Анализатор XML с parse_into_struct, превращенный в структуру массива дерева:
<?php
/**
* What to use for XML parsing / reading in PHP4
* @link http://stackoverflow.com/q/132233/367456
*/
$encoding = 'US-ASCII';
// https://gist.github.com/hakre/46386de578619fbd898c
$path = dirname(__FILE__) . '/time-series-example.xml';
$parser_creator = 'xml_parser_create'; // alternative creator is 'xml_parser_create_ns'
if (!function_exists($parser_creator)) {
trigger_error(
"XML Parsers' $parser_creator() not found. XML Parser "
. '<http://php.net/xml> is required, activate it in your PHP configuration.'
, E_USER_ERROR
);
return;
}
$parser = $parser_creator($encoding);
if (!$parser) {
trigger_error(sprintf('Unable to create a parser (Encoding: "%s")', $encoding), E_USER_ERROR);
return;
}
xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, 0);
xml_parser_set_option($parser, XML_OPTION_SKIP_WHITE, 1);
$data = file_get_contents($path);
if ($data === FALSE) {
trigger_error(sprintf('Unable to open file "%s" for reading', $path));
return;
}
$result = xml_parse_into_struct($parser, $data, $xml_struct_values);
unset($data);
xml_parser_free($parser);
unset($parser);
if ($result === 0) {
trigger_error(sprintf('Unable to parse data of file "%s" as XML', $path));
return;
}
define('TREE_NODE_TAG', 'tagName');
define('TREE_NODE_ATTRIBUTES', 'attributes');
define('TREE_NODE_CHILDREN', 'children');
define('TREE_NODE_TYPE_TAG', 'array');
define('TREE_NODE_TYPE_TEXT', 'string');
define('TREE_NODE_TYPE_NONE', 'NULL');
/**
* XML Parser indezies for parse into struct values
*/
define('XML_STRUCT_VALUE_TYPE', 'type');
define('XML_STRUCT_VALUE_LEVEL', 'level');
define('XML_STRUCT_VALUE_TAG', 'tag');
define('XML_STRUCT_VALUE_ATTRIBUTES', 'attributes');
define('XML_STRUCT_VALUE_VALUE', 'value');
/**
* XML Parser supported node types
*/
define('XML_STRUCT_TYPE_OPEN', 'open');
define('XML_STRUCT_TYPE_COMPLETE', 'complete');
define('XML_STRUCT_TYPE_CDATA', 'cdata');
define('XML_STRUCT_TYPE_CLOSE', 'close');
/**
* Tree Creator
* @return array
*/
function tree_create()
{
return array(
array(
TREE_NODE_TAG => NULL,
TREE_NODE_ATTRIBUTES => NULL,
TREE_NODE_CHILDREN => array(),
)
);
}
/**
* Add Tree Node into Tree a Level
*
* @param $tree
* @param $level
* @param $node
* @return array|bool Tree with the Node added or FALSE on error
*/
function tree_add_node($tree, $level, $node)
{
$type = gettype($node);
switch ($type) {
case TREE_NODE_TYPE_TEXT:
$level++;
break;
case TREE_NODE_TYPE_TAG:
break;
case TREE_NODE_TYPE_NONE:
trigger_error(sprintf('Can not add Tree Node of type None, keeping tree unchanged', $type, E_USER_NOTICE));
return $tree;
default:
trigger_error(sprintf('Can not add Tree Node of type "%s"', $type), E_USER_ERROR);
return FALSE;
}
if (!isset($tree[$level - 1])) {
trigger_error("There is no parent for level $level");
return FALSE;
}
$parent = & $tree[$level - 1];
if (isset($parent[TREE_NODE_CHILDREN]) && !is_array($parent[TREE_NODE_CHILDREN])) {
trigger_error("There are no children in parent for level $level");
return FALSE;
}
$parent[TREE_NODE_CHILDREN][] = & $node;
$tree[$level] = & $node;
return $tree;
}
/**
* Creator of a Tree Node
*
* @param $value XML Node
* @return array Tree Node
*/
function tree_node_create_from_xml_struct_value($value)
{
static $xml_node_default_types = array(
XML_STRUCT_VALUE_ATTRIBUTES => NULL,
XML_STRUCT_VALUE_VALUE => NULL,
);
$orig = $value;
$value += $xml_node_default_types;
switch ($value[XML_STRUCT_VALUE_TYPE]) {
case XML_STRUCT_TYPE_OPEN:
case XML_STRUCT_TYPE_COMPLETE:
$node = array(
TREE_NODE_TAG => $value[XML_STRUCT_VALUE_TAG],
// '__debug1' => $orig,
);
if (isset($value[XML_STRUCT_VALUE_ATTRIBUTES])) {
$node[TREE_NODE_ATTRIBUTES] = $value[XML_STRUCT_VALUE_ATTRIBUTES];
}
if (isset($value[XML_STRUCT_VALUE_VALUE])) {
$node[TREE_NODE_CHILDREN] = (array)$value[XML_STRUCT_VALUE_VALUE];
}
return $node;
case XML_STRUCT_TYPE_CDATA:
// TREE_NODE_TYPE_TEXT
return $value[XML_STRUCT_VALUE_VALUE];
case XML_STRUCT_TYPE_CLOSE:
return NULL;
default:
trigger_error(
sprintf(
'Unkonwn Xml Node Type "%s": %s', $value[XML_STRUCT_VALUE_TYPE], var_export($value, TRUE)
)
);
return FALSE;
}
}
$tree = tree_create();
while ($tree && $value = array_shift($xml_struct_values)) {
$node = tree_node_create_from_xml_struct_value($value);
if (NULL === $node) {
continue;
}
$tree = tree_add_node($tree, $value[XML_STRUCT_VALUE_LEVEL], $node);
unset($node);
}
if (!$tree) {
trigger_error('Parse error');
return;
}
if ($xml_struct_values) {
trigger_error(sprintf('Unable to process whole parsed XML array (%d elements left)', count($xml_struct_values)));
return;
}
// tree root is the first child of level 0
print_r($tree[0][TREE_NODE_CHILDREN][0]);
Выход:
Array
(
[tagName] => dwml
[attributes] => Array
(
[version] => 1.0
[xmlns:xsd] => http://www.w3.org/2001/XMLSchema
[xmlns:xsi] => http://www.w3.org/2001/XMLSchema-instance
[xsi:noNamespaceSchemaLocation] => http://www.nws.noaa.gov/forecasts/xml/DWMLgen/schema/DWML.xsd
)
[children] => Array
(
[0] => Array
(
[tagName] => head
[children] => Array
(
[0] => Array
(
[tagName] => product
[attributes] => Array
(
[srsName] => WGS 1984
[concise-name] => time-series
[operational-mode] => official
)
[children] => Array
(
[0] => Array
(
[tagName] => title
[children] => Array
(
[0] => NOAA's National Weather Service Forecast Data
)
)
[1] => Array
(
[tagName] => field
[children] => Array
(
[0] => meteorological
)
)
[2] => Array
(
[tagName] => category
[children] => Array
(
[0] => forecast
)
)
[3] => Array
(
[tagName] => creation-date
[attributes] => Array
(
[refresh-frequency] => PT1H
)
[children] => Array
(
[0] => 2013-11-02T06:51:17Z
)
)
)
)
[1] => Array
(
[tagName] => source
[children] => Array
(
[0] => Array
(
[tagName] => more-information
[children] => Array
(
[0] => http://www.nws.noaa.gov/forecasts/xml/
)
)
[1] => Array
(
[tagName] => production-center
[children] => Array
(
[0] => Meteorological Development Laboratory
[1] => Array
(
[tagName] => sub-center
[children] => Array
(
[0] => Product Generation Branch
)
)
)
)
[2] => Array
(
[tagName] => disclaimer
[children] => Array
(
[0] => http://www.nws.noaa.gov/disclaimer.html
)
)
[3] => Array
(
[tagName] => credit
[children] => Array
(
[0] => http://www.weather.gov/
)
)
[4] => Array
(
[tagName] => credit-logo
[children] => Array
(
[0] => http://www.weather.gov/images/xml_logo.gif
)
)
[5] => Array
(
[tagName] => feedback
[children] => Array
(
[0] => http://www.weather.gov/feedback.php
)
)
)
)
)
)
[1] => Array
(
[tagName] => data
[children] => Array
(
[0] => Array
(
[tagName] => location
[children] => Array
(
[0] => Array
(
[tagName] => location-key
[children] => Array
(
[0] => point1
)
)
[1] => Array
(
[tagName] => point
[attributes] => Array
(
[latitude] => 40.00
[longitude] => -120.00
)
)
)
)
[1] => Array
(
[tagName] => moreWeatherInformation
[attributes] => Array
(
[applicable-location] => point1
)
[children] => Array
(
[0] => http://forecast.weather.gov/MapClick.php?textField1=40.00&textField2=-120.00
)
)
[2] => Array
(
[tagName] => time-layout
[attributes] => Array
(
[time-coordinate] => local
[summarization] => none
)
[children] => Array
(
[0] => Array
(
[tagName] => layout-key
[children] => Array
(
[0] => k-p24h-n4-1
)
)
[1] => Array
(
[tagName] => start-valid-time
[children] => Array
(
[0] => 2013-11-02T08:00:00-07:00
)
)
[2] => Array
(
[tagName] => end-valid-time
[children] => Array
(
[0] => 2013-11-02T20:00:00-07:00
)
)
[3] => Array
(
[tagName] => start-valid-time
[children] => Array
(
[0] => 2013-11-03T07:00:00-08:00
)
)
[4] => Array
(
[tagName] => end-valid-time
[children] => Array
(
[0] => 2013-11-03T19:00:00-08:00
)
)
[5] => Array
(
[tagName] => start-valid-time
[children] => Array
(
[0] => 2013-11-04T07:00:00-08:00
)
)
[6] => Array
(
[tagName] => end-valid-time
[children] => Array
(
[0] => 2013-11-04T19:00:00-08:00
)
)
[7] => Array
(
[tagName] => start-valid-time
[children] => Array
(
[0] => 2013-11-05T07:00:00-08:00
)
)
[8] => Array
(
[tagName] => end-valid-time
[children] => Array
(
[0] => 2013-11-05T19:00:00-08:00
)
)
)
)
[3] => Array
(
[tagName] => time-layout
[attributes] => Array
(
[time-coordinate] => local
[summarization] => none
)
[children] => Array
(
[0] => Array
(
[tagName] => layout-key
[children] => Array
(
[0] => k-p24h-n5-2
)
)
[1] => Array
(
[tagName] => start-valid-time
[children] => Array
(
[0] => 2013-11-01T20:00:00-07:00
)
)
[2] => Array
(
[tagName] => end-valid-time
[children] => Array
(
[0] => 2013-11-02T09:00:00-07:00
)
)
[3] => Array
(
[tagName] => start-valid-time
[children] => Array
(
[0] => 2013-11-02T19:00:00-07:00
)
)
...
[10] => Array
(
[tagName] => end-valid-time
[children] => Array
(
[0] => 2013-11-06T08:00:00-08:00
)
)
)
)
[4] => Array
(
[tagName] => time-layout
[attributes] => Array
(
[time-coordinate] => local
[summarization] => none
)
[children] => Array
(
[0] => Array
(
[tagName] => layout-key
[children] => Array
(
[0] => k-p12h-n9-3
)
)
[1] => Array
(
[tagName] => start-valid-time
[children] => Array
(
[0] => 2013-11-01T17:00:00-07:00
)
)
...