Generator.php

Go to the documentation of this file.

<?php

class HTMLPurifier_Generator
{

    private $_xhtml = true;

    private $_scriptFix = false;

    private $_def;

    private $_sortAttr;

    protected $config;

    public function __construct($config, $context) {
        $this->config = $config;
        $this->_scriptFix = $config->get('Output.CommentScriptContents');
        $this->_sortAttr = $config->get('Output.SortAttr');
        $this->_def = $config->getHTMLDefinition();
        $this->_xhtml = $this->_def->doctype->xml;
    }

    public function generateFromTokens($tokens) {
        if (!$tokens) return '';

        // Basic algorithm
        $html = '';
        for ($i = 0, $size = count($tokens); $i < $size; $i++) {
            if ($this->_scriptFix && $tokens[$i]->name === 'script'
                && $i + 2 < $size && $tokens[$i+2] instanceof HTMLPurifier_Token_End) {
                // script special case
                // the contents of the script block must be ONE token
                // for this to work.
                $html .= $this->generateFromToken($tokens[$i++]);
                $html .= $this->generateScriptFromToken($tokens[$i++]);
            }
            $html .= $this->generateFromToken($tokens[$i]);
        }

        // Tidy cleanup
        if (extension_loaded('tidy') && $this->config->get('Output.TidyFormat')) {
            $tidy = new Tidy;
            $tidy->parseString($html, array(
               'indent'=> true,
               'output-xhtml' => $this->_xhtml,
               'show-body-only' => true,
               'indent-spaces' => 2,
               'wrap' => 68,
            ), 'utf8');
            $tidy->cleanRepair();
            $html = (string) $tidy; // explicit cast necessary
        }

        // Normalize newlines to system defined value
        $nl = $this->config->get('Output.Newline');
        if ($nl === null) $nl = PHP_EOL;
        if ($nl !== "\n") $html = str_replace("\n", $nl, $html);
        return $html;
    }

    public function generateFromToken($token) {
        if (!$token instanceof HTMLPurifier_Token) {
            trigger_error('Cannot generate HTML from non-HTMLPurifier_Token object', E_USER_WARNING);
            return '';

        } elseif ($token instanceof HTMLPurifier_Token_Start) {
            $attr = $this->generateAttributes($token->attr, $token->name);
            return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>';

        } elseif ($token instanceof HTMLPurifier_Token_End) {
            return '</' . $token->name . '>';

        } elseif ($token instanceof HTMLPurifier_Token_Empty) {
            $attr = $this->generateAttributes($token->attr, $token->name);
             return '<' . $token->name . ($attr ? ' ' : '') . $attr .
                ( $this->_xhtml ? ' /': '' ) // <br /> v. <br>
                . '>';

        } elseif ($token instanceof HTMLPurifier_Token_Text) {
            return $this->escape($token->data, ENT_NOQUOTES);

        } elseif ($token instanceof HTMLPurifier_Token_Comment) {
            return '<!--' . $token->data . '-->';
        } else {
            return '';

        }
    }

    public function generateScriptFromToken($token) {
        if (!$token instanceof HTMLPurifier_Token_Text) return $this->generateFromToken($token);
        // Thanks <http://lachy.id.au/log/2005/05/script-comments>
        $data = preg_replace('#//\s*$#', '', $token->data);
        return '<!--//--><![CDATA[//><!--' . "\n" . trim($data) . "\n" . '//--><!]]>';
    }

    public function generateAttributes($assoc_array_of_attributes, $element = false) {
        $html = '';
        if ($this->_sortAttr) ksort($assoc_array_of_attributes);
        foreach ($assoc_array_of_attributes as $key => $value) {
            if (!$this->_xhtml) {
                // Remove namespaced attributes
                if (strpos($key, ':') !== false) continue;
                // Check if we should minimize the attribute: val="val" -> val
                if ($element && !empty($this->_def->info[$element]->attr[$key]->minimized)) {
                    $html .= $key . ' ';
                    continue;
                }
            }
            $html .= $key.'="'.$this->escape($value).'" ';
        }
        return rtrim($html);
    }

    public function escape($string, $quote = ENT_COMPAT) {
        return htmlspecialchars($string, $quote, 'UTF-8');
    }

}

// vim: et sw=4 sts=4