/**
* Convert wikitext to HTML
* Do not call this function recursively.
*
* @param string $text Text we want to parse
* @param Title $title
* @param ParserOptions $options
* @param bool $linestart
* @param bool $clearState
* @param int $revid Number to pass in {{REVISIONID}}
* @return ParserOutput A ParserOutput
*/
public function parse($text, Title $title, ParserOptions $options, $linestart = true, $clearState = true, $revid = null)
{
/**
* First pass--just handle <nowiki> sections, pass the rest off
* to internalParse() which does all the real work.
*/
global $wgShowHostnames;
if ($clearState) {
// We use U+007F DELETE to construct strip markers, so we have to make
// sure that this character does not occur in the input text.
$text = strtr($text, "", "?");
$magicScopeVariable = $this->lock();
}
$this->startParse($title, $options, self::OT_HTML, $clearState);
$this->currentRevisionCache = null;
$this->mInputSize = strlen($text);
if ($this->mOptions->getEnableLimitReport()) {
$this->mOutput->resetParseStartTime();
}
$oldRevisionId = $this->mRevisionId;
$oldRevisionObject = $this->mRevisionObject;
$oldRevisionTimestamp = $this->mRevisionTimestamp;
$oldRevisionUser = $this->mRevisionUser;
$oldRevisionSize = $this->mRevisionSize;
if ($revid !== null) {
$this->mRevisionId = $revid;
$this->mRevisionObject = null;
$this->mRevisionTimestamp = null;
$this->mRevisionUser = null;
$this->mRevisionSize = null;
}
Hooks::run('ParserBeforeStrip', array(&$this, &$text, &$this->mStripState));
# No more strip!
Hooks::run('ParserAfterStrip', array(&$this, &$text, &$this->mStripState));
$text = $this->internalParse($text);
Hooks::run('ParserAfterParse', array(&$this, &$text, &$this->mStripState));
$text = $this->internalParseHalfParsed($text, true, $linestart);
/**
* A converted title will be provided in the output object if title and
* content conversion are enabled, the article text does not contain
* a conversion-suppressing double-underscore tag, and no
* {{DISPLAYTITLE:...}} is present. DISPLAYTITLE takes precedence over
* automatic link conversion.
*/
if (!($options->getDisableTitleConversion() || isset($this->mDoubleUnderscores['nocontentconvert']) || isset($this->mDoubleUnderscores['notitleconvert']) || $this->mOutput->getDisplayTitle() !== false)) {
$convruletitle = $this->getConverterLanguage()->getConvRuleTitle();
if ($convruletitle) {
$this->mOutput->setTitleText($convruletitle);
} else {
$titleText = $this->getConverterLanguage()->convertTitle($title);
$this->mOutput->setTitleText($titleText);
}
}
if ($this->mExpensiveFunctionCount > $this->mOptions->getExpensiveParserFunctionLimit()) {
$this->limitationWarn('expensive-parserfunction', $this->mExpensiveFunctionCount, $this->mOptions->getExpensiveParserFunctionLimit());
}
# Information on include size limits, for the benefit of users who try to skirt them
if ($this->mOptions->getEnableLimitReport()) {
$max = $this->mOptions->getMaxIncludeSize();
$cpuTime = $this->mOutput->getTimeSinceStart('cpu');
if ($cpuTime !== null) {
$this->mOutput->setLimitReportData('limitreport-cputime', sprintf("%.3f", $cpuTime));
}
$wallTime = $this->mOutput->getTimeSinceStart('wall');
$this->mOutput->setLimitReportData('limitreport-walltime', sprintf("%.3f", $wallTime));
$this->mOutput->setLimitReportData('limitreport-ppvisitednodes', array($this->mPPNodeCount, $this->mOptions->getMaxPPNodeCount()));
$this->mOutput->setLimitReportData('limitreport-ppgeneratednodes', array($this->mGeneratedPPNodeCount, $this->mOptions->getMaxGeneratedPPNodeCount()));
$this->mOutput->setLimitReportData('limitreport-postexpandincludesize', array($this->mIncludeSizes['post-expand'], $max));
$this->mOutput->setLimitReportData('limitreport-templateargumentsize', array($this->mIncludeSizes['arg'], $max));
$this->mOutput->setLimitReportData('limitreport-expansiondepth', array($this->mHighestExpansionDepth, $this->mOptions->getMaxPPExpandDepth()));
$this->mOutput->setLimitReportData('limitreport-expensivefunctioncount', array($this->mExpensiveFunctionCount, $this->mOptions->getExpensiveParserFunctionLimit()));
Hooks::run('ParserLimitReportPrepare', array($this, $this->mOutput));
$limitReport = "NewPP limit report\n";
if ($wgShowHostnames) {
$limitReport .= 'Parsed by ' . wfHostname() . "\n";
}
$limitReport .= 'Cached time: ' . $this->mOutput->getCacheTime() . "\n";
$limitReport .= 'Cache expiry: ' . $this->mOutput->getCacheExpiry() . "\n";
$limitReport .= 'Dynamic content: ' . ($this->mOutput->hasDynamicContent() ? 'true' : 'false') . "\n";
foreach ($this->mOutput->getLimitReportData() as $key => $value) {
if (Hooks::run('ParserLimitReportFormat', array($key, &$value, &$limitReport, false, false))) {
$keyMsg = wfMessage($key)->inLanguage('en')->useDatabase(false);
$valueMsg = wfMessage(array("{$key}-value-text", "{$key}-value"))->inLanguage('en')->useDatabase(false);
if (!$valueMsg->exists()) {
$valueMsg = new RawMessage('$1');
}
if (!$keyMsg->isDisabled() && !$valueMsg->isDisabled()) {
$valueMsg->params($value);
$limitReport .= "{$keyMsg->text()}: {$valueMsg->text()}\n";
}
}
}
// Since we're not really outputting HTML, decode the entities and
// then re-encode the things that need hiding inside HTML comments.
$limitReport = htmlspecialchars_decode($limitReport);
Hooks::run('ParserLimitReport', array($this, &$limitReport));
// Sanitize for comment. Note '‐' in the replacement is U+2010,
// which looks much like the problematic '-'.
$limitReport = str_replace(array('-', '&'), array('‐', '&'), $limitReport);
$text .= "\n<!-- \n{$limitReport}-->\n";
// Add on template profiling data
$dataByFunc = $this->mProfiler->getFunctionStats();
uasort($dataByFunc, function ($a, $b) {
return $a['real'] < $b['real'];
// descending order
});
$profileReport = "Transclusion expansion time report (%,ms,calls,template)\n";
foreach (array_slice($dataByFunc, 0, 10) as $item) {
$profileReport .= sprintf("%6.2f%% %8.3f %6d - %s\n", $item['%real'], $item['real'], $item['calls'], htmlspecialchars($item['name']));
}
$text .= "\n<!-- \n{$profileReport}-->\n";
if ($this->mGeneratedPPNodeCount > $this->mOptions->getMaxGeneratedPPNodeCount() / 10) {
wfDebugLog('generated-pp-node-count', $this->mGeneratedPPNodeCount . ' ' . $this->mTitle->getPrefixedDBkey());
}
}
$this->mOutput->setText($text);
$this->mRevisionId = $oldRevisionId;
$this->mRevisionObject = $oldRevisionObject;
$this->mRevisionTimestamp = $oldRevisionTimestamp;
$this->mRevisionUser = $oldRevisionUser;
$this->mRevisionSize = $oldRevisionSize;
$this->mInputSize = false;
$this->currentRevisionCache = null;
return $this->mOutput;
}
/**
* Convert wikitext to HTML
* Do not call this function recursively.
*
* @param string $text text we want to parse
* @param $title Title object
* @param $options ParserOptions
* @param $linestart boolean
* @param $clearState boolean
* @param int $revid number to pass in {{REVISIONID}}
* @return ParserOutput a ParserOutput
*/
public function parse($text, Title $title, ParserOptions $options, $linestart = true, $clearState = true, $revid = null)
{
/**
* First pass--just handle <nowiki> sections, pass the rest off
* to internalParse() which does all the real work.
*/
global $wgUseTidy, $wgAlwaysUseTidy, $wgShowHostnames;
$fname = __METHOD__ . '-' . wfGetCaller();
wfProfileIn(__METHOD__);
wfProfileIn($fname);
$this->startParse($title, $options, self::OT_HTML, $clearState);
$this->mInputSize = strlen($text);
if ($this->mOptions->getEnableLimitReport()) {
$this->mOutput->resetParseStartTime();
}
# Remove the strip marker tag prefix from the input, if present.
if ($clearState) {
$text = str_replace($this->mUniqPrefix, '', $text);
}
$oldRevisionId = $this->mRevisionId;
$oldRevisionObject = $this->mRevisionObject;
$oldRevisionTimestamp = $this->mRevisionTimestamp;
$oldRevisionUser = $this->mRevisionUser;
$oldRevisionSize = $this->mRevisionSize;
if ($revid !== null) {
$this->mRevisionId = $revid;
$this->mRevisionObject = null;
$this->mRevisionTimestamp = null;
$this->mRevisionUser = null;
$this->mRevisionSize = null;
}
wfRunHooks('ParserBeforeStrip', array(&$this, &$text, &$this->mStripState));
# No more strip!
wfRunHooks('ParserAfterStrip', array(&$this, &$text, &$this->mStripState));
$text = $this->internalParse($text);
wfRunHooks('ParserAfterParse', array(&$this, &$text, &$this->mStripState));
$text = $this->mStripState->unstripGeneral($text);
# Clean up special characters, only run once, next-to-last before doBlockLevels
$fixtags = array('/(.) (?=\\?|:|;|!|%|\\302\\273)/' => '\\1 ', '/(\\302\\253) /' => '\\1 ', '/ (!\\s*important)/' => ' \\1');
$text = preg_replace(array_keys($fixtags), array_values($fixtags), $text);
$text = $this->doBlockLevels($text, $linestart);
$this->replaceLinkHolders($text);
/**
* The input doesn't get language converted if
* a) It's disabled
* b) Content isn't converted
* c) It's a conversion table
* d) it is an interface message (which is in the user language)
*/
if (!($options->getDisableContentConversion() || isset($this->mDoubleUnderscores['nocontentconvert']))) {
if (!$this->mOptions->getInterfaceMessage()) {
# The position of the convert() call should not be changed. it
# assumes that the links are all replaced and the only thing left
# is the <nowiki> mark.
$text = $this->getConverterLanguage()->convert($text);
}
}
/**
* A converted title will be provided in the output object if title and
* content conversion are enabled, the article text does not contain
* a conversion-suppressing double-underscore tag, and no
* {{DISPLAYTITLE:...}} is present. DISPLAYTITLE takes precedence over
* automatic link conversion.
*/
if (!($options->getDisableTitleConversion() || isset($this->mDoubleUnderscores['nocontentconvert']) || isset($this->mDoubleUnderscores['notitleconvert']) || $this->mOutput->getDisplayTitle() !== false)) {
$convruletitle = $this->getConverterLanguage()->getConvRuleTitle();
if ($convruletitle) {
$this->mOutput->setTitleText($convruletitle);
} else {
$titleText = $this->getConverterLanguage()->convertTitle($title);
$this->mOutput->setTitleText($titleText);
}
}
$text = $this->mStripState->unstripNoWiki($text);
wfRunHooks('ParserBeforeTidy', array(&$this, &$text));
$text = $this->replaceTransparentTags($text);
$text = $this->mStripState->unstripGeneral($text);
$text = Sanitizer::normalizeCharReferences($text);
if ($wgUseTidy && $this->mOptions->getTidy() || $wgAlwaysUseTidy) {
$text = MWTidy::tidy($text);
} else {
# attempt to sanitize at least some nesting problems
# (bug #2702 and quite a few others)
$tidyregs = array('/(<([bi])>)(<([bi])>)?([^<]*)(<\\/?a[^<]*>)([^<]*)(<\\/\\4>)?(<\\/\\2>)/' => '\\1\\3\\5\\8\\9\\6\\1\\3\\7\\8\\9', '/(<a[^>]+>)([^<]*)(<a[^>]+>[^<]*)<\\/a>(.*)<\\/a>/' => '\\1\\2</a>\\3</a>\\1\\4</a>', '/(<([aib]) [^>]+>)([^<]*)(<div([^>]*)>)(.*)(<\\/div>)([^<]*)(<\\/\\2>)/' => '\\1\\3<div\\5>\\6</div>\\8\\9', '/<([bi])><\\/\\1>/' => '');
$text = preg_replace(array_keys($tidyregs), array_values($tidyregs), $text);
}
if ($this->mExpensiveFunctionCount > $this->mOptions->getExpensiveParserFunctionLimit()) {
$this->limitationWarn('expensive-parserfunction', $this->mExpensiveFunctionCount, $this->mOptions->getExpensiveParserFunctionLimit());
}
wfRunHooks('ParserAfterTidy', array(&$this, &$text));
# Information on include size limits, for the benefit of users who try to skirt them
if ($this->mOptions->getEnableLimitReport()) {
$max = $this->mOptions->getMaxIncludeSize();
$cpuTime = $this->mOutput->getTimeSinceStart('cpu');
if ($cpuTime !== null) {
$this->mOutput->setLimitReportData('limitreport-cputime', sprintf("%.3f", $cpuTime));
}
$wallTime = $this->mOutput->getTimeSinceStart('wall');
$this->mOutput->setLimitReportData('limitreport-walltime', sprintf("%.3f", $wallTime));
$this->mOutput->setLimitReportData('limitreport-ppvisitednodes', array($this->mPPNodeCount, $this->mOptions->getMaxPPNodeCount()));
$this->mOutput->setLimitReportData('limitreport-ppgeneratednodes', array($this->mGeneratedPPNodeCount, $this->mOptions->getMaxGeneratedPPNodeCount()));
$this->mOutput->setLimitReportData('limitreport-postexpandincludesize', array($this->mIncludeSizes['post-expand'], $max));
$this->mOutput->setLimitReportData('limitreport-templateargumentsize', array($this->mIncludeSizes['arg'], $max));
$this->mOutput->setLimitReportData('limitreport-expansiondepth', array($this->mHighestExpansionDepth, $this->mOptions->getMaxPPExpandDepth()));
$this->mOutput->setLimitReportData('limitreport-expensivefunctioncount', array($this->mExpensiveFunctionCount, $this->mOptions->getExpensiveParserFunctionLimit()));
wfRunHooks('ParserLimitReportPrepare', array($this, $this->mOutput));
$limitReport = "NewPP limit report\n";
if ($wgShowHostnames) {
$limitReport .= 'Parsed by ' . wfHostname() . "\n";
}
foreach ($this->mOutput->getLimitReportData() as $key => $value) {
if (wfRunHooks('ParserLimitReportFormat', array($key, &$value, &$limitReport, false, false))) {
$keyMsg = wfMessage($key)->inLanguage('en')->useDatabase(false);
$valueMsg = wfMessage(array("{$key}-value-text", "{$key}-value"))->inLanguage('en')->useDatabase(false);
if (!$valueMsg->exists()) {
$valueMsg = new RawMessage('$1');
}
if (!$keyMsg->isDisabled() && !$valueMsg->isDisabled()) {
$valueMsg->params($value);
$limitReport .= "{$keyMsg->text()}: {$valueMsg->text()}\n";
}
}
}
// Since we're not really outputting HTML, decode the entities and
// then re-encode the things that need hiding inside HTML comments.
$limitReport = htmlspecialchars_decode($limitReport);
wfRunHooks('ParserLimitReport', array($this, &$limitReport));
// Sanitize for comment. Note '‐' in the replacement is U+2010,
// which looks much like the problematic '-'.
$limitReport = str_replace(array('-', '&'), array('‐', '&'), $limitReport);
$text .= "\n<!-- \n{$limitReport}-->\n";
if ($this->mGeneratedPPNodeCount > $this->mOptions->getMaxGeneratedPPNodeCount() / 10) {
wfDebugLog('generated-pp-node-count', $this->mGeneratedPPNodeCount . ' ' . $this->mTitle->getPrefixedDBkey());
}
}
$this->mOutput->setText($text);
$this->mRevisionId = $oldRevisionId;
$this->mRevisionObject = $oldRevisionObject;
$this->mRevisionTimestamp = $oldRevisionTimestamp;
$this->mRevisionUser = $oldRevisionUser;
$this->mRevisionSize = $oldRevisionSize;
$this->mInputSize = false;
wfProfileOut($fname);
wfProfileOut(__METHOD__);
return $this->mOutput;
}
/**
* Convert wikitext to HTML
* Do not call this function recursively.
*
* @param string $text Text we want to parse
* @param Title $title
* @param ParserOptions $options
* @param bool $linestart
* @param bool $clearState
* @param int $revid Number to pass in {{REVISIONID}}
* @return ParserOutput A ParserOutput
*/
public function parse($text, Title $title, ParserOptions $options, $linestart = true, $clearState = true, $revid = null)
{
/**
* First pass--just handle <nowiki> sections, pass the rest off
* to internalParse() which does all the real work.
*/
global $wgShowHostnames;
if ($clearState) {
// We use U+007F DELETE to construct strip markers, so we have to make
// sure that this character does not occur in the input text.
$text = strtr($text, "", "?");
$magicScopeVariable = $this->lock();
}
$this->startParse($title, $options, self::OT_HTML, $clearState);
$this->currentRevisionCache = null;
$this->mInputSize = strlen($text);
if ($this->mOptions->getEnableLimitReport()) {
$this->mOutput->resetParseStartTime();
}
$oldRevisionId = $this->mRevisionId;
$oldRevisionObject = $this->mRevisionObject;
$oldRevisionTimestamp = $this->mRevisionTimestamp;
$oldRevisionUser = $this->mRevisionUser;
$oldRevisionSize = $this->mRevisionSize;
if ($revid !== null) {
$this->mRevisionId = $revid;
$this->mRevisionObject = null;
$this->mRevisionTimestamp = null;
$this->mRevisionUser = null;
$this->mRevisionSize = null;
}
Hooks::run('ParserBeforeStrip', [&$this, &$text, &$this->mStripState]);
# No more strip!
Hooks::run('ParserAfterStrip', [&$this, &$text, &$this->mStripState]);
$text = $this->internalParse($text);
Hooks::run('ParserAfterParse', [&$this, &$text, &$this->mStripState]);
$text = $this->internalParseHalfParsed($text, true, $linestart);
/**
* A converted title will be provided in the output object if title and
* content conversion are enabled, the article text does not contain
* a conversion-suppressing double-underscore tag, and no
* {{DISPLAYTITLE:...}} is present. DISPLAYTITLE takes precedence over
* automatic link conversion.
*/
if (!($options->getDisableTitleConversion() || isset($this->mDoubleUnderscores['nocontentconvert']) || isset($this->mDoubleUnderscores['notitleconvert']) || $this->mOutput->getDisplayTitle() !== false)) {
$convruletitle = $this->getConverterLanguage()->getConvRuleTitle();
if ($convruletitle) {
$this->mOutput->setTitleText($convruletitle);
} else {
$titleText = $this->getConverterLanguage()->convertTitle($title);
$this->mOutput->setTitleText($titleText);
}
}
# Done parsing! Compute runtime adaptive expiry if set
$this->mOutput->finalizeAdaptiveCacheExpiry();
# Warn if too many heavyweight parser functions were used
if ($this->mExpensiveFunctionCount > $this->mOptions->getExpensiveParserFunctionLimit()) {
$this->limitationWarn('expensive-parserfunction', $this->mExpensiveFunctionCount, $this->mOptions->getExpensiveParserFunctionLimit());
}
# Information on include size limits, for the benefit of users who try to skirt them
if ($this->mOptions->getEnableLimitReport()) {
$max = $this->mOptions->getMaxIncludeSize();
$cpuTime = $this->mOutput->getTimeSinceStart('cpu');
if ($cpuTime !== null) {
$this->mOutput->setLimitReportData('limitreport-cputime', sprintf("%.3f", $cpuTime));
}
$wallTime = $this->mOutput->getTimeSinceStart('wall');
$this->mOutput->setLimitReportData('limitreport-walltime', sprintf("%.3f", $wallTime));
$this->mOutput->setLimitReportData('limitreport-ppvisitednodes', [$this->mPPNodeCount, $this->mOptions->getMaxPPNodeCount()]);
$this->mOutput->setLimitReportData('limitreport-ppgeneratednodes', [$this->mGeneratedPPNodeCount, $this->mOptions->getMaxGeneratedPPNodeCount()]);
$this->mOutput->setLimitReportData('limitreport-postexpandincludesize', [$this->mIncludeSizes['post-expand'], $max]);
$this->mOutput->setLimitReportData('limitreport-templateargumentsize', [$this->mIncludeSizes['arg'], $max]);
$this->mOutput->setLimitReportData('limitreport-expansiondepth', [$this->mHighestExpansionDepth, $this->mOptions->getMaxPPExpandDepth()]);
$this->mOutput->setLimitReportData('limitreport-expensivefunctioncount', [$this->mExpensiveFunctionCount, $this->mOptions->getExpensiveParserFunctionLimit()]);
Hooks::run('ParserLimitReportPrepare', [$this, $this->mOutput]);
$limitReport = '';
Hooks::run('ParserLimitReport', [$this, &$limitReport]);
if ($limitReport != '') {
// Sanitize for comment. Note '‐' in the replacement is U+2010,
// which looks much like the problematic '-'.
$limitReport = str_replace(['-', '&'], ['‐', '&'], $limitReport);
$text .= "\n<!-- \nNewPP limit report\n{$limitReport}-->\n";
}
// Add on template profiling data in human/machine readable way
$dataByFunc = $this->mProfiler->getFunctionStats();
uasort($dataByFunc, function ($a, $b) {
return $a['real'] < $b['real'];
// descending order
});
$profileReport = [];
foreach (array_slice($dataByFunc, 0, 10) as $item) {
$profileReport[] = sprintf("%6.2f%% %8.3f %6d %s", $item['%real'], $item['real'], $item['calls'], $item['name']);
}
$this->mOutput->setLimitReportData('limitreport-timingprofile', $profileReport);
// Add other cache related metadata
if ($wgShowHostnames) {
$this->mOutput->setLimitReportData('cachereport-origin', wfHostname());
}
$this->mOutput->setLimitReportData('cachereport-timestamp', $this->mOutput->getCacheTime());
$this->mOutput->setLimitReportData('cachereport-ttl', $this->mOutput->getCacheExpiry());
$this->mOutput->setLimitReportData('cachereport-transientcontent', $this->mOutput->hasDynamicContent());
if ($this->mGeneratedPPNodeCount > $this->mOptions->getMaxGeneratedPPNodeCount() / 10) {
wfDebugLog('generated-pp-node-count', $this->mGeneratedPPNodeCount . ' ' . $this->mTitle->getPrefixedDBkey());
}
}
$this->mOutput->setText($text);
$this->mRevisionId = $oldRevisionId;
$this->mRevisionObject = $oldRevisionObject;
$this->mRevisionTimestamp = $oldRevisionTimestamp;
$this->mRevisionUser = $oldRevisionUser;
$this->mRevisionSize = $oldRevisionSize;
$this->mInputSize = false;
$this->currentRevisionCache = null;
return $this->mOutput;
}
