<?php

namespace common\helpers;

use common\exts\simplehtmldom\Parser;

define('HDOM_TYPE_ELEMENT', 1);
define('HDOM_TYPE_COMMENT', 2);
define('HDOM_TYPE_TEXT',    3);
define('HDOM_TYPE_ENDTAG',  4);
define('HDOM_TYPE_ROOT',    5);
define('HDOM_TYPE_UNKNOWN', 6);
define('HDOM_QUOTE_DOUBLE', 0);
define('HDOM_QUOTE_SINGLE', 1);
define('HDOM_QUOTE_NO',     3);
define('HDOM_INFO_BEGIN',   0);
define('HDOM_INFO_END',     1);
define('HDOM_INFO_QUOTE',   2);
define('HDOM_INFO_SPACE',   3);
define('HDOM_INFO_TEXT',    4);
define('HDOM_INFO_INNER',   5);
define('HDOM_INFO_OUTER',   6);
define('HDOM_INFO_ENDSPACE',7);
define('DEFAULT_TARGET_CHARSET', 'UTF-8');
define('DEFAULT_BR_TEXT', "\r\n");
define('DEFAULT_SPAN_TEXT', " ");
define('MAX_FILE_SIZE', 600000);

/**
 * Class SimpleHtmlDom
 * @package app\ht\helpers
 */
class SimpleHtmlDom
{
    // get html dom from file
    // $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1.
    public static function fileGetHtml($url, $useIncludePath = false, $context=null, $offset = -1, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $targetCharset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
    {
        // We DO force the tags to be terminated.
        $dom = new Parser(null, $lowercase, $forceTagsClosed, $targetCharset, $stripRN, $defaultBRText, $defaultSpanText);
        // For sourceforge users: uncomment the next line and comment the retreive_url_contents line 2 lines down if it is not already done.
        $contents = file_get_contents($url, $useIncludePath, $context, $offset);
        // Paperg - use our own mechanism for getting the contents as we want to control the timeout.
        //$contents = retrieve_url_contents($url);
        if (empty($contents) || strlen($contents) > MAX_FILE_SIZE)
        {
            return false;
        }
        // The second parameter can force the selectors to all be lowercase.
        $dom->load($contents, $lowercase, $stripRN);
        return $dom;
    }

    // get html dom from string
    public static function strGetHtml($str, $lowercase=true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT)
    {
        $dom = new Parser(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText);
        if (empty($str) || strlen($str) > MAX_FILE_SIZE)
        {
            $dom->clear();
            return false;
        }
        $dom->load($str, $lowercase, $stripRN);
        return $dom;
    }

    // dump html dom tree
    public static function dumpHtmlTree($node, $showAttr=true, $deep=0)
    {
        $node->dump($node);
    }
}