# feedwordpress/2020.0118/feedwordpress_parser.class.php FeedWordPress, version 2020.0118. 530 lines. - Page: https://pluginprobe.com/plugins/feedwordpress/2020.0118/code/feedwordpress_parser.class.php - Raw: https://pluginprobe.com/plugins/feedwordpress/2020.0118/raw/feedwordpress_parser.class.php - Modified: 2020-01-18T23:37:54+00:00 Line numbers below start at 1. Link to a line or a range by appending a fragment to the page URL, for example `https://pluginprobe.com/plugins/feedwordpress/2020.0118/code/feedwordpress_parser.class.php#L10-L20`. ```php namespace = array(''); $this->element = array(''); $this->xml_base = array(''); $this->xml_base_explicit = array(false); $this->xml_lang = array(''); $this->data = array(); $this->datas = array(array()); $this->current_xhtml_construct = -1; $this->xmlns_stack = array(); $this->xmlns_current = array(); // reset libxml parser xml_parser_free($xml); $xml = xml_parser_create_ns($this->encoding, $this->separator); xml_parser_set_option($xml, XML_OPTION_SKIP_WHITE, 1); xml_parser_set_option($xml, XML_OPTION_CASE_FOLDING, 0); xml_set_object($xml, $this); xml_set_character_data_handler($xml, 'cdata'); xml_set_element_handler($xml, 'tag_open', 'tag_close'); xml_set_start_namespace_decl_handler($xml, 'start_xmlns'); } public function parse (&$data, $encoding) { $data = apply_filters('feedwordpress_parser_parse', $data, $encoding, $this); // Use UTF-8 if we get passed US-ASCII, as every US-ASCII character is a UTF-8 character if (strtoupper($encoding) === 'US-ASCII') { $this->encoding = 'UTF-8'; } else { $this->encoding = $encoding; } // Strip BOM: // UTF-32 Big Endian BOM if (substr($data, 0, 4) === "\x00\x00\xFE\xFF") { $data = substr($data, 4); } // UTF-32 Little Endian BOM elseif (substr($data, 0, 4) === "\xFF\xFE\x00\x00") { $data = substr($data, 4); } // UTF-16 Big Endian BOM elseif (substr($data, 0, 2) === "\xFE\xFF") { $data = substr($data, 2); } // UTF-16 Little Endian BOM elseif (substr($data, 0, 2) === "\xFF\xFE") { $data = substr($data, 2); } // UTF-8 BOM elseif (substr($data, 0, 3) === "\xEF\xBB\xBF") { $data = substr($data, 3); } if (substr($data, 0, 5) === '')) !== false) { $declaration = new SimplePie_XML_Declaration_Parser(substr($data, 5, $pos - 5)); if ($declaration->parse()) { $data = substr($data, $pos + 2); $data = 'version . '" encoding="' . $encoding . '" standalone="' . (($declaration->standalone) ? 'yes' : 'no') . '"?>' . $data; } else { $this->error_string = 'SimplePie bug! Please report this!'; return false; } } $return = true; static $xml_is_sane = null; if ($xml_is_sane === null) { $parser_check = xml_parser_create(); xml_parse_into_struct($parser_check, '&', $values); xml_parser_free($parser_check); $xml_is_sane = isset($values[0]['value']); } // Create the parser if ($xml_is_sane) { $xml = xml_parser_create_ns($this->encoding, $this->separator); xml_parser_set_option($xml, XML_OPTION_SKIP_WHITE, 1); xml_parser_set_option($xml, XML_OPTION_CASE_FOLDING, 0); xml_set_object($xml, $this); xml_set_character_data_handler($xml, 'cdata'); xml_set_element_handler($xml, 'tag_open', 'tag_close'); xml_set_start_namespace_decl_handler($xml, 'start_xmlns'); // Parse! $parseResults = xml_parse($xml, $data, true); $endOfJunk = strpos($data, ' 0) : // There is some junk before the feed prolog. Try to get rid of it. $data = substr($data, $endOfJunk); $data = trim($data); $this->reset_parser($xml); $parseResults = xml_parse($xml, $data, true); endif; $badEntity = (xml_get_error_code($xml) == 26); if (!$parseResults and $badEntity) : // There was an entity that libxml couldn't understand. // Chances are, it was a stray HTML entity. So let's try // converting all the named HTML entities to numeric XML // entities and starting over. $data = $this->html_convert_entities($data); $this->reset_parser($xml); $parseResults = xml_parse($xml, $data, true); endif; if (!$parseResults) { $this->error_code = xml_get_error_code($xml); $this->error_string = xml_error_string($this->error_code); $return = false; } $this->current_line = xml_get_current_line_number($xml); $this->current_column = xml_get_current_column_number($xml); $this->current_byte = xml_get_current_byte_index($xml); xml_parser_free($xml); return $return; } else { libxml_clear_errors(); $xml = new XMLReader(); $xml->xml($data); while (@$xml->read()) { switch ($xml->nodeType) { case constant('XMLReader::END_ELEMENT'): if ($xml->namespaceURI !== '') { $tagName = "{$xml->namespaceURI}{$this->separator}{$xml->localName}"; } else { $tagName = $xml->localName; } $this->tag_close(null, $tagName); break; case constant('XMLReader::ELEMENT'): $empty = $xml->isEmptyElement; if ($xml->namespaceURI !== '') { $tagName = "{$xml->namespaceURI}{$this->separator}{$xml->localName}"; } else { $tagName = $xml->localName; } $attributes = array(); while ($xml->moveToNextAttribute()) { if ($xml->namespaceURI !== '') { $attrName = "{$xml->namespaceURI}{$this->separator}{$xml->localName}"; } else { $attrName = $xml->localName; } $attributes[$attrName] = $xml->value; } foreach ($attributes as $attr => $value) : list($ns, $local) = $this->split_ns($attr); if ($ns=='http://www.w3.org/2000/xmlns/') : if ('xmlns' == $local) : $local = false; endif; $this->start_xmlns(null, $local, $value); endif; endforeach; $this->tag_open(null, $tagName, $attributes); if ($empty) { $this->tag_close(null, $tagName); } break; case constant('XMLReader::TEXT'): case constant('XMLReader::CDATA'): $this->cdata(null, $xml->value); break; } } if ($error = libxml_get_last_error()) { $this->error_code = $error->code; $this->error_string = $error->message; $this->current_line = $error->line; $this->current_column = $error->column; return false; } else { return true; } } } /* FeedWordPress_Parser::parse() */ var $xmlns_stack = array(); var $xmlns_current = array(); function tag_open ($parser, $tag, $attributes) { $ret = parent::tag_open($parser, $tag, $attributes); if ($this->current_xhtml_construct < 0) : $this->data['xmlns'] = $this->xmlns_current; $this->xmlns_stack[] = $this->xmlns_current; endif; return $ret; } function tag_close($parser, $tag) { if ($this->current_xhtml_construct < 0) : $this->xmlns_current = array_pop($this->xmlns_stack); endif; $ret = parent::tag_close($parser, $tag); return $ret; } function start_xmlns ($parser, $prefix, $uri) { if (!$prefix) : $prefix = ''; endif; if ($this->current_xhtml_construct < 0) : $this->xmlns_current[$prefix] = $uri; endif; return true; } /* FeedWordPress_Parser::start_xmlns() */ /* html_convert_entities($string) -- convert named HTML entities to * XML-compatible numeric entities. Adapted from code by @inanimatt: * https://gist.github.com/inanimatt/879249 */ public function html_convert_entities($string) { return preg_replace_callback('/&([a-zA-Z][a-zA-Z0-9]+);/S', array($this, 'convert_entity'), $string); } /* Swap HTML named entity with its numeric equivalent. If the entity * isn't in the lookup table, this function returns a blank, which * destroys the character in the output - this is probably the * desired behaviour when producing XML. Adapted from code by @inanimatt: * https://gist.github.com/inanimatt/879249 */ public function convert_entity($matches) { static $table = array( 'quot' => '"', 'amp' => '&', 'lt' => '<', 'gt' => '>', 'OElig' => 'Œ', 'oelig' => 'œ', 'Scaron' => 'Š', 'scaron' => 'š', 'Yuml' => 'Ÿ', 'circ' => 'ˆ', 'tilde' => '˜', 'ensp' => ' ', 'emsp' => ' ', 'thinsp' => ' ', 'zwnj' => '‌', 'zwj' => '‍', 'lrm' => '‎', 'rlm' => '‏', 'ndash' => '–', 'mdash' => '—', 'lsquo' => '‘', 'rsquo' => '’', 'sbquo' => '‚', 'ldquo' => '“', 'rdquo' => '”', 'bdquo' => '„', 'dagger' => '†', 'Dagger' => '‡', 'permil' => '‰', 'lsaquo' => '‹', 'rsaquo' => '›', 'euro' => '€', 'fnof' => 'ƒ', 'Alpha' => 'Α', 'Beta' => 'Β', 'Gamma' => 'Γ', 'Delta' => 'Δ', 'Epsilon' => 'Ε', 'Zeta' => 'Ζ', 'Eta' => 'Η', 'Theta' => 'Θ', 'Iota' => 'Ι', 'Kappa' => 'Κ', 'Lambda' => 'Λ', 'Mu' => 'Μ', 'Nu' => 'Ν', 'Xi' => 'Ξ', 'Omicron' => 'Ο', 'Pi' => 'Π', 'Rho' => 'Ρ', 'Sigma' => 'Σ', 'Tau' => 'Τ', 'Upsilon' => 'Υ', 'Phi' => 'Φ', 'Chi' => 'Χ', 'Psi' => 'Ψ', 'Omega' => 'Ω', 'alpha' => 'α', 'beta' => 'β', 'gamma' => 'γ', 'delta' => 'δ', 'epsilon' => 'ε', 'zeta' => 'ζ', 'eta' => 'η', 'theta' => 'θ', 'iota' => 'ι', 'kappa' => 'κ', 'lambda' => 'λ', 'mu' => 'μ', 'nu' => 'ν', 'xi' => 'ξ', 'omicron' => 'ο', 'pi' => 'π', 'rho' => 'ρ', 'sigmaf' => 'ς', 'sigma' => 'σ', 'tau' => 'τ', 'upsilon' => 'υ', 'phi' => 'φ', 'chi' => 'χ', 'psi' => 'ψ', 'omega' => 'ω', 'thetasym' => 'ϑ', 'upsih' => 'ϒ', 'piv' => 'ϖ', 'bull' => '•', 'hellip' => '…', 'prime' => '′', 'Prime' => '″', 'oline' => '‾', 'frasl' => '⁄', 'weierp' => '℘', 'image' => 'ℑ', 'real' => 'ℜ', 'trade' => '™', 'alefsym' => 'ℵ', 'larr' => '←', 'uarr' => '↑', 'rarr' => '→', 'darr' => '↓', 'harr' => '↔', 'crarr' => '↵', 'lArr' => '⇐', 'uArr' => '⇑', 'rArr' => '⇒', 'dArr' => '⇓', 'hArr' => '⇔', 'forall' => '∀', 'part' => '∂', 'exist' => '∃', 'empty' => '∅', 'nabla' => '∇', 'isin' => '∈', 'notin' => '∉', 'ni' => '∋', 'prod' => '∏', 'sum' => '∑', 'minus' => '−', 'lowast' => '∗', 'radic' => '√', 'prop' => '∝', 'infin' => '∞', 'ang' => '∠', 'and' => '∧', 'or' => '∨', 'cap' => '∩', 'cup' => '∪', 'int' => '∫', 'there4' => '∴', 'sim' => '∼', 'cong' => '≅', 'asymp' => '≈', 'ne' => '≠', 'equiv' => '≡', 'le' => '≤', 'ge' => '≥', 'sub' => '⊂', 'sup' => '⊃', 'nsub' => '⊄', 'sube' => '⊆', 'supe' => '⊇', 'oplus' => '⊕', 'otimes' => '⊗', 'perp' => '⊥', 'sdot' => '⋅', 'lceil' => '⌈', 'rceil' => '⌉', 'lfloor' => '⌊', 'rfloor' => '⌋', 'lang' => '〈', 'rang' => '〉', 'loz' => '◊', 'spades' => '♠', 'clubs' => '♣', 'hearts' => '♥', 'diams' => '♦', 'nbsp' => ' ', 'iexcl' => '¡', 'cent' => '¢', 'pound' => '£', 'curren' => '¤', 'yen' => '¥', 'brvbar' => '¦', 'sect' => '§', 'uml' => '¨', 'copy' => '©', 'ordf' => 'ª', 'laquo' => '«', 'not' => '¬', 'shy' => '­', 'reg' => '®', 'macr' => '¯', 'deg' => '°', 'plusmn' => '±', 'sup2' => '²', 'sup3' => '³', 'acute' => '´', 'micro' => 'µ', 'para' => '¶', 'middot' => '·', 'cedil' => '¸', 'sup1' => '¹', 'ordm' => 'º', 'raquo' => '»', 'frac14' => '¼', 'frac12' => '½', 'frac34' => '¾', 'iquest' => '¿', 'Agrave' => 'À', 'Aacute' => 'Á', 'Acirc' => 'Â', 'Atilde' => 'Ã', 'Auml' => 'Ä', 'Aring' => 'Å', 'AElig' => 'Æ', 'Ccedil' => 'Ç', 'Egrave' => 'È', 'Eacute' => 'É', 'Ecirc' => 'Ê', 'Euml' => 'Ë', 'Igrave' => 'Ì', 'Iacute' => 'Í', 'Icirc' => 'Î', 'Iuml' => 'Ï', 'ETH' => 'Ð', 'Ntilde' => 'Ñ', 'Ograve' => 'Ò', 'Oacute' => 'Ó', 'Ocirc' => 'Ô', 'Otilde' => 'Õ', 'Ouml' => 'Ö', 'times' => '×', 'Oslash' => 'Ø', 'Ugrave' => 'Ù', 'Uacute' => 'Ú', 'Ucirc' => 'Û', 'Uuml' => 'Ü', 'Yacute' => 'Ý', 'THORN' => 'Þ', 'szlig' => 'ß', 'agrave' => 'à', 'aacute' => 'á', 'acirc' => 'â', 'atilde' => 'ã', 'auml' => 'ä', 'aring' => 'å', 'aelig' => 'æ', 'ccedil' => 'ç', 'egrave' => 'è', 'eacute' => 'é', 'ecirc' => 'ê', 'euml' => 'ë', 'igrave' => 'ì', 'iacute' => 'í', 'icirc' => 'î', 'iuml' => 'ï', 'eth' => 'ð', 'ntilde' => 'ñ', 'ograve' => 'ò', 'oacute' => 'ó', 'ocirc' => 'ô', 'otilde' => 'õ', 'ouml' => 'ö', 'divide' => '÷', 'oslash' => 'ø', 'ugrave' => 'ù', 'uacute' => 'ú', 'ucirc' => 'û', 'uuml' => 'ü', 'yacute' => 'ý', 'thorn' => 'þ', 'yuml' => 'ÿ' ); // Entity not found? Destroy it. return isset($table[$matches[1]]) ? $table[$matches[1]] : ''; } /* FeedWordPress_Parser::convert_entity() */ } /* class FeedWordPress_Parser */ ```