML. Cuando se crea un intérprete XML, la codificación de destino se crea igual a la codificación de fuente, pero se puede cambiar en cualquier momento. La codificación de destino afectará a la información de los caracteres así como a los nombres de las etiquetas y a los objetivos de instrucciones de procesado.
Si el intérprete XML encuentra caracteres fuera del rango que su codificación de fuente es capaz de representar, devolverá un error.
Si PHP encuentra caracteres en el documento XML interpretado que no pueden ser representados en la codificación de destino elegida, los caracteres problema serán "degradados". Actualmente, esto significa que tales caracteres se reemplazan por un signo de interrogación.
Algunos Ejemplos
Aquí hay algunos ejemplos de archivos de comandos PHP que interpretan documentos XML.
Ejemplos de Estructuras de Elementos XML
Este primer ejemplo muestra la estructura del elemento inicio en un documento con indentación.
Ejemplo de Mapeo de Etiquetas XML
Ejemplo 2. Traduciendo XML a HTML Este ejemplo transforma etiquetas de un documento XML directamente a etiquetas HTML. Los elementos no encontrados en el "array de traducción ("map array") son ignorados. Por supuesto, este ejemplo solamente funcionará con un tipo de documentos XML específico.
|
Ejemplo de Entidad Externa XML
Este ejemplo resalta el código XML. Ilustra cómo usar un gestor de referencia de entidades extenas para incluir y analizar otros documentos, así como cuúntos PIs pueden ser procesados, y un modo de determinar "confianza" para PIs que contienen código.
Los documentos XML que se pueden usar en este ejemplo se encuentran bajo el ejemplo (xmltest.xml y xmltest2.xml.)
Ejemplo 3. Ejemplo de Entidades Externas
|
Ejemplo 4. xmltest.xml
|
Este archivo se incluye desde xmltest.xml:
- Tabla de contenidos
- utf8_decode -- Convierte una cadena codificada UTF-8 a ISO-8859-1
- utf8_encode -- codifica una cadena ISO-8859-1 a UTF-8
- xml_error_string -- obtiene la cadena de error del analizador XML
- xml_get_current_byte_index -- obtiene el índice del byte actual para un analizador XML
- xml_get_current_column_number -- Obtiene el número de columna actual para un analizador XML.
- xml_get_current_line_number -- obtiene el número de línea actual de un analizador XML
- xml_get_error_code -- obtiene el código de error del analizador XML
- xml_parse_into_struct -- Parse XML data into an array structure
- xml_parse -- comienza a analizar un documento XML
- xml_parser_create_ns -- Create an XML parser with namespace support
- xml_parser_create -- crea un analizador de XML
- xml_parser_free -- Libera un analizador XML
- xml_parser_get_option -- obtiene las opciones de un analizador XML
- xml_parser_set_option -- establece las opciones de un analizador XML
- xml_set_character_data_handler -- Establece gestores de datos de caracteres
- xml_set_default_handler -- set up default handler
- xml_set_element_handler -- establece gestores de los elementos principio y fin
- xml_set_end_namespace_decl_handler -- Set up end namespace declaration handler
- xml_set_external_entity_ref_handler -- Establece gestores de referencia de entidades externas
- xml_set_notation_decl_handler -- Establece gestores de declaraciones de notación
- xml_set_object -- Usa un analizador XML dentro de un objecto
- xml_set_processing_instruction_handler -- Establece el gestor de instrucciones de procesado (PI)
- xml_set_start_namespace_decl_handler -- Set up start namespace declaration handler
- xml_set_unparsed_entity_decl_handler -- Establece un gestor de declaraciones de entidades no analizadas
add a note
User Contributed Notes
Funciones de intérprete XML
Glen at ITIStudios dot ca
02-Dec-2011 03:37
wolfon.AT-DoG.inbox.ru
28-Jul-2008 03:09
Finally a simple xml => array class.
Functioning like SimpleXML library.
<?php
class xml {
private $parser;
private $pointer;
public $dom;
public function __construct($data) {
$this->pointer =& $this->dom;
$this->parser = xml_parser_create();
xml_set_object($this->parser, $this);
xml_parser_set_option($this->parser, XML_OPTION_CASE_FOLDING, false);
xml_set_element_handler($this->parser, "tag_open", "tag_close");
xml_set_character_data_handler($this->parser, "cdata");
xml_parse($this->parser, $data);
}
private function tag_open($parser, $tag, $attributes) {
if (isset($this->pointer[$tag]['@attributes'])) {
$content = $this->pointer[$tag];
$this->pointer[$tag] = array(0 => $content);
$idx = 1;
} else if (isset($this->pointer[$tag]))
$idx = count($this->pointer[$tag]);
if (isset($idx)) {
$this->pointer[$tag][$idx] = Array(
'@idx' => $idx,
'@parent' => &$this->pointer);
$this->pointer =& $this->pointer[$tag][$idx];
} else {
$this->pointer[$tag] = Array(
'@parent' => &$this->pointer);
$this->pointer =& $this->pointer[$tag];
}
if (!empty($attributes))
$this->pointer['@attributes'] = $attributes;
}
private function cdata($parser, $cdata) {
$this->pointer['@data'] = $cdata;
}
private function tag_close($parser, $tag) {
$current = & $this->pointer;
if (isset($this->pointer['@idx']))
unset($current['@idx']);
$this->pointer = & $this->pointer['@parent'];
unset($current['@parent']);
if (isset($current['@data']) && count($current) == 1)
$current = $current['@data'];
else if (empty($current['@data'])||$current['@data']==0)
unset($current['@data']);
}
}
?>
maybe I'll do some explanations on habr
geoff at spacevs dot com
07-Nov-2007 09:13
Reading xml into a class:
<?PHP
class XmlData {}
$elements = array();
$elements[] =& new XmlData();
function startElement($parser, $name, $attrs) {
global $elements;
$element =& new XMLData();
$elements[count($elements)-1]->$name =& $element;
$elements[] =& $element;
}
function endElement($parser, $name) {
global $elements;
array_pop($elements);
}
function characterData($parser, $data) {
global $elements;
$elements[count($elements)-1]->data = $data;
}
$xml_parser = xml_parser_create();
xml_set_element_handler($xml_parser, "startElement", "endElement");
xml_set_character_data_handler($xml_parser, "characterData");
xml_parse($xml_parser, $xml, true);
xml_parser_free($xml_parser);
$request =& array_pop($elements);
echo $request->LOGIN->USER->data;
?>
demonpants at gmail dot com
22-Oct-2007 08:59
I wanted to access the ISBN database, and was previously parsing the HTML string generated from their main page, that is until I discovered they have an API that returns XML.
So, if anyone wants to get some information from the ISBN database, all you need to do is the following.
<?php
//Search the ISBN database for the book.
$url = "http://www.isbndb.com/api/books.xml? access_key=KEY&index1=isbn&value1=$_GET[ISBN]";
$p = xml_parser_create();
xml_parse_into_struct($p,file_get_contents($url),$results,$index);
xml_parser_free($p);
$title = $results[$index[TITLELONG][0]][value];
$author = $results[$index[AUTHORSTEXT][0]][value];
$publisher = $results[$index[PUBLISHERTEXT][0]][value];
?>
You will need to get an access key from isbndb.com, but it takes two seconds and is free. When you get it, replace KEY in the URL with your own key. Also, my code above will search for the book that fits the ISBN number stored in the GET variable ISBN - you can search by other parameters and return more than one result, but my example is for a simple ISBN search.
Zvjezdan Patz
09-Sep-2007 08:22
The problem I had was I needed to generate xml on the screen for users to actually see and copy to a file.
I'm generating the xml manually from a php file and the browser kept interpreting the xml...not very helpful.
This is how you get around it:
<?php
$file = file_get_contents("http://example.com/xml.php?whatever=$whatever");
print nl2br(htmlentities($file));
?>
Prints all my xml quite nicely.
v9 at fakehalo dot us
13-Jul-2007 08:04
I needed this for work/personal use. Sometimes you'll have a XML string generated as one long string and no line breaks...nusoap in the case of today/work, but there are any other number of possible things that will generate these. Anyways, this simply takes a long XML string and returns an indented/line-breaked version of the string for display/readability.
<?php
function xmlIndent($str){
$ret = "";
$indent = 0;
$indentInc = 3;
$noIndent = false;
while(($l = strpos($str,"<",$i))!==false){
if($l!=$r && $indent>0){ $ret .= "\n" . str_repeat(" ",$indent) . substr($str,$r,($l-$r)); }
$i = $l+1;
$r = strpos($str,">",$i)+1;
$t = substr($str,$l,($r-$l));
if(strpos($t,"/")==1){
$indent -= $indentInc;
$noIndent = true;
}
else if(($r-$l-strpos($t,"/"))==2 || substr($t,0,2)=="<?"){ $noIndent = true; }
if($indent<0){ $indent = 0; }
if($ret){ $ret .= "\n"; }
$ret .= str_repeat(" ",$indent);
$ret .= $t;
if(!$noIndent){ $indent += $indentInc; }
$noIndent = false;
}
$ret .= "\n";
return($ret);
}
?>
(...this was only tested for what i needed at work, could POSSIBLY need additions)
geoffers [at] gmail [dot] com
30-Dec-2006 03:27
Time to add my attempt at a very simple script that parses XML into a structure:
<?php
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>');
?>
Didier: dlvb ** free * fr
24-Dec-2006 09:53
Hi !
After parsing the XML and modifying it, I just add a method to rebuild the XML form the internal structure (xmlp->document).
The method xmlp->toXML writes into xmlp->XML attributes. Then, you just have to output it.
I hope it helps.
<?php
class XMLParser {
var $parser;
var $filePath;
var $document;
var $currTag;
var $tagStack;
var $XML;
var $_tag_to_close = false;
var $TAG_ATTRIBUT = 'attr';
var $TAG_DATA = 'data';
function XMLParser($path) {
$this->parser = xml_parser_create();
$this->filePath = $path;
$this->document = array();
$this->currTag =& $this->document;
$this->tagStack = array();
$this->XML = "";
}
function parse() {
xml_set_object($this->parser, $this);
xml_set_character_data_handler($this->parser, 'dataHandler');
xml_set_element_handler($this->parser, 'startHandler', 'endHandler');
if(!($fp = fopen($this->filePath, "r"))) {
die("Cannot open XML data file: $this->filePath");
return false;
}
while($data = fread($fp, 4096)) {
if(!xml_parse($this->parser, $data, feof($fp))) {
die(sprintf("XML error: %s at line %d",
xml_error_string(xml_get_error_code($this->parser)),
xml_get_current_line_number($this->parser)));
}
}
fclose($fp);
xml_parser_free($this->parser);
return true;
}
function startHandler($parser, $name, $attribs) {
if(!isset($this->currTag[$name]))
$this->currTag[$name] = array();
$newTag = array();
if(!empty($attribs))
$newTag[$this->TAG_ATTRIBUT] = $attribs;
array_push($this->currTag[$name], $newTag);
$t =& $this->currTag[$name];
$this->currTag =& $t[count($t)-1];
array_push($this->tagStack, $name);
}
function dataHandler($parser, $data) {
$data = trim($data);
if(!empty($data)) {
if(isset($this->currTag[$this->TAG_DATA]))
$this->currTag[$this->TAG_DATA] .= $data;
else
$this->currTag[$this->TAG_DATA] = $data;
}
}
function endHandler($parser, $name) {
$this->currTag =& $this->document;
array_pop($this->tagStack);
for($i = 0; $i < count($this->tagStack); $i++) {
$t =& $this->currTag[$this->tagStack[$i]];
$this->currTag =& $t[count($t)-1];
}
}
function clearOutput () {
$this->XML = "";
}
function openTag ($tag) {
$this->XML.="<".strtolower ($tag);
$this->_tag_to_close = true;
}
function closeTag () {
if ($this->_tag_to_close) {
$this->XML.=">";
$this->_tag_to_close = false;
}
}
function closingTag ($tag) {
$this->XML.="</".strtolower ($tag).">";
}
function output_attributes ($contenu_fils) {
foreach ($contenu_fils[$this->TAG_ATTRIBUT] as $nomAttribut => $valeur) {
$this->XML.= " ".strtolower($nomAttribut)."=\"".$valeur."\"";
}
}
function addData ($texte) {
// to be completed
$ca = array ("é", "è", "ê", "à");
$par = array ("é", "è", "ê", "agrave;");
return htmlspecialchars(str_replace ($ca, $par, $texte), ENT_NOQUOTES);
}
function toXML ($tags="") {
if ($tags=="") {
$tags = $this->document;
$this->clearOutput ();
}
foreach ($tags as $tag => $contenu) {
$this->process ($tag, $contenu);
}
}
function process ($tag, $contenu) {
// Pour tous les TAGs
foreach ($contenu as $indice => $contenu_fils) {
$this->openTag ($tag);
// Pour tous les fils (non attribut et non data)
foreach ($contenu_fils as $tagFils => $fils) {
switch ($tagFils) {
case $this->TAG_ATTRIBUT:
$this->output_attributes ($contenu_fils);
$this->closeTag ();
break;
case $this->TAG_DATA:
$this->closeTag ();
$this->XML.= $this->addData ($contenu_fils [$this->TAG_DATA]);
break;
default:
$this->closeTag ();
$this->process ($tagFils, $fils);
break;
}
}
$this->closingTag ($tag);
}
}
}
?>
forquan
28-Jan-2006 03:45
Here's code that will create an associative array from an xml file. Keys are the tag data and subarrays are formed from attributes and child tags
<?php
$p =& new xmlParser();
$p->parse('/*xml file*/');
print_r($p->output);
?>
<?php
class xmlParser{
var $xml_obj = null;
var $output = array();
var $attrs;
function xmlParser(){
$this->xml_obj = xml_parser_create();
xml_set_object($this->xml_obj,$this);
xml_set_character_data_handler($this->xml_obj, 'dataHandler');
xml_set_element_handler($this->xml_obj, "startHandler", "endHandler");
}
function parse($path){
if (!($fp = fopen($path, "r"))) {
die("Cannot open XML data file: $path");
return false;
}
while ($data = fread($fp, 4096)) {
if (!xml_parse($this->xml_obj, $data, feof($fp))) {
die(sprintf("XML error: %s at line %d",
xml_error_string(xml_get_error_code($this->xml_obj)),
xml_get_current_line_number($this->xml_obj)));
xml_parser_free($this->xml_obj);
}
}
return true;
}
function startHandler($parser, $name, $attribs){
$_content = array();
if(!empty($attribs))
$_content['attrs'] = $attribs;
array_push($this->output, $_content);
}
function dataHandler($parser, $data){
if(!empty($data) && $data!="\n") {
$_output_idx = count($this->output) - 1;
$this->output[$_output_idx]['content'] .= $data;
}
}
function endHandler($parser, $name){
if(count($this->output) > 1) {
$_data = array_pop($this->output);
$_output_idx = count($this->output) - 1;
$add = array();
if ($_data['attrs'])
$add['attrs'] = $_data['attrs'];
if ($_data['child'])
$add['child'] = $_data['child'];
$this->output[$_output_idx]['child'][$_data['content']] = $add;
}
}
}
?>
Greg S
17-Nov-2005 08:56
If you need utf8_encode support and configure PHP with --disable-all you will have some trouble. Unfortunately the configure options aren't completely documented. If you need utf8 functions and have everything disabled just recompile PHP with --enable-xml and you should be good to go.
compu_global_hyper_mega_net_2 at yahoo dot com
19-Sep-2004 01:35
The documentation regarding white space was never complete I think.
The XML_OPTION_SKIP_WHITE doesn't appear to do anything. I want to preserve the newlines in a cdata section. Setting XML_OPTION_SKIP_WHITE to 0 or false doesn't appear to help. My character_data_handler is getting called once for each line. This obviously should be reflected in the documentation as well. When/how often does the handler get called exactly? Having to build separate test cases is very time consuming.
Inserting newlines myself in my cdata handler is no good either. For non actual CDATA sections that cause my handler to get called, long lines are split up in multiple calls. My handler would not be able to tell the difference whether or not the subsequent calls would be due to the fact that the data is coming from the next line or the fact that some internal buffer is long enough for it to 'flush' out and call the handler.
This behaviour also needs to be properly documented.
odders
18-Mar-2004 10:36
I wrote a simple xml parser mainly to deal with rss version 2. I found lots of examples on the net, but they were all masive and bloated and hard to manipulate.
Output is sent to an array, which holds arrays containg data for each item.
Obviously, you will have to make modifications to the code to suit your needs, but there isnt a lot of code there, so that shouldnt be a problem.
<?php
$currentElements = array();
$newsArray = array();
readXml("./news.xml");
echo("<pre>");
print_r($newsArray);
echo("</pre>");
// Reads XML file into formatted html
function readXML($xmlFile)
{
$xmlParser = xml_parser_create();
xml_parser_set_option($xmlParser, XML_OPTION_CASE_FOLDING, false);
xml_set_element_handler($xmlParser, startElement, endElement);
xml_set_character_data_handler($xmlParser, characterData);
$fp = fopen($xmlFile, "r");
while($data = fread($fp, filesize($xmlFile))){
xml_parse($xmlParser, $data, feof($fp));}
xml_parser_free($xmlParser);
}
// Sets the current XML element, and pushes itself onto the element hierarchy
function startElement($parser, $name, $attrs)
{
global $currentElements, $itemCount;
array_push($currentElements, $name);
if($name == "item"){$itemCount += 1;}
}
// Prints XML data; finds highlights and links
function characterData($parser, $data)
{
global $currentElements, $newsArray, $itemCount;
$currentCount = count($currentElements);
$parentElement = $currentElements[$currentCount-2];
$thisElement = $currentElements[$currentCount-1];
if($parentElement == "item"){
$newsArray[$itemCount-1][$thisElement] = $data;}
else{
switch($name){
case "title":
break;
case "link":
break;
case "description":
break;
case "language":
break;
case "item":
break;}}
}
// If the XML element has ended, it is poped off the hierarchy
function endElement($parser, $name)
{
global $currentElements;
$currentCount = count($currentElements);
if($currentElements[$currentCount-1] == $name){
array_pop($currentElements);}
}
?>
software at serv-a-com dot com
22-Jan-2003 02:08
use:
<?php
while ($data = str_replace("\n","",fread($fp, 4096))){
// ...
}
?>
instead of:
<?php
while ($data = fread($fp, 4096)) {
// ...
}
?>
[UPDATE 17-FEB-2003: This post] resulted in some of the visitors e-mailg me on the carriage return stripping issue with questions. I'll try to make the following mumble as brief and easy to understand as possible.
1. Overview of the 4096 fragmentation issue
As you know the following freads the file 4096 bytes at a time (that is 4KB) this is perhaps ok for testing expat and figuring out how things work, but it it rather dangerous in the production environment. Data may not be fully understandable due to fread fragmentation and improperly formatted due to numerous sources(formats) of data contained within (i.e. end of line delimited CDATA).
<?php
while ($data = fread($fp, 4096)) {
if (!xml_parse($xml_parser, $data, feof($fp))) {
// ...
}
}
?>
Sometimes to save time one may want to load it all up into a one big variable and leave all the worries to expat. I think anything under 500 KB is ok (as long as nobody knows about it). Some may argue that larger variables are acceptable or even necessary because of the magic that take place while parsing using xml_parse. Our XML parser(expat) works and can be successfully implemented only when we know what type of XML data we are dealing with, it's average size and structure of general layout and data contained within tags. For example if the tags are followed by a line delimiter like a new line we can read it with fgets in and with minimal effort make sure that no data will be sent to the function that does not end with a end tag. But this require a fair knowledge of the file's preference for storing XML data and tags (and a bit of code between reading data and xml_parse'ing it).
It will save you a headache.
2. Pre Parser Strings and New Line Delimited Data
One important thing to note at this point is that the xml_parse function requires a string variable. You can manipulate the content of any string variable easily as we all know.
A better approach to removing newlines than:
<?php
while ($data = fread($fp, 4096)) {
$data = preg_replace("/\n|\r/","",$data); //flarp
if (!xml_parse($xml_parser, $data, feof($fp))) {...
?>
Above works across all 3 line-delimited text files (\n, \r, \r\n). But this could potentially (or will most likely) damage or scramble data contained in for example CDATA areas. As far as I am concerned end of line characters should not be used _within_ XML tags. What seems to be the ultimate solution is to pre-parse the loaded data this would require checking the position within the XML document and adding or subtracting (using a in-between fread temporary variable) data based on conditions like: "Is within tag", "Is within CDATA" etc. before fedding it to the parser. This of course opens up a new can of worms (as in parse data for the parser...). (above procedure would take place between fread and xml_parser calls this method would be compatible with the general usage examples on top of the page)
3. The Answer to parsing arbitrary XML and Preprocessor Revisited
You can't just feed any XML document to the parser you constructed and assuming that it will work! You have to know what kind of methods for storing data are used, for example is there a end of line delimited data in the file ?, Are there any carriage returns in the tags etc... XML files come formatted in different ways some are just a one long string of characters with out any end of line markers others have newlines, carriage returns or both (Microsloth Windows). May or may not contain space and other whitespace between tags. For this reason it is important to what I call Normalize the data before feeding it to the parser. You can perform this with regular expressions or plain old str_replace and concatenation. In many cases this can be done to the file it self sometimes to string data on the fly( as shown in the example above). But I feel it is important to normalize the data before even calling the function to call xml_parse. If you have the ability to access all data before that call you can convert it to what you fell the data should have been in the first place and omit many surprises and expensive regular expression substitution (in a tight spot) while fread'ing the data.
guy at bhaktiandvedanta dot com
27-Sep-2002 12:01
For a simple XML parser you can use this function. It doesn't require any extensions to run.
<?php
// Extracts content from XML tag
function GetElementByName ($xml, $start, $end) {
global $pos;
$startpos = strpos($xml, $start);
if ($startpos === false) {
return false;
}
$endpos = strpos($xml, $end);
$endpos = $endpos+strlen($end);
$pos = $endpos;
$endpos = $endpos-$startpos;
$endpos = $endpos - strlen($end);
$tag = substr ($xml, $startpos, $endpos);
$tag = substr ($tag, strlen($start));
return $tag;
}
// Open and read xml file. You can replace this with your xml data.
$file = "data.xml";
$pos = 0;
$Nodes = array();
if (!($fp = fopen($file, "r"))) {
die("could not open XML input");
}
while ($getline = fread($fp, 4096)) {
$data = $data . $getline;
}
$count = 0;
$pos = 0;
// Goes throw XML file and creates an array of all <XML_TAG> tags.
while ($node = GetElementByName($data, "<XML_TAG>", "</XML_TAG>")) {
$Nodes[$count] = $node;
$count++;
$data = substr($data, $pos);
}
// Gets infomation from tag siblings.
for ($i=0; $i<$count; $i++) {
$code = GetElementByName($Nodes[$i], "<Code>", "</Code>");
$desc = GetElementByName($Nodes[$i], "<Description>", "</Description>");
$price = GetElementByName($Nodes[$i], "<BasePrice>", "</BasePrice>");
}
?>
Hope this helps! :)
Guy Laor
dmarsh dot NO dot SPAM dot PLEASE at spscc dot ctc dot edu
18-Sep-2002 12:27
Some reference code I am working on as "XML Library" of which I am folding it info an object. Notice the use of the DEFINE:
Mainly Example 1 and parts of 2 & 3 re-written as an object:
--- MyXMLWalk.lib.php ---
<?php
if (!defined("PHPXMLWalk")) {
define("PHPXMLWalk",TRUE);
class XMLWalk {
var $p; //short for xml parser;
var $e; //short for element stack/array
function prl($x,$i=0) {
ob_start();
print_r($x);
$buf=ob_get_contents();
ob_end_clean();
return join("\n".str_repeat(" ",$i),split("\n",$buf));
}
function XMLWalk() {
$this->p = xml_parser_create();
$this->e = array();
xml_parser_set_option($this->p, XML_OPTION_CASE_FOLDING, true);
xml_set_element_handler($this->p, array(&$this, "startElement"), array(&$this, "endElement"));
xml_set_character_data_handler($this->p, array(&$this, "dataElement"));
register_shutdown_function(array(&$this, "free")); // make a destructor
}
function startElement($parser, $name, $attrs) {
if (count($attrs)>=1) {
$x = $this->prl($attrs, $this->e[$parser]+6);
} else {
$x = "";
}
print str_repeat(" ",$this->e[$parser]+0). "$name $x\n";
$this->e[$parser]++;
$this->e[$parser]++;
}
function dataElement($parser, $data) {
print str_repeat(" ",$this->e[$parser]+0). htmlspecialchars($data, ENT_QUOTES) ."\n";
}
function endElement($parser, $name) {
$this->e[$parser]--;
$this->e[$parser]--;
}
function parse($data, $fp) {
if (!xml_parse($this->p, $data, feof($fp))) {
die(sprintf("XML error: %s at line %d",
xml_error_string(xml_get_error_code($this->p)),
xml_get_current_line_number($this->p)));
}
}
function free() {
xml_parser_free($this->p);
}
} // end of class
} // end of define
?>
--- end of file ---
Calling code:
<?php
...
require("MyXMLWalk.lib.php");
$file = "x.xml";
$xme = new XMLWalk;
if (!($fp = fopen($file, "r"))) {
die("could not open XML input");
}
while ($data = fread($fp, 4096)) {
$xme->parse($data, $fp);
}
...
?>
jon at gettys dot org
14-Aug-2002 01:59
[Editor's note: see also xml_parse_into_struct().]
Very simple routine to convert an XML file into a PHP structure. $obj->xml contains the resulting PHP structure. I would be interested if someone could suggest a cleaner method than the evals I am using.
<?php
$filename = 'sample.xml';
$obj->tree = '$obj->xml';
$obj->xml = '';
function startElement($parser, $name, $attrs) {
global $obj;
// If var already defined, make array
eval('$test=isset('.$obj->tree.'->'.$name.');');
if ($test) {
eval('$tmp='.$obj->tree.'->'.$name.';');
eval('$arr=is_array('.$obj->tree.'->'.$name.');');
if (!$arr) {
eval('unset('.$obj->tree.'->'.$name.');');
eval($obj->tree.'->'.$name.'[0]=$tmp;');
$cnt = 1;
}
else {
eval('$cnt=count('.$obj->tree.'->'.$name.');');
}
$obj->tree .= '->'.$name."[$cnt]";
}
else {
$obj->tree .= '->'.$name;
}
if (count($attrs)) {
eval($obj->tree.'->attr=$attrs;');
}
}
function endElement($parser, $name) {
global $obj;
// Strip off last ->
for($a=strlen($obj->tree);$a>0;$a--) {
if (substr($obj->tree, $a, 2) == '->') {
$obj->tree = substr($obj->tree, 0, $a);
break;
}
}
}
function characterData($parser, $data) {
global $obj;
eval($obj->tree.'->data=\''.$data.'\';');
}
$xml_parser = xml_parser_create();
xml_set_element_handler($xml_parser, "startElement", "endElement");
xml_set_character_data_handler($xml_parser, "characterData");
if (!($fp = fopen($filename, "r"))) {
die("could not open XML input");
}
while ($data = fread($fp, 4096)) {
if (!xml_parse($xml_parser, $data, feof($fp))) {
die(sprintf("XML error: %s at line %d",
xml_error_string(xml_get_error_code($xml_parser)),
xml_get_current_line_number($xml_parser)));
}
}
xml_parser_free($xml_parser);
print_r($obj->xml);
return 0;
?>
hans dot schneider at bbdo-interone dot de
24-Jan-2002 08:43
I had to TRIM the data when I passed one large String containig a wellformed XML-File to xml_parse. The String was read by CURL, which aparently put a BLANK at the end of the String. This BLANK produced a "XML not wellformed"-Error in xml_parse!
sam at cwa dot co dot nz
28-Sep-2000 07:39
I've discovered some unusual behaviour in this API when ampersand entities are parsed in cdata; for some reason the parser breaks up the section around the entities, and calls the handler repeated times for each of the sections. If you don't allow for this oddity and you are trying to put the cdata into a variable, only the last part will be stored.
You can get around this with a line like:
$foo .= $cdata;
If the handler is called several times from the same tag, it will append them, rather than rewriting the variable each time. If the entire cdata section is returned, it doesn't matter.
May happen for other entities, but I haven't investigated.
Took me a while to figure out what was happening; hope this saves someone else the trouble.
Daniel dot Rendall at btinternet dot com
07-Jul-1999 10:21
When using the XML parser, make sure you're not using the magic quotes option (e.g. use set_magic_quotes_runtime(0) if it's not the compiled default), otherwise you'll get 'not well-formed' errors when dealing with tags with attributes set in them.