function parse($path, $data = '')
{
$this->state = 0;
/* reader */
if (!$this->v('reader')) {
ARC2::inc('Reader');
$this->reader =& new ARC2_Reader($this->a, $this);
}
$this->reader->setAcceptHeader('Accept: sparql-results+xml; q=0.9, */*; q=0.1');
$this->reader->activate($path, $data);
$this->x_base = isset($this->a['base']) && $this->a['base'] ? $this->a['base'] : $this->reader->base;
/* xml parser */
$this->initXMLParser();
/* parse */
$first = true;
while ($d = $this->reader->readStream()) {
if (!xml_parse($this->xml_parser, $d, false)) {
$error_str = xml_error_string(xml_get_error_code($this->xml_parser));
$line = xml_get_current_line_number($this->xml_parser);
$this->tmp_error = 'XML error: "' . $error_str . '" at line ' . $line . ' (parsing as ' . $this->getEncoding() . ')';
return $this->addError($this->tmp_error);
}
}
$this->target_encoding = xml_parser_get_option($this->xml_parser, XML_OPTION_TARGET_ENCODING);
xml_parser_free($this->xml_parser);
$this->reader->closeStream();
return $this->done();
}
function parse($path, $data = '', $iso_fallback = false)
{
/* reader */
if (!$this->v('reader')) {
ARC2::inc('Reader');
$this->reader = new ARC2_Reader($this->a, $this);
}
$this->reader->setAcceptHeader('Accept: application/rdf+xml; q=0.9, */*; q=0.1');
$this->reader->activate($path, $data);
$this->x_base = isset($this->a['base']) && $this->a['base'] ? $this->a['base'] : $this->reader->base;
/* xml parser */
$this->initXMLParser();
/* parse */
$first = true;
while ($d = $this->reader->readStream()) {
if (!$this->keep_time_limit) {
@set_time_limit($this->v('time_limit', 60, $this->a));
}
if ($iso_fallback && $first) {
$d = '<?xml version="1.0" encoding="ISO-8859-1"?>' . "\n" . preg_replace('/^\\<\\?xml [^\\>]+\\?\\>\\s*/s', '', $d);
$first = false;
}
preg_match_all('/<<<(.+?\\s*?)*?>>>/', $d, $res);
if (isset($res)) {
foreach ($res[0] as $templ) {
$key = 'template_' . count($this->templates);
$this->templates[$key] = str_replace('<<<', '', str_replace('>>>', '', $templ));
$d = str_replace($templ, $key, $d);
}
}
if (!xml_parse($this->xml_parser, $d, false)) {
$error_str = xml_error_string(xml_get_error_code($this->xml_parser));
$line = xml_get_current_line_number($this->xml_parser);
$this->tmp_error = 'XML error: "' . $error_str . '" at line ' . $line . ' (parsing as ' . $this->getEncoding() . ')';
if (!$iso_fallback && preg_match("/Invalid character/i", $error_str)) {
xml_parser_free($this->xml_parser);
unset($this->xml_parser);
$this->reader->closeStream();
$this->__init();
$this->encoding = 'ISO-8859-1';
unset($this->xml_parser);
unset($this->reader);
return $this->parse($path, $data, true);
} else {
return $this->addError($this->tmp_error);
}
}
}
$this->target_encoding = xml_parser_get_option($this->xml_parser, XML_OPTION_TARGET_ENCODING);
xml_parser_free($this->xml_parser);
$this->reader->closeStream();
unset($this->reader);
return $this->done();
}
protected function parseXML($xml)
{
$xml_parser = xml_parser_create();
// use case-folding so we are sure to find the tag in $map_array
xml_parser_set_option($xml_parser, XML_OPTION_CASE_FOLDING, true);
xml_parser_set_option($xml_parser, XML_OPTION_SKIP_WHITE, true);
$this->setEncoding(xml_parser_get_option($xml_parser, XML_OPTION_TARGET_ENCODING));
xml_set_element_handler($xml_parser, array($this, "startElement"), array($this, "endElement"));
xml_set_character_data_handler($xml_parser, array($this, "characterData"));
if (!xml_parse($xml_parser, $xml)) {
throw new KurogoDataException(sprintf("XML error: %s at line %d", xml_error_string(xml_get_error_code($xml_parser)), xml_get_current_line_number($xml_parser)));
}
xml_parser_free($xml_parser);
}
function parse($path, $data = '', $iso_fallback = false)
{
$this->nodes = array();
$this->node_count = 0;
$this->level = 0;
/* reader */
if (!$this->v('reader')) {
ARC2::inc('Reader');
$this->reader = new ARC2_Reader($this->a, $this);
}
$this->reader->setAcceptHeader('Accept: application/xml; q=0.9, */*; q=0.1');
$this->reader->activate($path, $data);
$this->x_base = isset($this->a['base']) && $this->a['base'] ? $this->a['base'] : $this->reader->base;
$this->base = $this->x_base;
$this->doc_url = $this->reader->base;
/* xml parser */
$this->initXMLParser();
/* parse */
$first = true;
while ($d = $this->reader->readStream(1)) {
if ($iso_fallback && $first) {
$d = '<?xml version="1.0" encoding="ISO-8859-1"?>' . "\n" . preg_replace('/^\\<\\?xml [^\\>]+\\?\\>\\s*/s', '', $d);
}
if (!xml_parse($this->xml_parser, $d, false)) {
$error_str = xml_error_string(xml_get_error_code($this->xml_parser));
$line = xml_get_current_line_number($this->xml_parser);
if (!$iso_fallback && preg_match("/Invalid character/i", $error_str)) {
xml_parser_free($this->xml_parser);
unset($this->xml_parser);
$this->reader->closeStream();
unset($this->reader);
$this->__init();
$this->encoding = 'ISO-8859-1';
$this->initXMLParser();
return $this->parse($path, $data, true);
} else {
return $this->addError('XML error: "' . $error_str . '" at line ' . $line . ' (parsing as ' . $this->getEncoding() . ')');
}
}
$first = false;
}
$this->target_encoding = xml_parser_get_option($this->xml_parser, XML_OPTION_TARGET_ENCODING);
xml_parser_free($this->xml_parser);
$this->reader->closeStream();
unset($this->reader);
return $this->done();
}
public function parseData($contents)
{
$this->clearInternalCache();
$xml_parser = xml_parser_create();
// use case-folding so we are sure to find the tag in $map_array
xml_parser_set_option($xml_parser, XML_OPTION_CASE_FOLDING, true);
xml_parser_set_option($xml_parser, XML_OPTION_SKIP_WHITE, true);
$this->setEncoding(xml_parser_get_option($xml_parser, XML_OPTION_TARGET_ENCODING));
xml_set_element_handler($xml_parser, array($this, "startElement"), array($this, "endElement"));
xml_set_character_data_handler($xml_parser, array($this, "characterData"));
if (!xml_parse($xml_parser, $contents)) {
throw new KurogoDataException(sprintf("XML error: %s at line %d", xml_error_string(xml_get_error_code($xml_parser)), xml_get_current_line_number($xml_parser)));
}
xml_parser_free($xml_parser);
$this->setTotalItems(count($this->items));
return $this->items;
}
function xmlParser($file, $max)
{
$this->max_news = $max;
$this->xml_parser = xml_parser_create();
xml_set_object($this->xml_parser, $this);
xml_set_element_handler($this->xml_parser, "startElement", "endElement");
xml_set_character_data_handler($this->xml_parser, 'elementContent');
$this->rss_option = xml_parser_get_option($this->xml_parser, XML_OPTION_TARGET_ENCODING);
if (!($data = $this->_get_contents($file))) {
$this->content[0]['title'] = "Fatal Error";
$this->content[0]['description'] = "Fatal Error: could not open XML input (" . $file . ")";
$this->content[0]['link'] = "#";
$this->content[0]['date'] = time();
}
preg_replace("#encoding=\"(.+?)\"#ie", "\$this->get_charset('\\1')", $data);
if (!xml_parse($this->xml_parser, $data)) {
$error_code = xml_get_error_code($this->xml_parser);
$error_line = xml_get_current_line_number($this->xml_parser);
if ($error_code == 4) {
$this->content = array();
$this->index = 0;
$this->tag_open = false;
$this->tagname = "";
$this->xml_parser = xml_parser_create();
xml_set_object($this->xml_parser, $this);
xml_set_element_handler($this->xml_parser, "startElement", "endElement");
xml_set_character_data_handler($this->xml_parser, 'elementContent');
$this->rss_option = xml_parser_get_option($this->xml_parser, XML_OPTION_TARGET_ENCODING);
$data = iconv($this->rss_charset, "utf-8", $data);
if (!xml_parse($this->xml_parser, $data)) {
$this->content[0]['title'] = "XML error in File: " . $file;
$this->content[0]['description'] = sprintf("XML error: %s at line %d", xml_error_string(xml_get_error_code($this->xml_parser)), xml_get_current_line_number($this->xml_parser));
$this->content[0]['link'] = "#";
$this->content[0]['date'] = time();
}
} else {
$this->content[0]['title'] = "XML error in File: " . $file;
$this->content[0]['description'] = sprintf("XML error: %s at line %d", xml_error_string($error_code), $error_line);
$this->content[0]['link'] = "#";
$this->content[0]['date'] = time();
}
}
xml_parser_free($this->xml_parser);
}
/**
* get option
*
* @param Charcoal_Integer|integer $option XML_OPTION_CASE_FOLDING or XML_OPTION_TARGET_ENCODING
*/
public function getRawOption($option)
{
Charcoal_ParamTrait::validateInteger(1, $option);
if (!$this->parser) {
_throw(new PhpXmlParserComponentException('parser object is not created'));
}
return xml_parser_get_option($this->parser, ui($option));
}
public function getOption($option)
{
return $this->parser ? xml_parser_get_option($this->parser, $option) : false;
}
<?php /* Prototype : proto bool xml_set_notation_decl_handler ( resource $parser , callback $handler ) * Description: Sets the notation declaration handler function for the XML parser. * Source code: ext/xml/xml.c * Alias to functions: */ echo "Simple testcase for xml_parser_get_option() function\n"; $parser = xml_parser_create_ns(); var_dump(xml_parser_get_option($parser, XML_OPTION_CASE_FOLDING)); var_dump(xml_parser_get_option($parser, XML_OPTION_TARGET_ENCODING)); var_dump(xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, 1)); var_dump(xml_parser_set_option($parser, XML_OPTION_TARGET_ENCODING, "ISO-8859-1")); var_dump(xml_parser_get_option($parser, XML_OPTION_CASE_FOLDING)); var_dump(xml_parser_get_option($parser, XML_OPTION_TARGET_ENCODING)); var_dump(xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, 0)); var_dump(xml_parser_set_option($parser, XML_OPTION_TARGET_ENCODING, "UTF-8")); var_dump(xml_parser_get_option($parser, XML_OPTION_CASE_FOLDING)); var_dump(xml_parser_get_option($parser, XML_OPTION_TARGET_ENCODING)); var_dump(xml_parser_set_option($parser, XML_OPTION_TARGET_ENCODING, "US-ASCII")); var_dump(xml_parser_get_option($parser, XML_OPTION_TARGET_ENCODING)); xml_parser_free($parser); echo "Done\n";
/**
* Parse XML data
*
* @param var data either a string or an xml.parser.InputSource
* @param string source default NULL optional source identifier, will show up in exception
* @return bool
* @throws xml.XMLFormatException in case the data could not be parsed
* @throws lang.NullPointerException in case a parser could not be created
*/
public function parse($data, $source = null)
{
if ($parser = xml_parser_create('')) {
xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, false);
if (null === $this->encoding) {
$this->encoding = xml_parser_get_option($parser, XML_OPTION_TARGET_ENCODING);
} else {
xml_parser_set_option($parser, XML_OPTION_TARGET_ENCODING, $this->encoding);
}
// Register callback
if ($this->callback) {
xml_set_object($parser, $this->callback);
$this->callback->onBegin($this);
xml_set_element_handler($parser, 'onStartElement', 'onEndElement');
xml_set_character_data_handler($parser, 'onCData');
xml_set_default_handler($parser, 'onDefault');
}
// Parse streams while reading data
if ($data instanceof InputSource) {
$stream = $data->getStream();
$source || ($source = $data->getSource());
do {
if ($stream->available()) {
$r = xml_parse($parser, $stream->read(), false);
} else {
$r = xml_parse($parser, '', true);
break;
}
} while ($r);
} else {
$r = xml_parse($parser, $data, true);
}
// Check for errors
if (!$r) {
$type = xml_get_error_code($parser);
$line = xml_get_current_line_number($parser);
$column = xml_get_current_column_number($parser);
$message = xml_error_string($type);
xml_parser_free($parser);
libxml_clear_errors();
$e = new XMLFormatException($message, $type, $source, $line, $column);
$this->callback && $this->callback->onError($this, $e);
throw $e;
}
xml_parser_free($parser);
$r = true;
$this->callback && ($r = $this->callback->onFinish($this));
return $r;
}
throw new \lang\NullPointerException('Could not create parser');
}
/**
* Récupérer toutes les informations dans un fichier DocBook.
* @param string $filename nom du fichier à analyser
* @return boolean booléen indiquant si le document XML a pu être lu
* @throws PEAR_ErrorStack
*/
function setFromDocbook($filename)
{
$xmltree = new XML_Tree($filename);
$xmltree->setErrorHandling(PEAR_ERROR_CALLBACK, array(&$this, '_XMLTreeErrorHandler'));
$article = $xmltree->getTreeFromFile();
if ($this->errors->hasErrors('error')) {
return false;
}
$this->charset = xml_parser_get_option($xmltree->parser, XML_OPTION_TARGET_ENCODING);
$this->repertoire = $this->stringValue(@$article->getAttribute("id"));
$this->type = $this->stringValue(@$article->getAttribute("role"));
$this->lang = $this->stringValue(@$article->getAttribute("lang"));
$artinfonode = $this->getElementsByTagName($article, "articleinfo");
if (count($artinfonode) == 0) {
$this->errors->push(OW_MISSING_NODE, 'error', array('file' => $filename, 'node' => 'articleinfo'));
return false;
}
/* Traitement particulier pour les balises <author> */
$auteurs = array();
foreach ($this->getElementsByTagName($artinfonode[0], "author") as $author) {
$firstnames = $this->getElementsByTagName($author, "firstname");
$surnames = $this->getElementsByTagName($author, "surname");
$nom = $this->stringValue(ucfirst(implode(' ', $firstnames)) . ' ' . ucfirst(implode(' ', $surnames)));
if (preg_match('/^\\s*$/', $nom) != 0) {
$auteurs[] = $nom;
}
}
$this->auteurs = implode(', ', $auteurs);
/* Traitement des autres méta-données */
$this->classement = array();
/**
* Tableau des balises que l'on récupère sans traitement particulier
*/
$autotags = array('title', 'titleabbrev', 'pubdate', 'date', 'abstract');
foreach ($artinfonode[0]->children as $child) {
$name = $child->name;
if (in_array($name, $autotags)) {
$this->{$name} = $this->stringValue($child);
}
if ($name == 'subjectset') {
foreach ($this->getElementsByTagName($child, 'subject') as $subjnode) {
$attribute = $this->stringValue($subjnode->getAttribute('role'));
if (empty($attribute)) {
continue;
}
$this->classement[$attribute] = array();
foreach ($this->getElementsByTagName($subjnode, 'subjectterm') as $entry) {
$this->classement[$attribute][] = $this->stringValue($entry);
}
}
}
}
return true;
}
/**
* Fetch a parser options
*
* @return mixed the option value
* @access public
*/
public function getOption($option)
{
if ($this->parser === null) {
throw new ParserException('Parser not been registered');
}
return xml_parser_get_option($this->parser, $option);
}
<?php
/* Prototype : proto int xml_parser_get_option(resource parser, int option)
* Description: Get options from an XML parser
* Source code: ext/xml/xml.c
* Alias to functions:
*/
echo "*** Testing xml_parser_get_option() : usage variations ***\n";
error_reporting(E_ALL & ~E_NOTICE);
class aClass
{
function __toString()
{
return "Some Ascii Data";
}
}
// Initialise function arguments not being substituted (if any)
$option = 10;
//get an unset variable
$unset_var = 10;
unset($unset_var);
$fp = fopen(__FILE__, "r");
//array of values to iterate over
$values = array(0, 1, 12345, -2345, 10.5, -10.5, 101234567000.0, 1.07654321E-9, 0.5, array(), array(0), array(1), array(1, 2), array('color' => 'red', 'item' => 'pen'), NULL, null, true, false, TRUE, FALSE, "", '', "string", 'string', new aClass(), $fp, $undefined_var, $unset_var);
// loop through each element of the array for parser
foreach ($values as $value) {
echo @"\nArg value {$value} \n";
var_dump(xml_parser_get_option($value, $option));
}
fclose($fp);
echo "Done";
function parse_data($data){
$this->init(false);
$this->encoding=($this->encoding=="auto") ? "UTF-8" : $this->encoding;
$this->create_parser();
if($this->save_data){
$this->data=$data;
}
if(!$success=xml_parse($this->parser, $data, true)){
$error_str = xml_error_string(xml_get_error_code($this->parser));
$line = xml_get_current_line_number($this->parser);
xml_parser_free($this->parser);
return "XML error: '".$error_str."' at line ".$line."\n";
}
$this->target_encoding=xml_parser_get_option($this->parser, XML_OPTION_TARGET_ENCODING);
xml_parser_free($this->parser);
return $this->done();
}
/**
* Récupérer toutes les informations dans un fichier DocBook.
* @param string $filename nom du fichier à analyser
* @return object DocInfos objet contenant les infos de l'article, ou un tableau de chaînes contenant des messages d'erreurs
* @todo Relire le code, il ne vérifie parfois pas assez les données d'entrées/les erreurs qui peuvent survenir pendant le traitement.
*/
function docbookGetArticleInfoFromFile($filename)
{
$doc = new DocInfos();
$errors =& PEAR_ErrorStack::singleton('OpenWeb_Backend_DocbookParse');
/* Extrait du XML toutes les informations pour remplir la classe Article */
/* Obtenir un arbre à partir du fichier XML */
$xmltree = new XML_Tree($filename);
/* lecture du fichier qui récupère la balise <article> */
$article = $xmltree->getTreeFromFile();
if ($xmltree->isError($article)) {
$erreur = $article->getUserInfo();
if ($erreur == '') {
$erreur = 'probablement un document mal formé';
}
return array('Impossible de parser le fichier XML (' . $erreur . ')');
}
$charset = xml_parser_get_option($xmltree->parser, XML_OPTION_TARGET_ENCODING);
$doc->repertoire = _toUtf8($charset, trim($article->getAttribute("id")));
$doc->type = _toUtf8($charset, array_key_exists("role", $article->attributes) ? $article->getAttribute("role") : "article");
$doc->lang = _toUtf8($charset, array_key_exists("lang", $article->attributes) ? $article->getAttribute("lang") : "fr");
$artinfonode = getElementsByTagName($article, "articleinfo");
if (count($artinfonode) == 0) {
return array('Impossible de continuer à parser le fichier XML : il manque la section articleinfo du docbook');
}
/* Traitement particulier pour les balises <author> */
$auteurs = array();
foreach (getElementsByTagName($artinfonode[0], "author") as $author) {
$firstnames = getElementsByTagName($author, "firstname");
$surnames = getElementsByTagName($author, "surname");
$auteurs[] = (count($firstnames) ? ucfirst(trim(tree2text($firstnames[0]))) : "") . ' ' . (count($surnames) ? ucfirst(trim(tree2text($surnames[0]))) : "");
}
$doc->auteurs = _toUtf8($charset, implode(', ', $auteurs));
$doc->classement = array();
foreach ($artinfonode[0]->children as $child) {
/* Récupération des balises <title>, <pubdate> et <date> */
if (!strcmp($child->name, "title")) {
$doc->titre = _toUtf8($charset, tree2text($child));
}
if (!strcmp($child->name, "titleabbrev")) {
$doc->titremini = _toUtf8($charset, tree2text($child));
}
if (!strcmp($child->name, "pubdate")) {
$doc->pubdate = _toUtf8($charset, tree2text($child));
}
if (!strcmp($child->name, "date")) {
$doc->update = _toUtf8($charset, tree2text($child));
}
if (!strcmp($child->name, "subjectset")) {
foreach (getElementsByTagName($child, "subject") as $subjnode) {
$attribute = _toUtf8($charset, $subjnode->getAttribute("role"));
$doc->classement[$attribute] = array();
foreach (getElementsByTagName($subjnode, "subjectterm") as $entry) {
$doc->classement[$attribute][] = _toUtf8($charset, tree2text($entry));
}
}
}
if (!strcmp($child->name, "abstract")) {
$doc->accroche = _toUtf8($charset, tree2text($child));
}
}
return $doc;
}
/* Prototype : proto int xml_parser_get_option(resource parser, int option)
* Description: Get options from an XML parser
* Source code: ext/xml/xml.c
* Alias to functions:
*/
echo "*** Testing xml_parser_get_option() : usage variations ***\n";
error_reporting(E_ALL & ~E_NOTICE);
class aClass
{
function __toString()
{
return "Some Ascii Data";
}
}
// Initialise function arguments not being substituted (if any)
$parser = xml_parser_create();
//get an unset variable
$unset_var = 10;
unset($unset_var);
$fp = fopen(__FILE__, "r");
//array of values to iterate over
$values = array(12345, -2345, 10.5, -10.5, 101234567000.0, 1.07654321E-9, 0.5, array(), array(0), array(1), array(1, 2), array('color' => 'red', 'item' => 'pen'), NULL, null, true, false, TRUE, FALSE, "", '', "string", 'string', new aClass(), $fp, $undefined_var, $unset_var);
// loop through each element of the array for option
foreach ($values as $value) {
echo @"\nArg value {$value} \n";
var_dump(xml_parser_get_option($parser, $value));
}
fclose($fp);
xml_parser_free($parser);
echo "Done";
<?php /* Prototype : proto int xml_parser_get_option(resource parser, int option) * Description: Get options from an XML parser * Source code: ext/xml/xml.c * Alias to functions: */ echo "*** Testing xml_parser_get_option() : error conditions ***\n"; //Test xml_parser_get_option with one more than the expected number of arguments echo "\n-- Testing xml_parser_get_option() function with more than expected no. of arguments --\n"; $option = 10; $extra_arg = 10; var_dump(xml_parser_get_option(null, $option, $extra_arg)); // Testing xml_parser_get_option with one less than the expected number of arguments echo "\n-- Testing xml_parser_get_option() function with less than expected no. of arguments --\n"; var_dump(xml_parser_get_option(null)); echo "Done";
/**
* get xml parser option
* @final
* @param $option
*/
function getOption($option)
{
return xml_parser_get_option($this->_p, $option);
}
<?php
require_once '../../includes/header.php';
?>
<pre>
<?php
//We firstly need to create the parser
$parser = xml_parser_create();
$perserOption = xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, 0);
var_dump($perserOption);
////bool(true)
$perserGetOption = xml_parser_get_option($parser, XML_OPTION_CASE_FOLDING);
var_dump($perserGetOption);
//int(0)
//Warning: xml_parser_get_option(): Unknown option
$perserGetOption = xml_parser_get_option($parser, XML_OPTION_SKIP_TAGSTART);
var_dump($perserGetOption);
//bool(false)
$xmlString = <<<XML
<?xml version='1.0' standalone='yes'?>
<movies>
<movie>
<title>PHP: Behind the Parser</title>
<characters>
<character>
<name>Ms. Coder</name>
<actor>Onlivia Actora</actor>
</character>
<character>
<name>Mr. Coder</name>
<actor>El ActÓr</actor>
