Question

I need to convert an XML document into JSON, in order to easily access the data in JavaScript. I am currently using this method to convert the XML into JSON:

json_encode(new SimpleXMLElement($xml, LIBXML_NOCDATA));

However, I ran into a problem when an element only contains 1 child element. When it is parsed with SimpleXML, it is treated as an object instead of an array. I want them to always be treated as arrays, unless the element only contains text.

Example:

$xml = <<<END
<xml>
  <TESTS>
    <TEST>TEXT HERE</TEST>
  </TESTS>
</xml>
END;

echo json_encode(new SimpleXMLElement($xml, LIBXML_NOCDATA));

This outputs:

{"TESTS":{"TEST":"TEXT HERE"}}

If I add another element under , then the output is how I want it:

$xml = <<<END
<xml>
  <TESTS>
    <TEST>TEXT HERE</TEST>
    <TEST>MORE TEXT HERE</TEST>
  </TESTS>
</xml>
END;

echo json_encode(new SimpleXMLElement($xml, LIBXML_NOCDATA));

Output:

{"TESTS":{"TEST":["TEXT HERE","TEXT HERE"]}}

Note how the elements are contained inside a JSON array instead of a JSON object. Is there a way to force elements to be parsed as arrays?

Answer 1

I had to deal with the same situation. Here is a quick first solution to the problem – works fine for your example.

class JsonWithArrays
{
    protected $root, $callback;

    public function __construct( SimpleXMLElement $root )
    {
        $this->root = $root;
    }

    /**
     * Set a callback to return if a node should be represented as an array
     * under any circumstances.
     *
     * The callback receives two parameters to react to: the SimpleXMLNode in
     * question, and the nesting level of that node.
     */
    public function use_callback_forcing_array ( $callback )
    {
        $this->callback = $callback;
        return $this;
    }

    public function to_json ()
    {
        $transformed = $this->transform_subnodes( $this->root, new stdClass(), 0 );
        return json_encode( $transformed );
    }

    protected function transform_subnodes ( SimpleXMLElement $parent, stdClass $transformed_parent, $nesting_level )
    {
        $nesting_level++;

        foreach( $parent->children() as $node )
        {
            $name = $node->getName();
            $value = (string) $node;

            if ( count( $node->children() ) > 0 )
            {
                $transformed_parent->$name = new stdClass();
                $this->transform_subnodes( $node, $transformed_parent->$name, $nesting_level );
            }
            elseif ( count( $parent->$name ) > 1 or $this->force_array( $node, $nesting_level ) )
            {
                $transformed_parent->{$name}[] = $value;
            }
            else
            {
                $transformed_parent->$name = $value;
            }
        }

        return $transformed_parent;
    }

    protected function force_array ( $node, $nesting_level )
    {
        if ( is_callable( $this->callback ) )
        {
            return call_user_func( $this->callback, $node, $nesting_level );
        }
        else
        {
            return false;
        }
    }
}

$xml = <<<END
<xml> 
  <TESTS> 
    <TEST>TEXT HERE</TEST> 
  </TESTS> 
</xml> 
END;

$xml2 = <<<END
<xml> 
  <TESTS> 
    <TEST>TEXT HERE</TEST> 
    <TEST>MORE TEXT HERE</TEST> 
  </TESTS> 
</xml> 
END;

// Callback using the node name. Could just as well be done using the nesting
// level.
function cb_testnode_as_array( SimpleXMLElement $node, $nesting_level )
{
    return $node->getName() == 'TEST';
}

$transform = new JsonWithArrays( new SimpleXMLElement($xml, LIBXML_NOCDATA) );
echo $transform
    ->use_callback_forcing_array( 'cb_testnode_as_array' )
    ->to_json();

echo PHP_EOL;

$transform2 = new JsonWithArrays( new SimpleXMLElement($xml2, LIBXML_NOCDATA) );
echo $transform2
    ->use_callback_forcing_array( 'cb_testnode_as_array' )
    ->to_json();