home/wwgoat/public_html/blog/wp-includes/SimplePie/src/Parser.php 0000644 00000103543 14720702302 0021111 0 ustar 00 registry = $registry;
}
public function parse(&$data, $encoding, $url = '')
{
if (class_exists('DOMXpath') && function_exists('Mf2\parse')) {
$doc = new \DOMDocument();
@$doc->loadHTML($data);
$xpath = new \DOMXpath($doc);
// Check for both h-feed and h-entry, as both a feed with no entries
// and a list of entries without an h-feed wrapper are both valid.
$query = '//*[contains(concat(" ", @class, " "), " h-feed ") or '.
'contains(concat(" ", @class, " "), " h-entry ")]';
$result = $xpath->query($query);
if ($result->length !== 0) {
return $this->parse_microformats($data, $url);
}
}
// Use UTF-8 if we get passed US-ASCII, as every US-ASCII character is a UTF-8 character
if (strtoupper($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 = $this->registry->create(DeclarationParser::class, [substr($data, 5, $pos - 5)]);
if ($declaration->parse()) {
$data = substr($data, $pos + 2);
$data = 'version . '" encoding="' . $encoding . '" standalone="' . (($declaration->standalone) ? 'yes' : 'no') . '"?>' ."\n". $this->declare_html_entities() . $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($xml, XML_OPTION_CASE_FOLDING, 0);
xml_set_character_data_handler($xml, [$this, 'cdata']);
xml_set_element_handler($xml, [$this, 'tag_open'], [$this, 'tag_close']);
// Parse!
$wrapper = @is_writable(sys_get_temp_dir()) ? 'php://temp' : 'php://memory';
if (($stream = fopen($wrapper, 'r+')) &&
fwrite($stream, $data) &&
rewind($stream)) {
//Parse by chunks not to use too much memory
do {
$stream_data = fread($stream, 1048576);
if (!xml_parse($xml, $stream_data === false ? '' : $stream_data, feof($stream))) {
$this->error_code = xml_get_error_code($xml);
$this->error_string = xml_error_string($this->error_code);
$return = false;
break;
}
} while (!feof($stream));
fclose($stream);
} else {
$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;
}
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;
}
$attributes = [];
while ($xml->moveToNextAttribute()) {
if ($xml->namespaceURI !== '') {
$attrName = $xml->namespaceURI . $this->separator . $xml->localName;
} else {
$attrName = $xml->localName;
}
$attributes[$attrName] = $xml->value;
}
$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;
}
return true;
}
public function get_error_code()
{
return $this->error_code;
}
public function get_error_string()
{
return $this->error_string;
}
public function get_current_line()
{
return $this->current_line;
}
public function get_current_column()
{
return $this->current_column;
}
public function get_current_byte()
{
return $this->current_byte;
}
public function get_data()
{
return $this->data;
}
public function tag_open($parser, $tag, $attributes)
{
[$this->namespace[], $this->element[]] = $this->split_ns($tag);
$attribs = [];
foreach ($attributes as $name => $value) {
[$attrib_namespace, $attribute] = $this->split_ns($name);
$attribs[$attrib_namespace][$attribute] = $value;
}
if (isset($attribs[\SimplePie\SimplePie::NAMESPACE_XML]['base'])) {
$base = $this->registry->call(Misc::class, 'absolutize_url', [$attribs[\SimplePie\SimplePie::NAMESPACE_XML]['base'], end($this->xml_base)]);
if ($base !== false) {
$this->xml_base[] = $base;
$this->xml_base_explicit[] = true;
}
} else {
$this->xml_base[] = end($this->xml_base);
$this->xml_base_explicit[] = end($this->xml_base_explicit);
}
if (isset($attribs[\SimplePie\SimplePie::NAMESPACE_XML]['lang'])) {
$this->xml_lang[] = $attribs[\SimplePie\SimplePie::NAMESPACE_XML]['lang'];
} else {
$this->xml_lang[] = end($this->xml_lang);
}
if ($this->current_xhtml_construct >= 0) {
$this->current_xhtml_construct++;
if (end($this->namespace) === \SimplePie\SimplePie::NAMESPACE_XHTML) {
$this->data['data'] .= '<' . end($this->element);
if (isset($attribs[''])) {
foreach ($attribs[''] as $name => $value) {
$this->data['data'] .= ' ' . $name . '="' . htmlspecialchars($value, ENT_COMPAT, $this->encoding) . '"';
}
}
$this->data['data'] .= '>';
}
} else {
$this->datas[] = &$this->data;
$this->data = &$this->data['child'][end($this->namespace)][end($this->element)][];
$this->data = ['data' => '', 'attribs' => $attribs, 'xml_base' => end($this->xml_base), 'xml_base_explicit' => end($this->xml_base_explicit), 'xml_lang' => end($this->xml_lang)];
if ((end($this->namespace) === \SimplePie\SimplePie::NAMESPACE_ATOM_03 && in_array(end($this->element), ['title', 'tagline', 'copyright', 'info', 'summary', 'content']) && isset($attribs['']['mode']) && $attribs['']['mode'] === 'xml')
|| (end($this->namespace) === \SimplePie\SimplePie::NAMESPACE_ATOM_10 && in_array(end($this->element), ['rights', 'subtitle', 'summary', 'info', 'title', 'content']) && isset($attribs['']['type']) && $attribs['']['type'] === 'xhtml')
|| (end($this->namespace) === \SimplePie\SimplePie::NAMESPACE_RSS_20 && in_array(end($this->element), ['title']))
|| (end($this->namespace) === \SimplePie\SimplePie::NAMESPACE_RSS_090 && in_array(end($this->element), ['title']))
|| (end($this->namespace) === \SimplePie\SimplePie::NAMESPACE_RSS_10 && in_array(end($this->element), ['title']))) {
$this->current_xhtml_construct = 0;
}
}
}
public function cdata($parser, $cdata)
{
if ($this->current_xhtml_construct >= 0) {
$this->data['data'] .= htmlspecialchars($cdata, ENT_QUOTES, $this->encoding);
} else {
$this->data['data'] .= $cdata;
}
}
public function tag_close($parser, $tag)
{
if ($this->current_xhtml_construct >= 0) {
$this->current_xhtml_construct--;
if (end($this->namespace) === \SimplePie\SimplePie::NAMESPACE_XHTML && !in_array(end($this->element), ['area', 'base', 'basefont', 'br', 'col', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param'])) {
$this->data['data'] .= 'element) . '>';
}
}
if ($this->current_xhtml_construct === -1) {
$this->data = &$this->datas[count($this->datas) - 1];
array_pop($this->datas);
}
array_pop($this->element);
array_pop($this->namespace);
array_pop($this->xml_base);
array_pop($this->xml_base_explicit);
array_pop($this->xml_lang);
}
public function split_ns($string)
{
static $cache = [];
if (!isset($cache[$string])) {
if ($pos = strpos($string, $this->separator)) {
static $separator_length;
if (!$separator_length) {
$separator_length = strlen($this->separator);
}
$namespace = substr($string, 0, $pos);
$local_name = substr($string, $pos + $separator_length);
if (strtolower($namespace) === \SimplePie\SimplePie::NAMESPACE_ITUNES) {
$namespace = \SimplePie\SimplePie::NAMESPACE_ITUNES;
}
// Normalize the Media RSS namespaces
if ($namespace === \SimplePie\SimplePie::NAMESPACE_MEDIARSS_WRONG ||
$namespace === \SimplePie\SimplePie::NAMESPACE_MEDIARSS_WRONG2 ||
$namespace === \SimplePie\SimplePie::NAMESPACE_MEDIARSS_WRONG3 ||
$namespace === \SimplePie\SimplePie::NAMESPACE_MEDIARSS_WRONG4 ||
$namespace === \SimplePie\SimplePie::NAMESPACE_MEDIARSS_WRONG5) {
$namespace = \SimplePie\SimplePie::NAMESPACE_MEDIARSS;
}
$cache[$string] = [$namespace, $local_name];
} else {
$cache[$string] = ['', $string];
}
}
return $cache[$string];
}
private function parse_hcard($data, $category = false)
{
$name = '';
$link = '';
// Check if h-card is set and pass that information on in the link.
if (isset($data['type']) && in_array('h-card', $data['type'])) {
if (isset($data['properties']['name'][0])) {
$name = $data['properties']['name'][0];
}
if (isset($data['properties']['url'][0])) {
$link = $data['properties']['url'][0];
if ($name === '') {
$name = $link;
} else {
// can't have commas in categories.
$name = str_replace(',', '', $name);
}
$person_tag = $category ? '' : '';
return ''.$person_tag.$name.'';
}
}
return $data['value'] ?? '';
}
private function parse_microformats(&$data, $url)
{
$feed_title = '';
$feed_author = null;
$author_cache = [];
$items = [];
$entries = [];
$mf = \Mf2\parse($data, $url);
// First look for an h-feed.
$h_feed = [];
foreach ($mf['items'] as $mf_item) {
if (in_array('h-feed', $mf_item['type'])) {
$h_feed = $mf_item;
break;
}
// Also look for h-feed or h-entry in the children of each top level item.
if (!isset($mf_item['children'][0]['type'])) {
continue;
}
if (in_array('h-feed', $mf_item['children'][0]['type'])) {
$h_feed = $mf_item['children'][0];
// In this case the parent of the h-feed may be an h-card, so use it as
// the feed_author.
if (in_array('h-card', $mf_item['type'])) {
$feed_author = $mf_item;
}
break;
} elseif (in_array('h-entry', $mf_item['children'][0]['type'])) {
$entries = $mf_item['children'];
// In this case the parent of the h-entry list may be an h-card, so use
// it as the feed_author.
if (in_array('h-card', $mf_item['type'])) {
$feed_author = $mf_item;
}
break;
}
}
if (isset($h_feed['children'])) {
$entries = $h_feed['children'];
// Also set the feed title and store author from the h-feed if available.
if (isset($mf['items'][0]['properties']['name'][0])) {
$feed_title = $mf['items'][0]['properties']['name'][0];
}
if (isset($mf['items'][0]['properties']['author'][0])) {
$feed_author = $mf['items'][0]['properties']['author'][0];
}
} elseif (count($entries) === 0) {
$entries = $mf['items'];
}
for ($i = 0; $i < count($entries); $i++) {
$entry = $entries[$i];
if (in_array('h-entry', $entry['type'])) {
$item = [];
$title = '';
$description = '';
if (isset($entry['properties']['url'][0])) {
$link = $entry['properties']['url'][0];
if (isset($link['value'])) {
$link = $link['value'];
}
$item['link'] = [['data' => $link]];
}
if (isset($entry['properties']['uid'][0])) {
$guid = $entry['properties']['uid'][0];
if (isset($guid['value'])) {
$guid = $guid['value'];
}
$item['guid'] = [['data' => $guid]];
}
if (isset($entry['properties']['name'][0])) {
$title = $entry['properties']['name'][0];
if (isset($title['value'])) {
$title = $title['value'];
}
$item['title'] = [['data' => $title]];
}
if (isset($entry['properties']['author'][0]) || isset($feed_author)) {
// author is a special case, it can be plain text or an h-card array.
// If it's plain text it can also be a url that should be followed to
// get the actual h-card.
$author = $entry['properties']['author'][0] ?? $feed_author;
if (!is_string($author)) {
$author = $this->parse_hcard($author);
} elseif (strpos($author, 'http') === 0) {
if (isset($author_cache[$author])) {
$author = $author_cache[$author];
} else {
$mf = \Mf2\fetch($author);
foreach ($mf['items'] as $hcard) {
// Only interested in an h-card by itself in this case.
if (!in_array('h-card', $hcard['type'])) {
continue;
}
// It must have a url property matching what we fetched.
if (!isset($hcard['properties']['url']) ||
!(in_array($author, $hcard['properties']['url']))) {
continue;
}
// Save parse_hcard the trouble of finding the correct url.
$hcard['properties']['url'][0] = $author;
// Cache this h-card for the next h-entry to check.
$author_cache[$author] = $this->parse_hcard($hcard);
$author = $author_cache[$author];
break;
}
}
}
$item['author'] = [['data' => $author]];
}
if (isset($entry['properties']['photo'][0])) {
// If a photo is also in content, don't need to add it again here.
$content = '';
if (isset($entry['properties']['content'][0]['html'])) {
$content = $entry['properties']['content'][0]['html'];
}
$photo_list = [];
for ($j = 0; $j < count($entry['properties']['photo']); $j++) {
$photo = $entry['properties']['photo'][$j];
if (!empty($photo) && strpos($content, $photo) === false) {
$photo_list[] = $photo;
}
}
// When there's more than one photo show the first and use a lightbox.
// Need a permanent, unique name for the image set, but don't have
// anything unique except for the content itself, so use that.
$count = count($photo_list);
if ($count > 1) {
$image_set_id = preg_replace('/[[:^alnum:]]/', '', $photo_list[0]);
$description = '';
for ($j = 0; $j < $count; $j++) {
$hidden = $j === 0 ? '' : 'class="hidden" ';
$description .= ''.
'
';
}
$description .= '
'.$count.' photos
';
} elseif ($count == 1) {
$description = '
';
}
}
if (isset($entry['properties']['content'][0]['html'])) {
// e-content['value'] is the same as p-name when they are on the same
// element. Use this to replace title with a strip_tags version so
// that alt text from images is not included in the title.
if ($entry['properties']['content'][0]['value'] === $title) {
$title = strip_tags($entry['properties']['content'][0]['html']);
$item['title'] = [['data' => $title]];
}
$description .= $entry['properties']['content'][0]['html'];
if (isset($entry['properties']['in-reply-to'][0])) {
$in_reply_to = '';
if (is_string($entry['properties']['in-reply-to'][0])) {
$in_reply_to = $entry['properties']['in-reply-to'][0];
} elseif (isset($entry['properties']['in-reply-to'][0]['value'])) {
$in_reply_to = $entry['properties']['in-reply-to'][0]['value'];
}
if ($in_reply_to !== '') {
$description .= ' '.
''.$in_reply_to.'
';
}
}
$item['description'] = [['data' => $description]];
}
if (isset($entry['properties']['category'])) {
$category_csv = '';
// Categories can also contain h-cards.
foreach ($entry['properties']['category'] as $category) {
if ($category_csv !== '') {
$category_csv .= ', ';
}
if (is_string($category)) {
// Can't have commas in categories.
$category_csv .= str_replace(',', '', $category);
} else {
$category_csv .= $this->parse_hcard($category, true);
}
}
$item['category'] = [['data' => $category_csv]];
}
if (isset($entry['properties']['published'][0])) {
$timestamp = strtotime($entry['properties']['published'][0]);
$pub_date = date('F j Y g:ia', $timestamp).' GMT';
$item['pubDate'] = [['data' => $pub_date]];
}
// The title and description are set to the empty string to represent
// a deleted item (which also makes it an invalid rss item).
if (isset($entry['properties']['deleted'][0])) {
$item['title'] = [['data' => '']];
$item['description'] = [['data' => '']];
}
$items[] = ['child' => ['' => $item]];
}
}
// Mimic RSS data format when storing microformats.
$link = [['data' => $url]];
$image = '';
if (!is_string($feed_author) &&
isset($feed_author['properties']['photo'][0])) {
$image = [['child' => ['' => ['url' =>
[['data' => $feed_author['properties']['photo'][0]]]]]]];
}
// Use the name given for the h-feed, or get the title from the html.
if ($feed_title !== '') {
$feed_title = [['data' => htmlspecialchars($feed_title)]];
} elseif ($position = strpos($data, '
')) {
$start = $position < 200 ? 0 : $position - 200;
$check = substr($data, $start, 400);
$matches = [];
if (preg_match('/<title>(.+)<\/title>/', $check, $matches)) {
$feed_title = [['data' => htmlspecialchars($matches[1])]];
}
}
$channel = ['channel' => [['child' => ['' =>
['link' => $link, 'image' => $image, 'title' => $feed_title,
'item' => $items]]]]];
$rss = [['attribs' => ['' => ['version' => '2.0']],
'child' => ['' => $channel]]];
$this->data = ['child' => ['' => ['rss' => $rss]]];
return true;
}
private function declare_html_entities()
{
// This is required because the RSS specification says that entity-encoded
// html is allowed, but the xml specification says they must be declared.
return '<!DOCTYPE html [ <!ENTITY nbsp " "> <!ENTITY iexcl "¡"> <!ENTITY cent "¢"> <!ENTITY pound "£"> <!ENTITY curren "¤"> <!ENTITY yen "¥"> <!ENTITY brvbar "¦"> <!ENTITY sect "§"> <!ENTITY uml "¨"> <!ENTITY copy "©"> <!ENTITY ordf "ª"> <!ENTITY laquo "«"> <!ENTITY not "¬"> <!ENTITY shy ""> <!ENTITY reg "®"> <!ENTITY macr "¯"> <!ENTITY deg "°"> <!ENTITY plusmn "±"> <!ENTITY sup2 "²"> <!ENTITY sup3 "³"> <!ENTITY acute "´"> <!ENTITY micro "µ"> <!ENTITY para "¶"> <!ENTITY middot "·"> <!ENTITY cedil "¸"> <!ENTITY sup1 "¹"> <!ENTITY ordm "º"> <!ENTITY raquo "»"> <!ENTITY frac14 "¼"> <!ENTITY frac12 "½"> <!ENTITY frac34 "¾"> <!ENTITY iquest "¿"> <!ENTITY Agrave "À"> <!ENTITY Aacute "Á"> <!ENTITY Acirc "Â"> <!ENTITY Atilde "Ã"> <!ENTITY Auml "Ä"> <!ENTITY Aring "Å"> <!ENTITY AElig "Æ"> <!ENTITY Ccedil "Ç"> <!ENTITY Egrave "È"> <!ENTITY Eacute "É"> <!ENTITY Ecirc "Ê"> <!ENTITY Euml "Ë"> <!ENTITY Igrave "Ì"> <!ENTITY Iacute "Í"> <!ENTITY Icirc "Î"> <!ENTITY Iuml "Ï"> <!ENTITY ETH "Ð"> <!ENTITY Ntilde "Ñ"> <!ENTITY Ograve "Ò"> <!ENTITY Oacute "Ó"> <!ENTITY Ocirc "Ô"> <!ENTITY Otilde "Õ"> <!ENTITY Ouml "Ö"> <!ENTITY times "×"> <!ENTITY Oslash "Ø"> <!ENTITY Ugrave "Ù"> <!ENTITY Uacute "Ú"> <!ENTITY Ucirc "Û"> <!ENTITY Uuml "Ü"> <!ENTITY Yacute "Ý"> <!ENTITY THORN "Þ"> <!ENTITY szlig "ß"> <!ENTITY agrave "à"> <!ENTITY aacute "á"> <!ENTITY acirc "â"> <!ENTITY atilde "ã"> <!ENTITY auml "ä"> <!ENTITY aring "å"> <!ENTITY aelig "æ"> <!ENTITY ccedil "ç"> <!ENTITY egrave "è"> <!ENTITY eacute "é"> <!ENTITY ecirc "ê"> <!ENTITY euml "ë"> <!ENTITY igrave "ì"> <!ENTITY iacute "í"> <!ENTITY icirc "î"> <!ENTITY iuml "ï"> <!ENTITY eth "ð"> <!ENTITY ntilde "ñ"> <!ENTITY ograve "ò"> <!ENTITY oacute "ó"> <!ENTITY ocirc "ô"> <!ENTITY otilde "õ"> <!ENTITY ouml "ö"> <!ENTITY divide "÷"> <!ENTITY oslash "ø"> <!ENTITY ugrave "ù"> <!ENTITY uacute "ú"> <!ENTITY ucirc "û"> <!ENTITY uuml "ü"> <!ENTITY yacute "ý"> <!ENTITY thorn "þ"> <!ENTITY yuml "ÿ"> <!ENTITY OElig "Œ"> <!ENTITY oelig "œ"> <!ENTITY Scaron "Š"> <!ENTITY scaron "š"> <!ENTITY Yuml "Ÿ"> <!ENTITY fnof "ƒ"> <!ENTITY circ "ˆ"> <!ENTITY tilde "˜"> <!ENTITY Alpha "Α"> <!ENTITY Beta "Β"> <!ENTITY Gamma "Γ"> <!ENTITY Epsilon "Ε"> <!ENTITY Zeta "Ζ"> <!ENTITY Eta "Η"> <!ENTITY Theta "Θ"> <!ENTITY Iota "Ι"> <!ENTITY Kappa "Κ"> <!ENTITY Lambda "Λ"> <!ENTITY Mu "Μ"> <!ENTITY Nu "Ν"> <!ENTITY Xi "Ξ"> <!ENTITY Omicron "Ο"> <!ENTITY Pi "Π"> <!ENTITY Rho "Ρ"> <!ENTITY Sigma "Σ"> <!ENTITY Tau "Τ"> <!ENTITY Upsilon "Υ"> <!ENTITY Phi "Φ"> <!ENTITY Chi "Χ"> <!ENTITY Psi "Ψ"> <!ENTITY Omega "Ω"> <!ENTITY alpha "α"> <!ENTITY beta "β"> <!ENTITY gamma "γ"> <!ENTITY delta "δ"> <!ENTITY epsilon "ε"> <!ENTITY zeta "ζ"> <!ENTITY eta "η"> <!ENTITY theta "θ"> <!ENTITY iota "ι"> <!ENTITY kappa "κ"> <!ENTITY lambda "λ"> <!ENTITY mu "μ"> <!ENTITY nu "ν"> <!ENTITY xi "ξ"> <!ENTITY omicron "ο"> <!ENTITY pi "π"> <!ENTITY rho "ρ"> <!ENTITY sigmaf "ς"> <!ENTITY sigma "σ"> <!ENTITY tau "τ"> <!ENTITY upsilon "υ"> <!ENTITY phi "φ"> <!ENTITY chi "χ"> <!ENTITY psi "ψ"> <!ENTITY omega "ω"> <!ENTITY thetasym "ϑ"> <!ENTITY upsih "ϒ"> <!ENTITY piv "ϖ"> <!ENTITY ensp " "> <!ENTITY emsp " "> <!ENTITY thinsp " "> <!ENTITY zwnj ""> <!ENTITY zwj ""> <!ENTITY lrm ""> <!ENTITY rlm ""> <!ENTITY ndash "–"> <!ENTITY mdash "—"> <!ENTITY lsquo "‘"> <!ENTITY rsquo "’"> <!ENTITY sbquo "‚"> <!ENTITY ldquo "“"> <!ENTITY rdquo "”"> <!ENTITY bdquo "„"> <!ENTITY dagger "†"> <!ENTITY Dagger "‡"> <!ENTITY bull "•"> <!ENTITY hellip "…"> <!ENTITY permil "‰"> <!ENTITY prime "′"> <!ENTITY Prime "″"> <!ENTITY lsaquo "‹"> <!ENTITY rsaquo "›"> <!ENTITY oline "‾"> <!ENTITY frasl "⁄"> <!ENTITY euro "€"> <!ENTITY image "ℑ"> <!ENTITY weierp "℘"> <!ENTITY real "ℜ"> <!ENTITY trade "™"> <!ENTITY alefsym "ℵ"> <!ENTITY larr "←"> <!ENTITY uarr "↑"> <!ENTITY rarr "→"> <!ENTITY darr "↓"> <!ENTITY harr "↔"> <!ENTITY crarr "↵"> <!ENTITY lArr "⇐"> <!ENTITY uArr "⇑"> <!ENTITY rArr "⇒"> <!ENTITY dArr "⇓"> <!ENTITY hArr "⇔"> <!ENTITY forall "∀"> <!ENTITY part "∂"> <!ENTITY exist "∃"> <!ENTITY empty "∅"> <!ENTITY nabla "∇"> <!ENTITY isin "∈"> <!ENTITY notin "∉"> <!ENTITY ni "∋"> <!ENTITY prod "∏"> <!ENTITY sum "∑"> <!ENTITY minus "−"> <!ENTITY lowast "∗"> <!ENTITY radic "√"> <!ENTITY prop "∝"> <!ENTITY infin "∞"> <!ENTITY ang "∠"> <!ENTITY and "∧"> <!ENTITY or "∨"> <!ENTITY cap "∩"> <!ENTITY cup "∪"> <!ENTITY int "∫"> <!ENTITY there4 "∴"> <!ENTITY sim "∼"> <!ENTITY cong "≅"> <!ENTITY asymp "≈"> <!ENTITY ne "≠"> <!ENTITY equiv "≡"> <!ENTITY le "≤"> <!ENTITY ge "≥"> <!ENTITY sub "⊂"> <!ENTITY sup "⊃"> <!ENTITY nsub "⊄"> <!ENTITY sube "⊆"> <!ENTITY supe "⊇"> <!ENTITY oplus "⊕"> <!ENTITY otimes "⊗"> <!ENTITY perp "⊥"> <!ENTITY sdot "⋅"> <!ENTITY lceil "⌈"> <!ENTITY rceil "⌉"> <!ENTITY lfloor "⌊"> <!ENTITY rfloor "⌋"> <!ENTITY lang "〈"> <!ENTITY rang "〉"> <!ENTITY loz "◊"> <!ENTITY spades "♠"> <!ENTITY clubs "♣"> <!ENTITY hearts "♥"> <!ENTITY diams "♦"> ]>';
}
}
class_alias('SimplePie\Parser', 'SimplePie_Parser');
home/wwgoat/public_html/blog/wp-includes/SimplePie/src/HTTP/Parser.php 0000644 00000035073 14720716043 0021701 0 ustar 00 <?php
/**
* SimplePie
*
* A PHP-Based RSS and Atom Feed Framework.
* Takes the hard work out of managing a complete RSS/Atom solution.
*
* Copyright (c) 2004-2022, Ryan Parman, Sam Sneddon, Ryan McCue, and contributors
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without modification, are
* permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice, this list of
* conditions and the following disclaimer.
*
* * Redistributions in binary form must reproduce the above copyright notice, this list
* of conditions and the following disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* * Neither the name of the SimplePie Team nor the names of its contributors may be used
* to endorse or promote products derived from this software without specific prior
* written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS
* OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
* AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS
* AND CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
* OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*
* @package SimplePie
* @copyright 2004-2016 Ryan Parman, Sam Sneddon, Ryan McCue
* @author Ryan Parman
* @author Sam Sneddon
* @author Ryan McCue
* @link http://simplepie.org/ SimplePie
* @license http://www.opensource.org/licenses/bsd-license.php BSD License
*/
namespace SimplePie\HTTP;
/**
* HTTP Response Parser
*
* @package SimplePie
* @subpackage HTTP
*/
class Parser
{
/**
* HTTP Version
*
* @var float
*/
public $http_version = 0.0;
/**
* Status code
*
* @var int
*/
public $status_code = 0;
/**
* Reason phrase
*
* @var string
*/
public $reason = '';
/**
* Key/value pairs of the headers
*
* @var array
*/
public $headers = [];
/**
* Body of the response
*
* @var string
*/
public $body = '';
private const STATE_HTTP_VERSION = 'http_version';
private const STATE_STATUS = 'status';
private const STATE_REASON = 'reason';
private const STATE_NEW_LINE = 'new_line';
private const STATE_BODY = 'body';
private const STATE_NAME = 'name';
private const STATE_VALUE = 'value';
private const STATE_VALUE_CHAR = 'value_char';
private const STATE_QUOTE = 'quote';
private const STATE_QUOTE_ESCAPED = 'quote_escaped';
private const STATE_QUOTE_CHAR = 'quote_char';
private const STATE_CHUNKED = 'chunked';
private const STATE_EMIT = 'emit';
private const STATE_ERROR = false;
/**
* Current state of the state machine
*
* @var self::STATE_*
*/
protected $state = self::STATE_HTTP_VERSION;
/**
* Input data
*
* @var string
*/
protected $data = '';
/**
* Input data length (to avoid calling strlen() everytime this is needed)
*
* @var int
*/
protected $data_length = 0;
/**
* Current position of the pointer
*
* @var int
*/
protected $position = 0;
/**
* Name of the hedaer currently being parsed
*
* @var string
*/
protected $name = '';
/**
* Value of the hedaer currently being parsed
*
* @var string
*/
protected $value = '';
/**
* Create an instance of the class with the input data
*
* @param string $data Input data
*/
public function __construct($data)
{
$this->data = $data;
$this->data_length = strlen($this->data);
}
/**
* Parse the input data
*
* @return bool true on success, false on failure
*/
public function parse()
{
while ($this->state && $this->state !== self::STATE_EMIT && $this->has_data()) {
$state = $this->state;
$this->$state();
}
$this->data = '';
if ($this->state === self::STATE_EMIT || $this->state === self::STATE_BODY) {
return true;
}
$this->http_version = '';
$this->status_code = 0;
$this->reason = '';
$this->headers = [];
$this->body = '';
return false;
}
/**
* Check whether there is data beyond the pointer
*
* @return bool true if there is further data, false if not
*/
protected function has_data()
{
return (bool) ($this->position < $this->data_length);
}
/**
* See if the next character is LWS
*
* @return bool true if the next character is LWS, false if not
*/
protected function is_linear_whitespace()
{
return (bool) ($this->data[$this->position] === "\x09"
|| $this->data[$this->position] === "\x20"
|| ($this->data[$this->position] === "\x0A"
&& isset($this->data[$this->position + 1])
&& ($this->data[$this->position + 1] === "\x09" || $this->data[$this->position + 1] === "\x20")));
}
/**
* Parse the HTTP version
*/
protected function http_version()
{
if (strpos($this->data, "\x0A") !== false && strtoupper(substr($this->data, 0, 5)) === 'HTTP/') {
$len = strspn($this->data, '0123456789.', 5);
$this->http_version = substr($this->data, 5, $len);
$this->position += 5 + $len;
if (substr_count($this->http_version, '.') <= 1) {
$this->http_version = (float) $this->http_version;
$this->position += strspn($this->data, "\x09\x20", $this->position);
$this->state = self::STATE_STATUS;
} else {
$this->state = self::STATE_ERROR;
}
} else {
$this->state = self::STATE_ERROR;
}
}
/**
* Parse the status code
*/
protected function status()
{
if ($len = strspn($this->data, '0123456789', $this->position)) {
$this->status_code = (int) substr($this->data, $this->position, $len);
$this->position += $len;
$this->state = self::STATE_REASON;
} else {
$this->state = self::STATE_ERROR;
}
}
/**
* Parse the reason phrase
*/
protected function reason()
{
$len = strcspn($this->data, "\x0A", $this->position);
$this->reason = trim(substr($this->data, $this->position, $len), "\x09\x0D\x20");
$this->position += $len + 1;
$this->state = self::STATE_NEW_LINE;
}
/**
* Deal with a new line, shifting data around as needed
*/
protected function new_line()
{
$this->value = trim($this->value, "\x0D\x20");
if ($this->name !== '' && $this->value !== '') {
$this->name = strtolower($this->name);
// We should only use the last Content-Type header. c.f. issue #1
if (isset($this->headers[$this->name]) && $this->name !== 'content-type') {
$this->headers[$this->name] .= ', ' . $this->value;
} else {
$this->headers[$this->name] = $this->value;
}
}
$this->name = '';
$this->value = '';
if (substr($this->data[$this->position], 0, 2) === "\x0D\x0A") {
$this->position += 2;
$this->state = self::STATE_BODY;
} elseif ($this->data[$this->position] === "\x0A") {
$this->position++;
$this->state = self::STATE_BODY;
} else {
$this->state = self::STATE_NAME;
}
}
/**
* Parse a header name
*/
protected function name()
{
$len = strcspn($this->data, "\x0A:", $this->position);
if (isset($this->data[$this->position + $len])) {
if ($this->data[$this->position + $len] === "\x0A") {
$this->position += $len;
$this->state = self::STATE_NEW_LINE;
} else {
$this->name = substr($this->data, $this->position, $len);
$this->position += $len + 1;
$this->state = self::STATE_VALUE;
}
} else {
$this->state = self::STATE_ERROR;
}
}
/**
* Parse LWS, replacing consecutive LWS characters with a single space
*/
protected function linear_whitespace()
{
do {
if (substr($this->data, $this->position, 2) === "\x0D\x0A") {
$this->position += 2;
} elseif ($this->data[$this->position] === "\x0A") {
$this->position++;
}
$this->position += strspn($this->data, "\x09\x20", $this->position);
} while ($this->has_data() && $this->is_linear_whitespace());
$this->value .= "\x20";
}
/**
* See what state to move to while within non-quoted header values
*/
protected function value()
{
if ($this->is_linear_whitespace()) {
$this->linear_whitespace();
} else {
switch ($this->data[$this->position]) {
case '"':
// Workaround for ETags: we have to include the quotes as
// part of the tag.
if (strtolower($this->name) === 'etag') {
$this->value .= '"';
$this->position++;
$this->state = self::STATE_VALUE_CHAR;
break;
}
$this->position++;
$this->state = self::STATE_QUOTE;
break;
case "\x0A":
$this->position++;
$this->state = self::STATE_NEW_LINE;
break;
default:
$this->state = self::STATE_VALUE_CHAR;
break;
}
}
}
/**
* Parse a header value while outside quotes
*/
protected function value_char()
{
$len = strcspn($this->data, "\x09\x20\x0A\"", $this->position);
$this->value .= substr($this->data, $this->position, $len);
$this->position += $len;
$this->state = self::STATE_VALUE;
}
/**
* See what state to move to while within quoted header values
*/
protected function quote()
{
if ($this->is_linear_whitespace()) {
$this->linear_whitespace();
} else {
switch ($this->data[$this->position]) {
case '"':
$this->position++;
$this->state = self::STATE_VALUE;
break;
case "\x0A":
$this->position++;
$this->state = self::STATE_NEW_LINE;
break;
case '\\':
$this->position++;
$this->state = self::STATE_QUOTE_ESCAPED;
break;
default:
$this->state = self::STATE_QUOTE_CHAR;
break;
}
}
}
/**
* Parse a header value while within quotes
*/
protected function quote_char()
{
$len = strcspn($this->data, "\x09\x20\x0A\"\\", $this->position);
$this->value .= substr($this->data, $this->position, $len);
$this->position += $len;
$this->state = self::STATE_VALUE;
}
/**
* Parse an escaped character within quotes
*/
protected function quote_escaped()
{
$this->value .= $this->data[$this->position];
$this->position++;
$this->state = self::STATE_QUOTE;
}
/**
* Parse the body
*/
protected function body()
{
$this->body = substr($this->data, $this->position);
if (!empty($this->headers['transfer-encoding'])) {
unset($this->headers['transfer-encoding']);
$this->state = self::STATE_CHUNKED;
} else {
$this->state = self::STATE_EMIT;
}
}
/**
* Parsed a "Transfer-Encoding: chunked" body
*/
protected function chunked()
{
if (!preg_match('/^([0-9a-f]+)[^\r\n]*\r\n/i', trim($this->body))) {
$this->state = self::STATE_EMIT;
return;
}
$decoded = '';
$encoded = $this->body;
while (true) {
$is_chunked = (bool) preg_match('/^([0-9a-f]+)[^\r\n]*\r\n/i', $encoded, $matches);
if (!$is_chunked) {
// Looks like it's not chunked after all
$this->state = self::STATE_EMIT;
return;
}
$length = hexdec(trim($matches[1]));
if ($length === 0) {
// Ignore trailer headers
$this->state = self::STATE_EMIT;
$this->body = $decoded;
return;
}
$chunk_length = strlen($matches[0]);
$decoded .= substr($encoded, $chunk_length, $length);
$encoded = substr($encoded, $chunk_length + $length + 2);
// BC for PHP < 8.0: substr() can return bool instead of string
$encoded = ($encoded === false) ? '' : $encoded;
if (trim($encoded) === '0' || empty($encoded)) {
$this->state = self::STATE_EMIT;
$this->body = $decoded;
return;
}
}
}
/**
* Prepare headers (take care of proxies headers)
*
* @param string $headers Raw headers
* @param integer $count Redirection count. Default to 1.
*
* @return string
*/
public static function prepareHeaders($headers, $count = 1)
{
$data = explode("\r\n\r\n", $headers, $count);
$data = array_pop($data);
if (false !== stripos($data, "HTTP/1.0 200 Connection established\r\n")) {
$exploded = explode("\r\n\r\n", $data, 2);
$data = end($exploded);
}
if (false !== stripos($data, "HTTP/1.1 200 Connection established\r\n")) {
$exploded = explode("\r\n\r\n", $data, 2);
$data = end($exploded);
}
return $data;
}
}
class_alias('SimplePie\HTTP\Parser', 'SimplePie_HTTP_Parser');