ParseHTML.php

Go to the documentation of this file.

<?php

class Auth_Yadis_ParseHTML {

    var $_re_flags = "si";

    var $_removed_re =
           "<!--.*?-->|<!\[CDATA\[.*?\]\]>|<script\b(?!:)[^>]*>.*?<\/script>";

    var $_tag_expr = "<%s%s(?:\s.*?)?%s>";

    var $_attr_find = '\b([-\w]+)=(".*?"|\'.*?\'|.+?)[\/\s>]';

    function Auth_Yadis_ParseHTML()
    {
        $this->_attr_find = sprintf("/%s/%s",
                                    $this->_attr_find,
                                    $this->_re_flags);

        $this->_removed_re = sprintf("/%s/%s",
                                     $this->_removed_re,
                                     $this->_re_flags);

        $this->_entity_replacements = array(
                                            'amp' => '&',
                                            'lt' => '<',
                                            'gt' => '>',
                                            'quot' => '"'
                                            );

        $this->_ent_replace =
            sprintf("&(%s);", implode("|",
                                      $this->_entity_replacements));
    }

    function replaceEntities($str)
    {
        foreach ($this->_entity_replacements as $old => $new) {
            $str = preg_replace(sprintf("/&%s;/", $old), $new, $str);
        }

        // Replace numeric entities because html_entity_decode doesn't
        // do it for us.
        $str = preg_replace_callback(
            '~&#x([0-9a-f]+);~i',
            function($hit) {
                return chr(hexdec($hit[1]));
            },
            $str
        );
        $str = preg_replace_callback(
            '~&#([0-9]+);~',
            function($hit) {
                return chr($hit[1]);
            },
            $str
        );

        return $str;
    }

    function removeQuotes($str)
    {
        $matches = array();
        $double = '/^"(.*)"$/';
        $single = "/^\'(.*)\'$/";

        if (preg_match($double, $str, $matches)) {
            return $matches[1];
        } else if (preg_match($single, $str, $matches)) {
            return $matches[1];
        } else {
            return $str;
        }
    }

    function tagPattern($tag_names, $close, $self_close)
    {
        if (is_array($tag_names)) {
            $tag_names = '(?:'.implode('|',$tag_names).')';
        }
        if ($close) {
            $close = '\/' . (($close == 1)? '' : '?');
        } else {
            $close = '';
        }
        if ($self_close) {
            $self_close = '(?:\/\s*)' . (($self_close == 1)? '' : '?');
        } else {
            $self_close = '';
        }
        $expr = sprintf($this->_tag_expr, $close, $tag_names, $self_close);

        return sprintf("/%s/%s", $expr, $this->_re_flags);
    }

    function getMetaTags($html_string)
    {
        $html_string = preg_replace($this->_removed_re,
                                    "",
                                    $html_string);

        $key_tags = array($this->tagPattern('html', false, false),
                          $this->tagPattern('head', false, false),
                          $this->tagPattern('head', true, false),
                          $this->tagPattern('html', true, false),
                          $this->tagPattern(array(
                          'body', 'frameset', 'frame', 'p', 'div',
                          'table','span','a'), 'maybe', 'maybe'));
        $key_tags_pos = array();
        foreach ($key_tags as $pat) {
            $matches = array();
            preg_match($pat, $html_string, $matches, PREG_OFFSET_CAPTURE);
            if($matches) {
                $key_tags_pos[] = $matches[0][1];
            } else {
                $key_tags_pos[] = null;
            }
        }
        // no opening head tag
        if (is_null($key_tags_pos[1])) {
            return array();
        }
        // the effective </head> is the min of the following
        if (is_null($key_tags_pos[2])) {
            $key_tags_pos[2] = strlen($html_string);
        }
        foreach (array($key_tags_pos[3], $key_tags_pos[4]) as $pos) {
            if (!is_null($pos) && $pos < $key_tags_pos[2]) {
                $key_tags_pos[2] = $pos;
            }
        }
        // closing head tag comes before opening head tag
        if ($key_tags_pos[1] > $key_tags_pos[2]) {
            return array();
        }
        // if there is an opening html tag, make sure the opening head tag
        // comes after it
        if (!is_null($key_tags_pos[0]) && $key_tags_pos[1] < $key_tags_pos[0]) {
            return array();
        }
        $html_string = substr($html_string, $key_tags_pos[1],
                              ($key_tags_pos[2]-$key_tags_pos[1]));

        $link_data = array();
        $link_matches = array();
        
        if (!preg_match_all($this->tagPattern('meta', false, 'maybe'),
                            $html_string, $link_matches)) {
            return array();
        }

        foreach ($link_matches[0] as $link) {
            $attr_matches = array();
            preg_match_all($this->_attr_find, $link, $attr_matches);
            $link_attrs = array();
            foreach ($attr_matches[0] as $index => $full_match) {
                $name = $attr_matches[1][$index];
                $value = $this->replaceEntities(
                              $this->removeQuotes($attr_matches[2][$index]));

                $link_attrs[strtolower($name)] = $value;
            }
            $link_data[] = $link_attrs;
        }

        return $link_data;
    }

    function getHTTPEquiv($html_string)
    {
        $meta_tags = $this->getMetaTags($html_string);

        if ($meta_tags) {
            foreach ($meta_tags as $tag) {
                if (array_key_exists('http-equiv', $tag) &&
                    (in_array(strtolower($tag['http-equiv']),
                              array('x-xrds-location', 'x-yadis-location'))) &&
                    array_key_exists('content', $tag)) {
                    return $tag['content'];
                }
            }
        }

        return null;
    }
}