includes/GlobalFunctions.php

   1 <?php
   2 /**
   3  * Global functions used everywhere.
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  */
  22
  23 if ( !defined( 'MEDIAWIKI' ) ) {
  24         die( "This file is part of MediaWiki, it is not a valid entry point" );
  25 }
  26
  27 use Liuggio\StatsdClient\Sender\SocketSender;
  28 use MediaWiki\Logger\LoggerFactory;
  29 use MediaWiki\Session\SessionManager;
  30 use Wikimedia\ScopedCallback;
  31
  32 // Hide compatibility functions from Doxygen
  33 /// @cond
  34 /**
  35  * Compatibility functions
  36  *
  37  * We support PHP 5.5.9 and up.
  38  * Re-implementations of newer functions or functions in non-standard
  39  * PHP extensions may be included here.
  40  */
  41
  42 // hash_equals function only exists in PHP >= 5.6.0
  43 // http://php.net/hash_equals
  44 if ( !function_exists( 'hash_equals' ) ) {
  45         /**
  46          * Check whether a user-provided string is equal to a fixed-length secret string
  47          * without revealing bytes of the secret string through timing differences.
  48          *
  49          * The usual way to compare strings (PHP's === operator or the underlying memcmp()
  50          * function in C) is to compare corresponding bytes and stop at the first difference,
  51          * which would take longer for a partial match than for a complete mismatch. This
  52          * is not secure when one of the strings (e.g. an HMAC or token) must remain secret
  53          * and the other may come from an attacker. Statistical analysis of timing measurements
  54          * over many requests may allow the attacker to guess the string's bytes one at a time
  55          * (and check his guesses) even if the timing differences are extremely small.
  56          *
  57          * When making such a security-sensitive comparison, it is essential that the sequence
  58          * in which instructions are executed and memory locations are accessed not depend on
  59          * the secret string's value. HOWEVER, for simplicity, we do not attempt to minimize
  60          * the inevitable leakage of the string's length. That is generally known anyway as
  61          * a chararacteristic of the hash function used to compute the secret value.
  62          *
  63          * Longer explanation: http://www.emerose.com/timing-attacks-explained
  64          *
  65          * @codeCoverageIgnore
  66          * @param string $known_string Fixed-length secret string to compare against
  67          * @param string $user_string User-provided string
  68          * @return bool True if the strings are the same, false otherwise
  69          */
  70         function hash_equals( $known_string, $user_string ) {
  71                 // Strict type checking as in PHP's native implementation
  72                 if ( !is_string( $known_string ) ) {
  73                         trigger_error( 'hash_equals(): Expected known_string to be a string, ' .
  74                                 gettype( $known_string ) . ' given', E_USER_WARNING );
  75
  76                         return false;
  77                 }
  78
  79                 if ( !is_string( $user_string ) ) {
  80                         trigger_error( 'hash_equals(): Expected user_string to be a string, ' .
  81                                 gettype( $user_string ) . ' given', E_USER_WARNING );
  82
  83                         return false;
  84                 }
  85
  86                 $known_string_len = strlen( $known_string );
  87                 if ( $known_string_len !== strlen( $user_string ) ) {
  88                         return false;
  89                 }
  90
  91                 $result = 0;
  92                 for ( $i = 0; $i < $known_string_len; $i++ ) {
  93                         $result |= ord( $known_string[$i] ) ^ ord( $user_string[$i] );
  94                 }
  95
  96                 return ( $result === 0 );
  97         }
  98 }
  99 /// @endcond
 100
 101 /**
 102  * Load an extension
 103  *
 104  * This queues an extension to be loaded through
 105  * the ExtensionRegistry system.
 106  *
 107  * @param string $ext Name of the extension to load
 108  * @param string|null $path Absolute path of where to find the extension.json file
 109  * @since 1.25
 110  */
 111 function wfLoadExtension( $ext, $path = null ) {
 112         if ( !$path ) {
 113                 global $wgExtensionDirectory;
 114                 $path = "$wgExtensionDirectory/$ext/extension.json";
 115         }
 116         ExtensionRegistry::getInstance()->queue( $path );
 117 }
 118
 119 /**
 120  * Load multiple extensions at once
 121  *
 122  * Same as wfLoadExtension, but more efficient if you
 123  * are loading multiple extensions.
 124  *
 125  * If you want to specify custom paths, you should interact with
 126  * ExtensionRegistry directly.
 127  *
 128  * @see wfLoadExtension
 129  * @param string[] $exts Array of extension names to load
 130  * @since 1.25
 131  */
 132 function wfLoadExtensions( array $exts ) {
 133         global $wgExtensionDirectory;
 134         $registry = ExtensionRegistry::getInstance();
 135         foreach ( $exts as $ext ) {
 136                 $registry->queue( "$wgExtensionDirectory/$ext/extension.json" );
 137         }
 138 }
 139
 140 /**
 141  * Load a skin
 142  *
 143  * @see wfLoadExtension
 144  * @param string $skin Name of the extension to load
 145  * @param string|null $path Absolute path of where to find the skin.json file
 146  * @since 1.25
 147  */
 148 function wfLoadSkin( $skin, $path = null ) {
 149         if ( !$path ) {
 150                 global $wgStyleDirectory;
 151                 $path = "$wgStyleDirectory/$skin/skin.json";
 152         }
 153         ExtensionRegistry::getInstance()->queue( $path );
 154 }
 155
 156 /**
 157  * Load multiple skins at once
 158  *
 159  * @see wfLoadExtensions
 160  * @param string[] $skins Array of extension names to load
 161  * @since 1.25
 162  */
 163 function wfLoadSkins( array $skins ) {
 164         global $wgStyleDirectory;
 165         $registry = ExtensionRegistry::getInstance();
 166         foreach ( $skins as $skin ) {
 167                 $registry->queue( "$wgStyleDirectory/$skin/skin.json" );
 168         }
 169 }
 170
 171 /**
 172  * Like array_diff( $a, $b ) except that it works with two-dimensional arrays.
 173  * @param array $a
 174  * @param array $b
 175  * @return array
 176  */
 177 function wfArrayDiff2( $a, $b ) {
 178         return array_udiff( $a, $b, 'wfArrayDiff2_cmp' );
 179 }
 180
 181 /**
 182  * @param array|string $a
 183  * @param array|string $b
 184  * @return int
 185  */
 186 function wfArrayDiff2_cmp( $a, $b ) {
 187         if ( is_string( $a ) && is_string( $b ) ) {
 188                 return strcmp( $a, $b );
 189         } elseif ( count( $a ) !== count( $b ) ) {
 190                 return count( $a ) < count( $b ) ? -1 : 1;
 191         } else {
 192                 reset( $a );
 193                 reset( $b );
 194                 while ( ( list( , $valueA ) = each( $a ) ) && ( list( , $valueB ) = each( $b ) ) ) {
 195                         $cmp = strcmp( $valueA, $valueB );
 196                         if ( $cmp !== 0 ) {
 197                                 return $cmp;
 198                         }
 199                 }
 200                 return 0;
 201         }
 202 }
 203
 204 /**
 205  * Appends to second array if $value differs from that in $default
 206  *
 207  * @param string|int $key
 208  * @param mixed $value
 209  * @param mixed $default
 210  * @param array $changed Array to alter
 211  * @throws MWException
 212  */
 213 function wfAppendToArrayIfNotDefault( $key, $value, $default, &$changed ) {
 214         if ( is_null( $changed ) ) {
 215                 throw new MWException( 'GlobalFunctions::wfAppendToArrayIfNotDefault got null' );
 216         }
 217         if ( $default[$key] !== $value ) {
 218                 $changed[$key] = $value;
 219         }
 220 }
 221
 222 /**
 223  * Merge arrays in the style of getUserPermissionsErrors, with duplicate removal
 224  * e.g.
 225  *      wfMergeErrorArrays(
 226  *              [ [ 'x' ] ],
 227  *              [ [ 'x', '2' ] ],
 228  *              [ [ 'x' ] ],
 229  *              [ [ 'y' ] ]
 230  *      );
 231  * returns:
 232  *              [
 233  *              [ 'x', '2' ],
 234  *              [ 'x' ],
 235  *              [ 'y' ]
 236  *      ]
 237  *
 238  * @param array $array1,...
 239  * @return array
 240  */
 241 function wfMergeErrorArrays( /*...*/ ) {
 242         $args = func_get_args();
 243         $out = [];
 244         foreach ( $args as $errors ) {
 245                 foreach ( $errors as $params ) {
 246                         $originalParams = $params;
 247                         if ( $params[0] instanceof MessageSpecifier ) {
 248                                 $msg = $params[0];
 249                                 $params = array_merge( [ $msg->getKey() ], $msg->getParams() );
 250                         }
 251                         # @todo FIXME: Sometimes get nested arrays for $params,
 252                         # which leads to E_NOTICEs
 253                         $spec = implode( "\t", $params );
 254                         $out[$spec] = $originalParams;
 255                 }
 256         }
 257         return array_values( $out );
 258 }
 259
 260 /**
 261  * Insert array into another array after the specified *KEY*
 262  *
 263  * @param array $array The array.
 264  * @param array $insert The array to insert.
 265  * @param mixed $after The key to insert after
 266  * @return array
 267  */
 268 function wfArrayInsertAfter( array $array, array $insert, $after ) {
 269         // Find the offset of the element to insert after.
 270         $keys = array_keys( $array );
 271         $offsetByKey = array_flip( $keys );
 272
 273         $offset = $offsetByKey[$after];
 274
 275         // Insert at the specified offset
 276         $before = array_slice( $array, 0, $offset + 1, true );
 277         $after = array_slice( $array, $offset + 1, count( $array ) - $offset, true );
 278
 279         $output = $before + $insert + $after;
 280
 281         return $output;
 282 }
 283
 284 /**
 285  * Recursively converts the parameter (an object) to an array with the same data
 286  *
 287  * @param object|array $objOrArray
 288  * @param bool $recursive
 289  * @return array
 290  */
 291 function wfObjectToArray( $objOrArray, $recursive = true ) {
 292         $array = [];
 293         if ( is_object( $objOrArray ) ) {
 294                 $objOrArray = get_object_vars( $objOrArray );
 295         }
 296         foreach ( $objOrArray as $key => $value ) {
 297                 if ( $recursive && ( is_object( $value ) || is_array( $value ) ) ) {
 298                         $value = wfObjectToArray( $value );
 299                 }
 300
 301                 $array[$key] = $value;
 302         }
 303
 304         return $array;
 305 }
 306
 307 /**
 308  * Get a random decimal value between 0 and 1, in a way
 309  * not likely to give duplicate values for any realistic
 310  * number of articles.
 311  *
 312  * @note This is designed for use in relation to Special:RandomPage
 313  *       and the page_random database field.
 314  *
 315  * @return string
 316  */
 317 function wfRandom() {
 318         // The maximum random value is "only" 2^31-1, so get two random
 319         // values to reduce the chance of dupes
 320         $max = mt_getrandmax() + 1;
 321         $rand = number_format( ( mt_rand() * $max + mt_rand() ) / $max / $max, 12, '.', '' );
 322         return $rand;
 323 }
 324
 325 /**
 326  * Get a random string containing a number of pseudo-random hex characters.
 327  *
 328  * @note This is not secure, if you are trying to generate some sort
 329  *       of token please use MWCryptRand instead.
 330  *
 331  * @param int $length The length of the string to generate
 332  * @return string
 333  * @since 1.20
 334  */
 335 function wfRandomString( $length = 32 ) {
 336         $str = '';
 337         for ( $n = 0; $n < $length; $n += 7 ) {
 338                 $str .= sprintf( '%07x', mt_rand() & 0xfffffff );
 339         }
 340         return substr( $str, 0, $length );
 341 }
 342
 343 /**
 344  * We want some things to be included as literal characters in our title URLs
 345  * for prettiness, which urlencode encodes by default.  According to RFC 1738,
 346  * all of the following should be safe:
 347  *
 348  * ;:@&=$-_.+!*'(),
 349  *
 350  * RFC 1738 says ~ is unsafe, however RFC 3986 considers it an unreserved
 351  * character which should not be encoded. More importantly, google chrome
 352  * always converts %7E back to ~, and converting it in this function can
 353  * cause a redirect loop (T105265).
 354  *
 355  * But + is not safe because it's used to indicate a space; &= are only safe in
 356  * paths and not in queries (and we don't distinguish here); ' seems kind of
 357  * scary; and urlencode() doesn't touch -_. to begin with.  Plus, although /
 358  * is reserved, we don't care.  So the list we unescape is:
 359  *
 360  * ;:@$!*(),/~
 361  *
 362  * However, IIS7 redirects fail when the url contains a colon (see T24709),
 363  * so no fancy : for IIS7.
 364  *
 365  * %2F in the page titles seems to fatally break for some reason.
 366  *
 367  * @param string $s
 368  * @return string
 369  */
 370 function wfUrlencode( $s ) {
 371         static $needle;
 372
 373         if ( is_null( $s ) ) {
 374                 $needle = null;
 375                 return '';
 376         }
 377
 378         if ( is_null( $needle ) ) {
 379                 $needle = [ '%3B', '%40', '%24', '%21', '%2A', '%28', '%29', '%2C', '%2F', '%7E' ];
 380                 if ( !isset( $_SERVER['SERVER_SOFTWARE'] ) ||
 381                         ( strpos( $_SERVER['SERVER_SOFTWARE'], 'Microsoft-IIS/7' ) === false )
 382                 ) {
 383                         $needle[] = '%3A';
 384                 }
 385         }
 386
 387         $s = urlencode( $s );
 388         $s = str_ireplace(
 389                 $needle,
 390                 [ ';', '@', '$', '!', '*', '(', ')', ',', '/', '~', ':' ],
 391                 $s
 392         );
 393
 394         return $s;
 395 }
 396
 397 /**
 398  * This function takes one or two arrays as input, and returns a CGI-style string, e.g.
 399  * "days=7&limit=100". Options in the first array override options in the second.
 400  * Options set to null or false will not be output.
 401  *
 402  * @param array $array1 ( String|Array )
 403  * @param array|null $array2 ( String|Array )
 404  * @param string $prefix
 405  * @return string
 406  */
 407 function wfArrayToCgi( $array1, $array2 = null, $prefix = '' ) {
 408         if ( !is_null( $array2 ) ) {
 409                 $array1 = $array1 + $array2;
 410         }
 411
 412         $cgi = '';
 413         foreach ( $array1 as $key => $value ) {
 414                 if ( !is_null( $value ) && $value !== false ) {
 415                         if ( $cgi != '' ) {
 416                                 $cgi .= '&';
 417                         }
 418                         if ( $prefix !== '' ) {
 419                                 $key = $prefix . "[$key]";
 420                         }
 421                         if ( is_array( $value ) ) {
 422                                 $firstTime = true;
 423                                 foreach ( $value as $k => $v ) {
 424                                         $cgi .= $firstTime ? '' : '&';
 425                                         if ( is_array( $v ) ) {
 426                                                 $cgi .= wfArrayToCgi( $v, null, $key . "[$k]" );
 427                                         } else {
 428                                                 $cgi .= urlencode( $key . "[$k]" ) . '=' . urlencode( $v );
 429                                         }
 430                                         $firstTime = false;
 431                                 }
 432                         } else {
 433                                 if ( is_object( $value ) ) {
 434                                         $value = $value->__toString();
 435                                 }
 436                                 $cgi .= urlencode( $key ) . '=' . urlencode( $value );
 437                         }
 438                 }
 439         }
 440         return $cgi;
 441 }
 442
 443 /**
 444  * This is the logical opposite of wfArrayToCgi(): it accepts a query string as
 445  * its argument and returns the same string in array form.  This allows compatibility
 446  * with legacy functions that accept raw query strings instead of nice
 447  * arrays.  Of course, keys and values are urldecode()d.
 448  *
 449  * @param string $query Query string
 450  * @return string[] Array version of input
 451  */
 452 function wfCgiToArray( $query ) {
 453         if ( isset( $query[0] ) && $query[0] == '?' ) {
 454                 $query = substr( $query, 1 );
 455         }
 456         $bits = explode( '&', $query );
 457         $ret = [];
 458         foreach ( $bits as $bit ) {
 459                 if ( $bit === '' ) {
 460                         continue;
 461                 }
 462                 if ( strpos( $bit, '=' ) === false ) {
 463                         // Pieces like &qwerty become 'qwerty' => '' (at least this is what php does)
 464                         $key = $bit;
 465                         $value = '';
 466                 } else {
 467                         list( $key, $value ) = explode( '=', $bit );
 468                 }
 469                 $key = urldecode( $key );
 470                 $value = urldecode( $value );
 471                 if ( strpos( $key, '[' ) !== false ) {
 472                         $keys = array_reverse( explode( '[', $key ) );
 473                         $key = array_pop( $keys );
 474                         $temp = $value;
 475                         foreach ( $keys as $k ) {
 476                                 $k = substr( $k, 0, -1 );
 477                                 $temp = [ $k => $temp ];
 478                         }
 479                         if ( isset( $ret[$key] ) ) {
 480                                 $ret[$key] = array_merge( $ret[$key], $temp );
 481                         } else {
 482                                 $ret[$key] = $temp;
 483                         }
 484                 } else {
 485                         $ret[$key] = $value;
 486                 }
 487         }
 488         return $ret;
 489 }
 490
 491 /**
 492  * Append a query string to an existing URL, which may or may not already
 493  * have query string parameters already. If so, they will be combined.
 494  *
 495  * @param string $url
 496  * @param string|string[] $query String or associative array
 497  * @return string
 498  */
 499 function wfAppendQuery( $url, $query ) {
 500         if ( is_array( $query ) ) {
 501                 $query = wfArrayToCgi( $query );
 502         }
 503         if ( $query != '' ) {
 504                 // Remove the fragment, if there is one
 505                 $fragment = false;
 506                 $hashPos = strpos( $url, '#' );
 507                 if ( $hashPos !== false ) {
 508                         $fragment = substr( $url, $hashPos );
 509                         $url = substr( $url, 0, $hashPos );
 510                 }
 511
 512                 // Add parameter
 513                 if ( false === strpos( $url, '?' ) ) {
 514                         $url .= '?';
 515                 } else {
 516                         $url .= '&';
 517                 }
 518                 $url .= $query;
 519
 520                 // Put the fragment back
 521                 if ( $fragment !== false ) {
 522                         $url .= $fragment;
 523                 }
 524         }
 525         return $url;
 526 }
 527
 528 /**
 529  * Expand a potentially local URL to a fully-qualified URL. Assumes $wgServer
 530  * is correct.
 531  *
 532  * The meaning of the PROTO_* constants is as follows:
 533  * PROTO_HTTP: Output a URL starting with http://
 534  * PROTO_HTTPS: Output a URL starting with https://
 535  * PROTO_RELATIVE: Output a URL starting with // (protocol-relative URL)
 536  * PROTO_CURRENT: Output a URL starting with either http:// or https:// , depending
 537  *    on which protocol was used for the current incoming request
 538  * PROTO_CANONICAL: For URLs without a domain, like /w/index.php , use $wgCanonicalServer.
 539  *    For protocol-relative URLs, use the protocol of $wgCanonicalServer
 540  * PROTO_INTERNAL: Like PROTO_CANONICAL, but uses $wgInternalServer instead of $wgCanonicalServer
 541  *
 542  * @todo this won't work with current-path-relative URLs
 543  * like "subdir/foo.html", etc.
 544  *
 545  * @param string $url Either fully-qualified or a local path + query
 546  * @param string $defaultProto One of the PROTO_* constants. Determines the
 547  *    protocol to use if $url or $wgServer is protocol-relative
 548  * @return string Fully-qualified URL, current-path-relative URL or false if
 549  *    no valid URL can be constructed
 550  */
 551 function wfExpandUrl( $url, $defaultProto = PROTO_CURRENT ) {
 552         global $wgServer, $wgCanonicalServer, $wgInternalServer, $wgRequest,
 553                 $wgHttpsPort;
 554         if ( $defaultProto === PROTO_CANONICAL ) {
 555                 $serverUrl = $wgCanonicalServer;
 556         } elseif ( $defaultProto === PROTO_INTERNAL && $wgInternalServer !== false ) {
 557                 // Make $wgInternalServer fall back to $wgServer if not set
 558                 $serverUrl = $wgInternalServer;
 559         } else {
 560                 $serverUrl = $wgServer;
 561                 if ( $defaultProto === PROTO_CURRENT ) {
 562                         $defaultProto = $wgRequest->getProtocol() . '://';
 563                 }
 564         }
 565
 566         // Analyze $serverUrl to obtain its protocol
 567         $bits = wfParseUrl( $serverUrl );
 568         $serverHasProto = $bits && $bits['scheme'] != '';
 569
 570         if ( $defaultProto === PROTO_CANONICAL || $defaultProto === PROTO_INTERNAL ) {
 571                 if ( $serverHasProto ) {
 572                         $defaultProto = $bits['scheme'] . '://';
 573                 } else {
 574                         // $wgCanonicalServer or $wgInternalServer doesn't have a protocol.
 575                         // This really isn't supposed to happen. Fall back to HTTP in this
 576                         // ridiculous case.
 577                         $defaultProto = PROTO_HTTP;
 578                 }
 579         }
 580
 581         $defaultProtoWithoutSlashes = substr( $defaultProto, 0, -2 );
 582
 583         if ( substr( $url, 0, 2 ) == '//' ) {
 584                 $url = $defaultProtoWithoutSlashes . $url;
 585         } elseif ( substr( $url, 0, 1 ) == '/' ) {
 586                 // If $serverUrl is protocol-relative, prepend $defaultProtoWithoutSlashes,
 587                 // otherwise leave it alone.
 588                 $url = ( $serverHasProto ? '' : $defaultProtoWithoutSlashes ) . $serverUrl . $url;
 589         }
 590
 591         $bits = wfParseUrl( $url );
 592
 593         // ensure proper port for HTTPS arrives in URL
 594         // https://phabricator.wikimedia.org/T67184
 595         if ( $defaultProto === PROTO_HTTPS && $wgHttpsPort != 443 ) {
 596                 $bits['port'] = $wgHttpsPort;
 597         }
 598
 599         if ( $bits && isset( $bits['path'] ) ) {
 600                 $bits['path'] = wfRemoveDotSegments( $bits['path'] );
 601                 return wfAssembleUrl( $bits );
 602         } elseif ( $bits ) {
 603                 # No path to expand
 604                 return $url;
 605         } elseif ( substr( $url, 0, 1 ) != '/' ) {
 606                 # URL is a relative path
 607                 return wfRemoveDotSegments( $url );
 608         }
 609
 610         # Expanded URL is not valid.
 611         return false;
 612 }
 613
 614 /**
 615  * This function will reassemble a URL parsed with wfParseURL.  This is useful
 616  * if you need to edit part of a URL and put it back together.
 617  *
 618  * This is the basic structure used (brackets contain keys for $urlParts):
 619  * [scheme][delimiter][user]:[pass]@[host]:[port][path]?[query]#[fragment]
 620  *
 621  * @todo Need to integrate this into wfExpandUrl (see T34168)
 622  *
 623  * @since 1.19
 624  * @param array $urlParts URL parts, as output from wfParseUrl
 625  * @return string URL assembled from its component parts
 626  */
 627 function wfAssembleUrl( $urlParts ) {
 628         $result = '';
 629
 630         if ( isset( $urlParts['delimiter'] ) ) {
 631                 if ( isset( $urlParts['scheme'] ) ) {
 632                         $result .= $urlParts['scheme'];
 633                 }
 634
 635                 $result .= $urlParts['delimiter'];
 636         }
 637
 638         if ( isset( $urlParts['host'] ) ) {
 639                 if ( isset( $urlParts['user'] ) ) {
 640                         $result .= $urlParts['user'];
 641                         if ( isset( $urlParts['pass'] ) ) {
 642                                 $result .= ':' . $urlParts['pass'];
 643                         }
 644                         $result .= '@';
 645                 }
 646
 647                 $result .= $urlParts['host'];
 648
 649                 if ( isset( $urlParts['port'] ) ) {
 650                         $result .= ':' . $urlParts['port'];
 651                 }
 652         }
 653
 654         if ( isset( $urlParts['path'] ) ) {
 655                 $result .= $urlParts['path'];
 656         }
 657
 658         if ( isset( $urlParts['query'] ) ) {
 659                 $result .= '?' . $urlParts['query'];
 660         }
 661
 662         if ( isset( $urlParts['fragment'] ) ) {
 663                 $result .= '#' . $urlParts['fragment'];
 664         }
 665
 666         return $result;
 667 }
 668
 669 /**
 670  * Remove all dot-segments in the provided URL path.  For example,
 671  * '/a/./b/../c/' becomes '/a/c/'.  For details on the algorithm, please see
 672  * RFC3986 section 5.2.4.
 673  *
 674  * @todo Need to integrate this into wfExpandUrl (see T34168)
 675  *
 676  * @param string $urlPath URL path, potentially containing dot-segments
 677  * @return string URL path with all dot-segments removed
 678  */
 679 function wfRemoveDotSegments( $urlPath ) {
 680         $output = '';
 681         $inputOffset = 0;
 682         $inputLength = strlen( $urlPath );
 683
 684         while ( $inputOffset < $inputLength ) {
 685                 $prefixLengthOne = substr( $urlPath, $inputOffset, 1 );
 686                 $prefixLengthTwo = substr( $urlPath, $inputOffset, 2 );
 687                 $prefixLengthThree = substr( $urlPath, $inputOffset, 3 );
 688                 $prefixLengthFour = substr( $urlPath, $inputOffset, 4 );
 689                 $trimOutput = false;
 690
 691                 if ( $prefixLengthTwo == './' ) {
 692                         # Step A, remove leading "./"
 693                         $inputOffset += 2;
 694                 } elseif ( $prefixLengthThree == '../' ) {
 695                         # Step A, remove leading "../"
 696                         $inputOffset += 3;
 697                 } elseif ( ( $prefixLengthTwo == '/.' ) && ( $inputOffset + 2 == $inputLength ) ) {
 698                         # Step B, replace leading "/.$" with "/"
 699                         $inputOffset += 1;
 700                         $urlPath[$inputOffset] = '/';
 701                 } elseif ( $prefixLengthThree == '/./' ) {
 702                         # Step B, replace leading "/./" with "/"
 703                         $inputOffset += 2;
 704                 } elseif ( $prefixLengthThree == '/..' && ( $inputOffset + 3 == $inputLength ) ) {
 705                         # Step C, replace leading "/..$" with "/" and
 706                         # remove last path component in output
 707                         $inputOffset += 2;
 708                         $urlPath[$inputOffset] = '/';
 709                         $trimOutput = true;
 710                 } elseif ( $prefixLengthFour == '/../' ) {
 711                         # Step C, replace leading "/../" with "/" and
 712                         # remove last path component in output
 713                         $inputOffset += 3;
 714                         $trimOutput = true;
 715                 } elseif ( ( $prefixLengthOne == '.' ) && ( $inputOffset + 1 == $inputLength ) ) {
 716                         # Step D, remove "^.$"
 717                         $inputOffset += 1;
 718                 } elseif ( ( $prefixLengthTwo == '..' ) && ( $inputOffset + 2 == $inputLength ) ) {
 719                         # Step D, remove "^..$"
 720                         $inputOffset += 2;
 721                 } else {
 722                         # Step E, move leading path segment to output
 723                         if ( $prefixLengthOne == '/' ) {
 724                                 $slashPos = strpos( $urlPath, '/', $inputOffset + 1 );
 725                         } else {
 726                                 $slashPos = strpos( $urlPath, '/', $inputOffset );
 727                         }
 728                         if ( $slashPos === false ) {
 729                                 $output .= substr( $urlPath, $inputOffset );
 730                                 $inputOffset = $inputLength;
 731                         } else {
 732                                 $output .= substr( $urlPath, $inputOffset, $slashPos - $inputOffset );
 733                                 $inputOffset += $slashPos - $inputOffset;
 734                         }
 735                 }
 736
 737                 if ( $trimOutput ) {
 738                         $slashPos = strrpos( $output, '/' );
 739                         if ( $slashPos === false ) {
 740                                 $output = '';
 741                         } else {
 742                                 $output = substr( $output, 0, $slashPos );
 743                         }
 744                 }
 745         }
 746
 747         return $output;
 748 }
 749
 750 /**
 751  * Returns a regular expression of url protocols
 752  *
 753  * @param bool $includeProtocolRelative If false, remove '//' from the returned protocol list.
 754  *        DO NOT USE this directly, use wfUrlProtocolsWithoutProtRel() instead
 755  * @return string
 756  */
 757 function wfUrlProtocols( $includeProtocolRelative = true ) {
 758         global $wgUrlProtocols;
 759
 760         // Cache return values separately based on $includeProtocolRelative
 761         static $withProtRel = null, $withoutProtRel = null;
 762         $cachedValue = $includeProtocolRelative ? $withProtRel : $withoutProtRel;
 763         if ( !is_null( $cachedValue ) ) {
 764                 return $cachedValue;
 765         }
 766
 767         // Support old-style $wgUrlProtocols strings, for backwards compatibility
 768         // with LocalSettings files from 1.5
 769         if ( is_array( $wgUrlProtocols ) ) {
 770                 $protocols = [];
 771                 foreach ( $wgUrlProtocols as $protocol ) {
 772                         // Filter out '//' if !$includeProtocolRelative
 773                         if ( $includeProtocolRelative || $protocol !== '//' ) {
 774                                 $protocols[] = preg_quote( $protocol, '/' );
 775                         }
 776                 }
 777
 778                 $retval = implode( '|', $protocols );
 779         } else {
 780                 // Ignore $includeProtocolRelative in this case
 781                 // This case exists for pre-1.6 compatibility, and we can safely assume
 782                 // that '//' won't appear in a pre-1.6 config because protocol-relative
 783                 // URLs weren't supported until 1.18
 784                 $retval = $wgUrlProtocols;
 785         }
 786
 787         // Cache return value
 788         if ( $includeProtocolRelative ) {
 789                 $withProtRel = $retval;
 790         } else {
 791                 $withoutProtRel = $retval;
 792         }
 793         return $retval;
 794 }
 795
 796 /**
 797  * Like wfUrlProtocols(), but excludes '//' from the protocol list. Use this if
 798  * you need a regex that matches all URL protocols but does not match protocol-
 799  * relative URLs
 800  * @return string
 801  */
 802 function wfUrlProtocolsWithoutProtRel() {
 803         return wfUrlProtocols( false );
 804 }
 805
 806 /**
 807  * parse_url() work-alike, but non-broken.  Differences:
 808  *
 809  * 1) Does not raise warnings on bad URLs (just returns false).
 810  * 2) Handles protocols that don't use :// (e.g., mailto: and news:, as well as
 811  *    protocol-relative URLs) correctly.
 812  * 3) Adds a "delimiter" element to the array, either '://', ':' or '//' (see (2)).
 813  *
 814  * @param string $url A URL to parse
 815  * @return string[]|bool Bits of the URL in an associative array, per PHP docs, false on failure
 816  */
 817 function wfParseUrl( $url ) {
 818         global $wgUrlProtocols; // Allow all protocols defined in DefaultSettings/LocalSettings.php
 819
 820         // Protocol-relative URLs are handled really badly by parse_url(). It's so
 821         // bad that the easiest way to handle them is to just prepend 'http:' and
 822         // strip the protocol out later.
 823         $wasRelative = substr( $url, 0, 2 ) == '//';
 824         if ( $wasRelative ) {
 825                 $url = "http:$url";
 826         }
 827         MediaWiki\suppressWarnings();
 828         $bits = parse_url( $url );
 829         MediaWiki\restoreWarnings();
 830         // parse_url() returns an array without scheme for some invalid URLs, e.g.
 831         // parse_url("%0Ahttp://example.com") == [ 'host' => '%0Ahttp', 'path' => 'example.com' ]
 832         if ( !$bits || !isset( $bits['scheme'] ) ) {
 833                 return false;
 834         }
 835
 836         // parse_url() incorrectly handles schemes case-sensitively. Convert it to lowercase.
 837         $bits['scheme'] = strtolower( $bits['scheme'] );
 838
 839         // most of the protocols are followed by ://, but mailto: and sometimes news: not, check for it
 840         if ( in_array( $bits['scheme'] . '://', $wgUrlProtocols ) ) {
 841                 $bits['delimiter'] = '://';
 842         } elseif ( in_array( $bits['scheme'] . ':', $wgUrlProtocols ) ) {
 843                 $bits['delimiter'] = ':';
 844                 // parse_url detects for news: and mailto: the host part of an url as path
 845                 // We have to correct this wrong detection
 846                 if ( isset( $bits['path'] ) ) {
 847                         $bits['host'] = $bits['path'];
 848                         $bits['path'] = '';
 849                 }
 850         } else {
 851                 return false;
 852         }
 853
 854         /* Provide an empty host for eg. file:/// urls (see T30627) */
 855         if ( !isset( $bits['host'] ) ) {
 856                 $bits['host'] = '';
 857
 858                 // See T47069
 859                 if ( isset( $bits['path'] ) ) {
 860                         /* parse_url loses the third / for file:///c:/ urls (but not on variants) */
 861                         if ( substr( $bits['path'], 0, 1 ) !== '/' ) {
 862                                 $bits['path'] = '/' . $bits['path'];
 863                         }
 864                 } else {
 865                         $bits['path'] = '';
 866                 }
 867         }
 868
 869         // If the URL was protocol-relative, fix scheme and delimiter
 870         if ( $wasRelative ) {
 871                 $bits['scheme'] = '';
 872                 $bits['delimiter'] = '//';
 873         }
 874         return $bits;
 875 }
 876
 877 /**
 878  * Take a URL, make sure it's expanded to fully qualified, and replace any
 879  * encoded non-ASCII Unicode characters with their UTF-8 original forms
 880  * for more compact display and legibility for local audiences.
 881  *
 882  * @todo handle punycode domains too
 883  *
 884  * @param string $url
 885  * @return string
 886  */
 887 function wfExpandIRI( $url ) {
 888         return preg_replace_callback(
 889                 '/((?:%[89A-F][0-9A-F])+)/i',
 890                 'wfExpandIRI_callback',
 891                 wfExpandUrl( $url )
 892         );
 893 }
 894
 895 /**
 896  * Private callback for wfExpandIRI
 897  * @param array $matches
 898  * @return string
 899  */
 900 function wfExpandIRI_callback( $matches ) {
 901         return urldecode( $matches[1] );
 902 }
 903
 904 /**
 905  * Make URL indexes, appropriate for the el_index field of externallinks.
 906  *
 907  * @param string $url
 908  * @return array
 909  */
 910 function wfMakeUrlIndexes( $url ) {
 911         $bits = wfParseUrl( $url );
 912
 913         // Reverse the labels in the hostname, convert to lower case
 914         // For emails reverse domainpart only
 915         if ( $bits['scheme'] == 'mailto' ) {
 916                 $mailparts = explode( '@', $bits['host'], 2 );
 917                 if ( count( $mailparts ) === 2 ) {
 918                         $domainpart = strtolower( implode( '.', array_reverse( explode( '.', $mailparts[1] ) ) ) );
 919                 } else {
 920                         // No domain specified, don't mangle it
 921                         $domainpart = '';
 922                 }
 923                 $reversedHost = $domainpart . '@' . $mailparts[0];
 924         } else {
 925                 $reversedHost = strtolower( implode( '.', array_reverse( explode( '.', $bits['host'] ) ) ) );
 926         }
 927         // Add an extra dot to the end
 928         // Why? Is it in wrong place in mailto links?
 929         if ( substr( $reversedHost, -1, 1 ) !== '.' ) {
 930                 $reversedHost .= '.';
 931         }
 932         // Reconstruct the pseudo-URL
 933         $prot = $bits['scheme'];
 934         $index = $prot . $bits['delimiter'] . $reversedHost;
 935         // Leave out user and password. Add the port, path, query and fragment
 936         if ( isset( $bits['port'] ) ) {
 937                 $index .= ':' . $bits['port'];
 938         }
 939         if ( isset( $bits['path'] ) ) {
 940                 $index .= $bits['path'];
 941         } else {
 942                 $index .= '/';
 943         }
 944         if ( isset( $bits['query'] ) ) {
 945                 $index .= '?' . $bits['query'];
 946         }
 947         if ( isset( $bits['fragment'] ) ) {
 948                 $index .= '#' . $bits['fragment'];
 949         }
 950
 951         if ( $prot == '' ) {
 952                 return [ "http:$index", "https:$index" ];
 953         } else {
 954                 return [ $index ];
 955         }
 956 }
 957
 958 /**
 959  * Check whether a given URL has a domain that occurs in a given set of domains
 960  * @param string $url URL
 961  * @param array $domains Array of domains (strings)
 962  * @return bool True if the host part of $url ends in one of the strings in $domains
 963  */
 964 function wfMatchesDomainList( $url, $domains ) {
 965         $bits = wfParseUrl( $url );
 966         if ( is_array( $bits ) && isset( $bits['host'] ) ) {
 967                 $host = '.' . $bits['host'];
 968                 foreach ( (array)$domains as $domain ) {
 969                         $domain = '.' . $domain;
 970                         if ( substr( $host, -strlen( $domain ) ) === $domain ) {
 971                                 return true;
 972                         }
 973                 }
 974         }
 975         return false;
 976 }
 977
 978 /**
 979  * Sends a line to the debug log if enabled or, optionally, to a comment in output.
 980  * In normal operation this is a NOP.
 981  *
 982  * Controlling globals:
 983  * $wgDebugLogFile - points to the log file
 984  * $wgDebugRawPage - if false, 'action=raw' hits will not result in debug output.
 985  * $wgDebugComments - if on, some debug items may appear in comments in the HTML output.
 986  *
 987  * @since 1.25 support for additional context data
 988  *
 989  * @param string $text
 990  * @param string|bool $dest Destination of the message:
 991  *     - 'all': both to the log and HTML (debug toolbar or HTML comments)
 992  *     - 'private': excluded from HTML output
 993  *   For backward compatibility, it can also take a boolean:
 994  *     - true: same as 'all'
 995  *     - false: same as 'private'
 996  * @param array $context Additional logging context data
 997  */
 998 function wfDebug( $text, $dest = 'all', array $context = [] ) {
 999         global $wgDebugRawPage, $wgDebugLogPrefix;
1000         global $wgDebugTimestamps, $wgRequestTime;
1001
1002         if ( !$wgDebugRawPage && wfIsDebugRawPage() ) {
1003                 return;
1004         }
1005
1006         $text = trim( $text );
1007
1008         if ( $wgDebugTimestamps ) {
1009                 $context['seconds_elapsed'] = sprintf(
1010                         '%6.4f',
1011                         microtime( true ) - $wgRequestTime
1012                 );
1013                 $context['memory_used'] = sprintf(
1014                         '%5.1fM',
1015                         ( memory_get_usage( true ) / ( 1024 * 1024 ) )
1016                 );
1017         }
1018
1019         if ( $wgDebugLogPrefix !== '' ) {
1020                 $context['prefix'] = $wgDebugLogPrefix;
1021         }
1022         $context['private'] = ( $dest === false || $dest === 'private' );
1023
1024         $logger = LoggerFactory::getInstance( 'wfDebug' );
1025         $logger->debug( $text, $context );
1026 }
1027
1028 /**
1029  * Returns true if debug logging should be suppressed if $wgDebugRawPage = false
1030  * @return bool
1031  */
1032 function wfIsDebugRawPage() {
1033         static $cache;
1034         if ( $cache !== null ) {
1035                 return $cache;
1036         }
1037         # Check for raw action using $_GET not $wgRequest, since the latter might not be initialised yet
1038         if ( ( isset( $_GET['action'] ) && $_GET['action'] == 'raw' )
1039                 || (
1040                         isset( $_SERVER['SCRIPT_NAME'] )
1041                         && substr( $_SERVER['SCRIPT_NAME'], -8 ) == 'load.php'
1042                 )
1043         ) {
1044                 $cache = true;
1045         } else {
1046                 $cache = false;
1047         }
1048         return $cache;
1049 }
1050
1051 /**
1052  * Send a line giving PHP memory usage.
1053  *
1054  * @param bool $exact Print exact byte values instead of kibibytes (default: false)
1055  */
1056 function wfDebugMem( $exact = false ) {
1057         $mem = memory_get_usage();
1058         if ( !$exact ) {
1059                 $mem = floor( $mem / 1024 ) . ' KiB';
1060         } else {
1061                 $mem .= ' B';
1062         }
1063         wfDebug( "Memory usage: $mem\n" );
1064 }
1065
1066 /**
1067  * Send a line to a supplementary debug log file, if configured, or main debug
1068  * log if not.
1069  *
1070  * To configure a supplementary log file, set $wgDebugLogGroups[$logGroup] to
1071  * a string filename or an associative array mapping 'destination' to the
1072  * desired filename. The associative array may also contain a 'sample' key
1073  * with an integer value, specifying a sampling factor. Sampled log events
1074  * will be emitted with a 1 in N random chance.
1075  *
1076  * @since 1.23 support for sampling log messages via $wgDebugLogGroups.
1077  * @since 1.25 support for additional context data
1078  * @since 1.25 sample behavior dependent on configured $wgMWLoggerDefaultSpi
1079  *
1080  * @param string $logGroup
1081  * @param string $text
1082  * @param string|bool $dest Destination of the message:
1083  *     - 'all': both to the log and HTML (debug toolbar or HTML comments)
1084  *     - 'private': only to the specific log if set in $wgDebugLogGroups and
1085  *       discarded otherwise
1086  *   For backward compatibility, it can also take a boolean:
1087  *     - true: same as 'all'
1088  *     - false: same as 'private'
1089  * @param array $context Additional logging context data
1090  */
1091 function wfDebugLog(
1092         $logGroup, $text, $dest = 'all', array $context = []
1093 ) {
1094         $text = trim( $text );
1095
1096         $logger = LoggerFactory::getInstance( $logGroup );
1097         $context['private'] = ( $dest === false || $dest === 'private' );
1098         $logger->info( $text, $context );
1099 }
1100
1101 /**
1102  * Log for database errors
1103  *
1104  * @since 1.25 support for additional context data
1105  *
1106  * @param string $text Database error message.
1107  * @param array $context Additional logging context data
1108  */
1109 function wfLogDBError( $text, array $context = [] ) {
1110         $logger = LoggerFactory::getInstance( 'wfLogDBError' );
1111         $logger->error( trim( $text ), $context );
1112 }
1113
1114 /**
1115  * Throws a warning that $function is deprecated
1116  *
1117  * @param string $function
1118  * @param string|bool $version Version of MediaWiki that the function
1119  *    was deprecated in (Added in 1.19).
1120  * @param string|bool $component Added in 1.19.
1121  * @param int $callerOffset How far up the call stack is the original
1122  *    caller. 2 = function that called the function that called
1123  *    wfDeprecated (Added in 1.20)
1124  *
1125  * @return null
1126  */
1127 function wfDeprecated( $function, $version = false, $component = false, $callerOffset = 2 ) {
1128         MWDebug::deprecated( $function, $version, $component, $callerOffset + 1 );
1129 }
1130
1131 /**
1132  * Send a warning either to the debug log or in a PHP error depending on
1133  * $wgDevelopmentWarnings. To log warnings in production, use wfLogWarning() instead.
1134  *
1135  * @param string $msg Message to send
1136  * @param int $callerOffset Number of items to go back in the backtrace to
1137  *        find the correct caller (1 = function calling wfWarn, ...)
1138  * @param int $level PHP error level; defaults to E_USER_NOTICE;
1139  *        only used when $wgDevelopmentWarnings is true
1140  */
1141 function wfWarn( $msg, $callerOffset = 1, $level = E_USER_NOTICE ) {
1142         MWDebug::warning( $msg, $callerOffset + 1, $level, 'auto' );
1143 }
1144
1145 /**
1146  * Send a warning as a PHP error and the debug log. This is intended for logging
1147  * warnings in production. For logging development warnings, use WfWarn instead.
1148  *
1149  * @param string $msg Message to send
1150  * @param int $callerOffset Number of items to go back in the backtrace to
1151  *        find the correct caller (1 = function calling wfLogWarning, ...)
1152  * @param int $level PHP error level; defaults to E_USER_WARNING
1153  */
1154 function wfLogWarning( $msg, $callerOffset = 1, $level = E_USER_WARNING ) {
1155         MWDebug::warning( $msg, $callerOffset + 1, $level, 'production' );
1156 }
1157
1158 /**
1159  * Log to a file without getting "file size exceeded" signals.
1160  *
1161  * Can also log to TCP or UDP with the syntax udp://host:port/prefix. This will
1162  * send lines to the specified port, prefixed by the specified prefix and a space.
1163  * @since 1.25 support for additional context data
1164  *
1165  * @param string $text
1166  * @param string $file Filename
1167  * @param array $context Additional logging context data
1168  * @throws MWException
1169  * @deprecated since 1.25 Use \MediaWiki\Logger\LegacyLogger::emit or UDPTransport
1170  */
1171 function wfErrorLog( $text, $file, array $context = [] ) {
1172         wfDeprecated( __METHOD__, '1.25' );
1173         $logger = LoggerFactory::getInstance( 'wfErrorLog' );
1174         $context['destination'] = $file;
1175         $logger->info( trim( $text ), $context );
1176 }
1177
1178 /**
1179  * @todo document
1180  */
1181 function wfLogProfilingData() {
1182         global $wgDebugLogGroups, $wgDebugRawPage;
1183
1184         $context = RequestContext::getMain();
1185         $request = $context->getRequest();
1186
1187         $profiler = Profiler::instance();
1188         $profiler->setContext( $context );
1189         $profiler->logData();
1190
1191         $config = $context->getConfig();
1192         if ( $config->get( 'StatsdServer' ) ) {
1193                 try {
1194                         $statsdServer = explode( ':', $config->get( 'StatsdServer' ) );
1195                         $statsdHost = $statsdServer[0];
1196                         $statsdPort = isset( $statsdServer[1] ) ? $statsdServer[1] : 8125;
1197                         $statsdSender = new SocketSender( $statsdHost, $statsdPort );
1198                         $statsdClient = new SamplingStatsdClient( $statsdSender, true, false );
1199                         $statsdClient->setSamplingRates( $config->get( 'StatsdSamplingRates' ) );
1200                         $statsdClient->send( $context->getStats()->getBuffer() );
1201                 } catch ( Exception $ex ) {
1202                         MWExceptionHandler::logException( $ex );
1203                 }
1204         }
1205
1206         # Profiling must actually be enabled...
1207         if ( $profiler instanceof ProfilerStub ) {
1208                 return;
1209         }
1210
1211         if ( isset( $wgDebugLogGroups['profileoutput'] )
1212                 && $wgDebugLogGroups['profileoutput'] === false
1213         ) {
1214                 // Explicitly disabled
1215                 return;
1216         }
1217         if ( !$wgDebugRawPage && wfIsDebugRawPage() ) {
1218                 return;
1219         }
1220
1221         $ctx = [ 'elapsed' => $request->getElapsedTime() ];
1222         if ( !empty( $_SERVER['HTTP_X_FORWARDED_FOR'] ) ) {
1223                 $ctx['forwarded_for'] = $_SERVER['HTTP_X_FORWARDED_FOR'];
1224         }
1225         if ( !empty( $_SERVER['HTTP_CLIENT_IP'] ) ) {
1226                 $ctx['client_ip'] = $_SERVER['HTTP_CLIENT_IP'];
1227         }
1228         if ( !empty( $_SERVER['HTTP_FROM'] ) ) {
1229                 $ctx['from'] = $_SERVER['HTTP_FROM'];
1230         }
1231         if ( isset( $ctx['forwarded_for'] ) ||
1232                 isset( $ctx['client_ip'] ) ||
1233                 isset( $ctx['from'] ) ) {
1234                 $ctx['proxy'] = $_SERVER['REMOTE_ADDR'];
1235         }
1236
1237         // Don't load $wgUser at this late stage just for statistics purposes
1238         // @todo FIXME: We can detect some anons even if it is not loaded.
1239         // See User::getId()
1240         $user = $context->getUser();
1241         $ctx['anon'] = $user->isItemLoaded( 'id' ) && $user->isAnon();
1242
1243         // Command line script uses a FauxRequest object which does not have
1244         // any knowledge about an URL and throw an exception instead.
1245         try {
1246                 $ctx['url'] = urldecode( $request->getRequestURL() );
1247         } catch ( Exception $ignored ) {
1248                 // no-op
1249         }
1250
1251         $ctx['output'] = $profiler->getOutput();
1252
1253         $log = LoggerFactory::getInstance( 'profileoutput' );
1254         $log->info( "Elapsed: {elapsed}; URL: <{url}>\n{output}", $ctx );
1255 }
1256
1257 /**
1258  * Increment a statistics counter
1259  *
1260  * @param string $key
1261  * @param int $count
1262  * @return void
1263  */
1264 function wfIncrStats( $key, $count = 1 ) {
1265         $stats = RequestContext::getMain()->getStats();
1266         $stats->updateCount( $key, $count );
1267 }
1268
1269 /**
1270  * Check whether the wiki is in read-only mode.
1271  *
1272  * @return bool
1273  */
1274 function wfReadOnly() {
1275         return wfReadOnlyReason() !== false;
1276 }
1277
1278 /**
1279  * Check if the site is in read-only mode and return the message if so
1280  *
1281  * This checks wfConfiguredReadOnlyReason() and the main load balancer
1282  * for replica DB lag. This may result in DB connection being made.
1283  *
1284  * @return string|bool String when in read-only mode; false otherwise
1285  */
1286 function wfReadOnlyReason() {
1287         $readOnly = wfConfiguredReadOnlyReason();
1288         if ( $readOnly !== false ) {
1289                 return $readOnly;
1290         }
1291
1292         static $lbReadOnly = null;
1293         if ( $lbReadOnly === null ) {
1294                 // Callers use this method to be aware that data presented to a user
1295                 // may be very stale and thus allowing submissions can be problematic.
1296                 $lbReadOnly = wfGetLB()->getReadOnlyReason();
1297         }
1298
1299         return $lbReadOnly;
1300 }
1301
1302 /**
1303  * Get the value of $wgReadOnly or the contents of $wgReadOnlyFile.
1304  *
1305  * @return string|bool String when in read-only mode; false otherwise
1306  * @since 1.27
1307  */
1308 function wfConfiguredReadOnlyReason() {
1309         global $wgReadOnly, $wgReadOnlyFile;
1310
1311         if ( $wgReadOnly === null ) {
1312                 // Set $wgReadOnly for faster access next time
1313                 if ( is_file( $wgReadOnlyFile ) && filesize( $wgReadOnlyFile ) > 0 ) {
1314                         $wgReadOnly = file_get_contents( $wgReadOnlyFile );
1315                 } else {
1316                         $wgReadOnly = false;
1317                 }
1318         }
1319
1320         return $wgReadOnly;
1321 }
1322
1323 /**
1324  * Return a Language object from $langcode
1325  *
1326  * @param Language|string|bool $langcode Either:
1327  *                  - a Language object
1328  *                  - code of the language to get the message for, if it is
1329  *                    a valid code create a language for that language, if
1330  *                    it is a string but not a valid code then make a basic
1331  *                    language object
1332  *                  - a boolean: if it's false then use the global object for
1333  *                    the current user's language (as a fallback for the old parameter
1334  *                    functionality), or if it is true then use global object
1335  *                    for the wiki's content language.
1336  * @return Language
1337  */
1338 function wfGetLangObj( $langcode = false ) {
1339         # Identify which language to get or create a language object for.
1340         # Using is_object here due to Stub objects.
1341         if ( is_object( $langcode ) ) {
1342                 # Great, we already have the object (hopefully)!
1343                 return $langcode;
1344         }
1345
1346         global $wgContLang, $wgLanguageCode;
1347         if ( $langcode === true || $langcode === $wgLanguageCode ) {
1348                 # $langcode is the language code of the wikis content language object.
1349                 # or it is a boolean and value is true
1350                 return $wgContLang;
1351         }
1352
1353         global $wgLang;
1354         if ( $langcode === false || $langcode === $wgLang->getCode() ) {
1355                 # $langcode is the language code of user language object.
1356                 # or it was a boolean and value is false
1357                 return $wgLang;
1358         }
1359
1360         $validCodes = array_keys( Language::fetchLanguageNames() );
1361         if ( in_array( $langcode, $validCodes ) ) {
1362                 # $langcode corresponds to a valid language.
1363                 return Language::factory( $langcode );
1364         }
1365
1366         # $langcode is a string, but not a valid language code; use content language.
1367         wfDebug( "Invalid language code passed to wfGetLangObj, falling back to content language.\n" );
1368         return $wgContLang;
1369 }
1370
1371 /**
1372  * This is the function for getting translated interface messages.
1373  *
1374  * @see Message class for documentation how to use them.
1375  * @see https://www.mediawiki.org/wiki/Manual:Messages_API
1376  *
1377  * This function replaces all old wfMsg* functions.
1378  *
1379  * @param string|string[]|MessageSpecifier $key Message key, or array of keys, or a MessageSpecifier
1380  * @param mixed $params,... Normal message parameters
1381  * @return Message
1382  *
1383  * @since 1.17
1384  *
1385  * @see Message::__construct
1386  */
1387 function wfMessage( $key /*...*/ ) {
1388         $params = func_get_args();
1389         array_shift( $params );
1390         if ( isset( $params[0] ) && is_array( $params[0] ) ) {
1391                 $params = $params[0];
1392         }
1393         return new Message( $key, $params );
1394 }
1395
1396 /**
1397  * This function accepts multiple message keys and returns a message instance
1398  * for the first message which is non-empty. If all messages are empty then an
1399  * instance of the first message key is returned.
1400  *
1401  * @param string|string[] $keys,... Message keys
1402  * @return Message
1403  *
1404  * @since 1.18
1405  *
1406  * @see Message::newFallbackSequence
1407  */
1408 function wfMessageFallback( /*...*/ ) {
1409         $args = func_get_args();
1410         return call_user_func_array( 'Message::newFallbackSequence', $args );
1411 }
1412
1413 /**
1414  * Replace message parameter keys on the given formatted output.
1415  *
1416  * @param string $message
1417  * @param array $args
1418  * @return string
1419  * @private
1420  */
1421 function wfMsgReplaceArgs( $message, $args ) {
1422         # Fix windows line-endings
1423         # Some messages are split with explode("\n", $msg)
1424         $message = str_replace( "\r", '', $message );
1425
1426         // Replace arguments
1427         if ( is_array( $args ) && $args ) {
1428                 if ( is_array( $args[0] ) ) {
1429                         $args = array_values( $args[0] );
1430                 }
1431                 $replacementKeys = [];
1432                 foreach ( $args as $n => $param ) {
1433                         $replacementKeys['$' . ( $n + 1 )] = $param;
1434                 }
1435                 $message = strtr( $message, $replacementKeys );
1436         }
1437
1438         return $message;
1439 }
1440
1441 /**
1442  * Fetch server name for use in error reporting etc.
1443  * Use real server name if available, so we know which machine
1444  * in a server farm generated the current page.
1445  *
1446  * @return string
1447  */
1448 function wfHostname() {
1449         static $host;
1450         if ( is_null( $host ) ) {
1451
1452                 # Hostname overriding
1453                 global $wgOverrideHostname;
1454                 if ( $wgOverrideHostname !== false ) {
1455                         # Set static and skip any detection
1456                         $host = $wgOverrideHostname;
1457                         return $host;
1458                 }
1459
1460                 if ( function_exists( 'posix_uname' ) ) {
1461                         // This function not present on Windows
1462                         $uname = posix_uname();
1463                 } else {
1464                         $uname = false;
1465                 }
1466                 if ( is_array( $uname ) && isset( $uname['nodename'] ) ) {
1467                         $host = $uname['nodename'];
1468                 } elseif ( getenv( 'COMPUTERNAME' ) ) {
1469                         # Windows computer name
1470                         $host = getenv( 'COMPUTERNAME' );
1471                 } else {
1472                         # This may be a virtual server.
1473                         $host = $_SERVER['SERVER_NAME'];
1474                 }
1475         }
1476         return $host;
1477 }
1478
1479 /**
1480  * Returns a script tag that stores the amount of time it took MediaWiki to
1481  * handle the request in milliseconds as 'wgBackendResponseTime'.
1482  *
1483  * If $wgShowHostnames is true, the script will also set 'wgHostname' to the
1484  * hostname of the server handling the request.
1485  *
1486  * @return string
1487  */
1488 function wfReportTime() {
1489         global $wgRequestTime, $wgShowHostnames;
1490
1491         $responseTime = round( ( microtime( true ) - $wgRequestTime ) * 1000 );
1492         $reportVars = [ 'wgBackendResponseTime' => $responseTime ];
1493         if ( $wgShowHostnames ) {
1494                 $reportVars['wgHostname'] = wfHostname();
1495         }
1496         return Skin::makeVariablesScript( $reportVars );
1497 }
1498
1499 /**
1500  * Safety wrapper for debug_backtrace().
1501  *
1502  * Will return an empty array if debug_backtrace is disabled, otherwise
1503  * the output from debug_backtrace() (trimmed).
1504  *
1505  * @param int $limit This parameter can be used to limit the number of stack frames returned
1506  *
1507  * @return array Array of backtrace information
1508  */
1509 function wfDebugBacktrace( $limit = 0 ) {
1510         static $disabled = null;
1511
1512         if ( is_null( $disabled ) ) {
1513                 $disabled = !function_exists( 'debug_backtrace' );
1514                 if ( $disabled ) {
1515                         wfDebug( "debug_backtrace() is disabled\n" );
1516                 }
1517         }
1518         if ( $disabled ) {
1519                 return [];
1520         }
1521
1522         if ( $limit ) {
1523                 return array_slice( debug_backtrace( DEBUG_BACKTRACE_PROVIDE_OBJECT, $limit + 1 ), 1 );
1524         } else {
1525                 return array_slice( debug_backtrace(), 1 );
1526         }
1527 }
1528
1529 /**
1530  * Get a debug backtrace as a string
1531  *
1532  * @param bool|null $raw If true, the return value is plain text. If false, HTML.
1533  *   Defaults to $wgCommandLineMode if unset.
1534  * @return string
1535  * @since 1.25 Supports $raw parameter.
1536  */
1537 function wfBacktrace( $raw = null ) {
1538         global $wgCommandLineMode;
1539
1540         if ( $raw === null ) {
1541                 $raw = $wgCommandLineMode;
1542         }
1543
1544         if ( $raw ) {
1545                 $frameFormat = "%s line %s calls %s()\n";
1546                 $traceFormat = "%s";
1547         } else {
1548                 $frameFormat = "<li>%s line %s calls %s()</li>\n";
1549                 $traceFormat = "<ul>\n%s</ul>\n";
1550         }
1551
1552         $frames = array_map( function ( $frame ) use ( $frameFormat ) {
1553                 $file = !empty( $frame['file'] ) ? basename( $frame['file'] ) : '-';
1554                 $line = isset( $frame['line'] ) ? $frame['line'] : '-';
1555                 $call = $frame['function'];
1556                 if ( !empty( $frame['class'] ) ) {
1557                         $call = $frame['class'] . $frame['type'] . $call;
1558                 }
1559                 return sprintf( $frameFormat, $file, $line, $call );
1560         }, wfDebugBacktrace() );
1561
1562         return sprintf( $traceFormat, implode( '', $frames ) );
1563 }
1564
1565 /**
1566  * Get the name of the function which called this function
1567  * wfGetCaller( 1 ) is the function with the wfGetCaller() call (ie. __FUNCTION__)
1568  * wfGetCaller( 2 ) [default] is the caller of the function running wfGetCaller()
1569  * wfGetCaller( 3 ) is the parent of that.
1570  *
1571  * @param int $level
1572  * @return string
1573  */
1574 function wfGetCaller( $level = 2 ) {
1575         $backtrace = wfDebugBacktrace( $level + 1 );
1576         if ( isset( $backtrace[$level] ) ) {
1577                 return wfFormatStackFrame( $backtrace[$level] );
1578         } else {
1579                 return 'unknown';
1580         }
1581 }
1582
1583 /**
1584  * Return a string consisting of callers in the stack. Useful sometimes
1585  * for profiling specific points.
1586  *
1587  * @param int $limit The maximum depth of the stack frame to return, or false for the entire stack.
1588  * @return string
1589  */
1590 function wfGetAllCallers( $limit = 3 ) {
1591         $trace = array_reverse( wfDebugBacktrace() );
1592         if ( !$limit || $limit > count( $trace ) - 1 ) {
1593                 $limit = count( $trace ) - 1;
1594         }
1595         $trace = array_slice( $trace, -$limit - 1, $limit );
1596         return implode( '/', array_map( 'wfFormatStackFrame', $trace ) );
1597 }
1598
1599 /**
1600  * Return a string representation of frame
1601  *
1602  * @param array $frame
1603  * @return string
1604  */
1605 function wfFormatStackFrame( $frame ) {
1606         if ( !isset( $frame['function'] ) ) {
1607                 return 'NO_FUNCTION_GIVEN';
1608         }
1609         return isset( $frame['class'] ) && isset( $frame['type'] ) ?
1610                 $frame['class'] . $frame['type'] . $frame['function'] :
1611                 $frame['function'];
1612 }
1613
1614 /* Some generic result counters, pulled out of SearchEngine */
1615
1616 /**
1617  * @todo document
1618  *
1619  * @param int $offset
1620  * @param int $limit
1621  * @return string
1622  */
1623 function wfShowingResults( $offset, $limit ) {
1624         return wfMessage( 'showingresults' )->numParams( $limit, $offset + 1 )->parse();
1625 }
1626
1627 /**
1628  * Whether the client accept gzip encoding
1629  *
1630  * Uses the Accept-Encoding header to check if the client supports gzip encoding.
1631  * Use this when considering to send a gzip-encoded response to the client.
1632  *
1633  * @param bool $force Forces another check even if we already have a cached result.
1634  * @return bool
1635  */
1636 function wfClientAcceptsGzip( $force = false ) {
1637         static $result = null;
1638         if ( $result === null || $force ) {
1639                 $result = false;
1640                 if ( isset( $_SERVER['HTTP_ACCEPT_ENCODING'] ) ) {
1641                         # @todo FIXME: We may want to blacklist some broken browsers
1642                         $m = [];
1643                         if ( preg_match(
1644                                         '/\bgzip(?:;(q)=([0-9]+(?:\.[0-9]+)))?\b/',
1645                                         $_SERVER['HTTP_ACCEPT_ENCODING'],
1646                                         $m
1647                                 )
1648                         ) {
1649                                 if ( isset( $m[2] ) && ( $m[1] == 'q' ) && ( $m[2] == 0 ) ) {
1650                                         $result = false;
1651                                         return $result;
1652                                 }
1653                                 wfDebug( "wfClientAcceptsGzip: client accepts gzip.\n" );
1654                                 $result = true;
1655                         }
1656                 }
1657         }
1658         return $result;
1659 }
1660
1661 /**
1662  * Escapes the given text so that it may be output using addWikiText()
1663  * without any linking, formatting, etc. making its way through. This
1664  * is achieved by substituting certain characters with HTML entities.
1665  * As required by the callers, "<nowiki>" is not used.
1666  *
1667  * @param string $text Text to be escaped
1668  * @return string
1669  */
1670 function wfEscapeWikiText( $text ) {
1671         global $wgEnableMagicLinks;
1672         static $repl = null, $repl2 = null;
1673         if ( $repl === null ) {
1674                 $repl = [
1675                         '"' => '&#34;', '&' => '&#38;', "'" => '&#39;', '<' => '&#60;',
1676                         '=' => '&#61;', '>' => '&#62;', '[' => '&#91;', ']' => '&#93;',
1677                         '{' => '&#123;', '|' => '&#124;', '}' => '&#125;', ';' => '&#59;',
1678                         "\n#" => "\n&#35;", "\r#" => "\r&#35;",
1679                         "\n*" => "\n&#42;", "\r*" => "\r&#42;",
1680                         "\n:" => "\n&#58;", "\r:" => "\r&#58;",
1681                         "\n " => "\n&#32;", "\r " => "\r&#32;",
1682                         "\n\n" => "\n&#10;", "\r\n" => "&#13;\n",
1683                         "\n\r" => "\n&#13;", "\r\r" => "\r&#13;",
1684                         "\n\t" => "\n&#9;", "\r\t" => "\r&#9;", // "\n\t\n" is treated like "\n\n"
1685                         "\n----" => "\n&#45;---", "\r----" => "\r&#45;---",
1686                         '__' => '_&#95;', '://' => '&#58;//',
1687                 ];
1688
1689                 $magicLinks = array_keys( array_filter( $wgEnableMagicLinks ) );
1690                 // We have to catch everything "\s" matches in PCRE
1691                 foreach ( $magicLinks as $magic ) {
1692                         $repl["$magic "] = "$magic&#32;";
1693                         $repl["$magic\t"] = "$magic&#9;";
1694                         $repl["$magic\r"] = "$magic&#13;";
1695                         $repl["$magic\n"] = "$magic&#10;";
1696                         $repl["$magic\f"] = "$magic&#12;";
1697                 }
1698
1699                 // And handle protocols that don't use "://"
1700                 global $wgUrlProtocols;
1701                 $repl2 = [];
1702                 foreach ( $wgUrlProtocols as $prot ) {
1703                         if ( substr( $prot, -1 ) === ':' ) {
1704                                 $repl2[] = preg_quote( substr( $prot, 0, -1 ), '/' );
1705                         }
1706                 }
1707                 $repl2 = $repl2 ? '/\b(' . implode( '|', $repl2 ) . '):/i' : '/^(?!)/';
1708         }
1709         $text = substr( strtr( "\n$text", $repl ), 1 );
1710         $text = preg_replace( $repl2, '$1&#58;', $text );
1711         return $text;
1712 }
1713
1714 /**
1715  * Sets dest to source and returns the original value of dest
1716  * If source is NULL, it just returns the value, it doesn't set the variable
1717  * If force is true, it will set the value even if source is NULL
1718  *
1719  * @param mixed $dest
1720  * @param mixed $source
1721  * @param bool $force
1722  * @return mixed
1723  */
1724 function wfSetVar( &$dest, $source, $force = false ) {
1725         $temp = $dest;
1726         if ( !is_null( $source ) || $force ) {
1727                 $dest = $source;
1728         }
1729         return $temp;
1730 }
1731
1732 /**
1733  * As for wfSetVar except setting a bit
1734  *
1735  * @param int $dest
1736  * @param int $bit
1737  * @param bool $state
1738  *
1739  * @return bool
1740  */
1741 function wfSetBit( &$dest, $bit, $state = true ) {
1742         $temp = (bool)( $dest & $bit );
1743         if ( !is_null( $state ) ) {
1744                 if ( $state ) {
1745                         $dest |= $bit;
1746                 } else {
1747                         $dest &= ~$bit;
1748                 }
1749         }
1750         return $temp;
1751 }
1752
1753 /**
1754  * A wrapper around the PHP function var_export().
1755  * Either print it or add it to the regular output ($wgOut).
1756  *
1757  * @param mixed $var A PHP variable to dump.
1758  */
1759 function wfVarDump( $var ) {
1760         global $wgOut;
1761         $s = str_replace( "\n", "<br />\n", var_export( $var, true ) . "\n" );
1762         if ( headers_sent() || !isset( $wgOut ) || !is_object( $wgOut ) ) {
1763                 print $s;
1764         } else {
1765                 $wgOut->addHTML( $s );
1766         }
1767 }
1768
1769 /**
1770  * Provide a simple HTTP error.
1771  *
1772  * @param int|string $code
1773  * @param string $label
1774  * @param string $desc
1775  */
1776 function wfHttpError( $code, $label, $desc ) {
1777         global $wgOut;
1778         HttpStatus::header( $code );
1779         if ( $wgOut ) {
1780                 $wgOut->disable();
1781                 $wgOut->sendCacheControl();
1782         }
1783
1784         header( 'Content-type: text/html; charset=utf-8' );
1785         print '<!DOCTYPE html>' .
1786                 '<html><head><title>' .
1787                 htmlspecialchars( $label ) .
1788                 '</title></head><body><h1>' .
1789                 htmlspecialchars( $label ) .
1790                 '</h1><p>' .
1791                 nl2br( htmlspecialchars( $desc ) ) .
1792                 "</p></body></html>\n";
1793 }
1794
1795 /**
1796  * Clear away any user-level output buffers, discarding contents.
1797  *
1798  * Suitable for 'starting afresh', for instance when streaming
1799  * relatively large amounts of data without buffering, or wanting to
1800  * output image files without ob_gzhandler's compression.
1801  *
1802  * The optional $resetGzipEncoding parameter controls suppression of
1803  * the Content-Encoding header sent by ob_gzhandler; by default it
1804  * is left. See comments for wfClearOutputBuffers() for why it would
1805  * be used.
1806  *
1807  * Note that some PHP configuration options may add output buffer
1808  * layers which cannot be removed; these are left in place.
1809  *
1810  * @param bool $resetGzipEncoding
1811  */
1812 function wfResetOutputBuffers( $resetGzipEncoding = true ) {
1813         if ( $resetGzipEncoding ) {
1814                 // Suppress Content-Encoding and Content-Length
1815                 // headers from 1.10+s wfOutputHandler
1816                 global $wgDisableOutputCompression;
1817                 $wgDisableOutputCompression = true;
1818         }
1819         while ( $status = ob_get_status() ) {
1820                 if ( isset( $status['flags'] ) ) {
1821                         $flags = PHP_OUTPUT_HANDLER_CLEANABLE | PHP_OUTPUT_HANDLER_REMOVABLE;
1822                         $deleteable = ( $status['flags'] & $flags ) === $flags;
1823                 } elseif ( isset( $status['del'] ) ) {
1824                         $deleteable = $status['del'];
1825                 } else {
1826                         // Guess that any PHP-internal setting can't be removed.
1827                         $deleteable = $status['type'] !== 0; /* PHP_OUTPUT_HANDLER_INTERNAL */
1828                 }
1829                 if ( !$deleteable ) {
1830                         // Give up, and hope the result doesn't break
1831                         // output behavior.
1832                         break;
1833                 }
1834                 if ( $status['name'] === 'MediaWikiTestCase::wfResetOutputBuffersBarrier' ) {
1835                         // Unit testing barrier to prevent this function from breaking PHPUnit.
1836                         break;
1837                 }
1838                 if ( !ob_end_clean() ) {
1839                         // Could not remove output buffer handler; abort now
1840                         // to avoid getting in some kind of infinite loop.
1841                         break;
1842                 }
1843                 if ( $resetGzipEncoding ) {
1844                         if ( $status['name'] == 'ob_gzhandler' ) {
1845                                 // Reset the 'Content-Encoding' field set by this handler
1846                                 // so we can start fresh.
1847                                 header_remove( 'Content-Encoding' );
1848                                 break;
1849                         }
1850                 }
1851         }
1852 }
1853
1854 /**
1855  * More legible than passing a 'false' parameter to wfResetOutputBuffers():
1856  *
1857  * Clear away output buffers, but keep the Content-Encoding header
1858  * produced by ob_gzhandler, if any.
1859  *
1860  * This should be used for HTTP 304 responses, where you need to
1861  * preserve the Content-Encoding header of the real result, but
1862  * also need to suppress the output of ob_gzhandler to keep to spec
1863  * and avoid breaking Firefox in rare cases where the headers and
1864  * body are broken over two packets.
1865  */
1866 function wfClearOutputBuffers() {
1867         wfResetOutputBuffers( false );
1868 }
1869
1870 /**
1871  * Converts an Accept-* header into an array mapping string values to quality
1872  * factors
1873  *
1874  * @param string $accept
1875  * @param string $def Default
1876  * @return float[] Associative array of string => float pairs
1877  */
1878 function wfAcceptToPrefs( $accept, $def = '*/*' ) {
1879         # No arg means accept anything (per HTTP spec)
1880         if ( !$accept ) {
1881                 return [ $def => 1.0 ];
1882         }
1883
1884         $prefs = [];
1885
1886         $parts = explode( ',', $accept );
1887
1888         foreach ( $parts as $part ) {
1889                 # @todo FIXME: Doesn't deal with params like 'text/html; level=1'
1890                 $values = explode( ';', trim( $part ) );
1891                 $match = [];
1892                 if ( count( $values ) == 1 ) {
1893                         $prefs[$values[0]] = 1.0;
1894                 } elseif ( preg_match( '/q\s*=\s*(\d*\.\d+)/', $values[1], $match ) ) {
1895                         $prefs[$values[0]] = floatval( $match[1] );
1896                 }
1897         }
1898
1899         return $prefs;
1900 }
1901
1902 /**
1903  * Checks if a given MIME type matches any of the keys in the given
1904  * array. Basic wildcards are accepted in the array keys.
1905  *
1906  * Returns the matching MIME type (or wildcard) if a match, otherwise
1907  * NULL if no match.
1908  *
1909  * @param string $type
1910  * @param array $avail
1911  * @return string
1912  * @private
1913  */
1914 function mimeTypeMatch( $type, $avail ) {
1915         if ( array_key_exists( $type, $avail ) ) {
1916                 return $type;
1917         } else {
1918                 $mainType = explode( '/', $type )[0];
1919                 if ( array_key_exists( "$mainType/*", $avail ) ) {
1920                         return "$mainType/*";
1921                 } elseif ( array_key_exists( '*/*', $avail ) ) {
1922                         return '*/*';
1923                 } else {
1924                         return null;
1925                 }
1926         }
1927 }
1928
1929 /**
1930  * Returns the 'best' match between a client's requested internet media types
1931  * and the server's list of available types. Each list should be an associative
1932  * array of type to preference (preference is a float between 0.0 and 1.0).
1933  * Wildcards in the types are acceptable.
1934  *
1935  * @param array $cprefs Client's acceptable type list
1936  * @param array $sprefs Server's offered types
1937  * @return string
1938  *
1939  * @todo FIXME: Doesn't handle params like 'text/plain; charset=UTF-8'
1940  * XXX: generalize to negotiate other stuff
1941  */
1942 function wfNegotiateType( $cprefs, $sprefs ) {
1943         $combine = [];
1944
1945         foreach ( array_keys( $sprefs ) as $type ) {
1946                 $subType = explode( '/', $type )[1];
1947                 if ( $subType != '*' ) {
1948                         $ckey = mimeTypeMatch( $type, $cprefs );
1949                         if ( $ckey ) {
1950                                 $combine[$type] = $sprefs[$type] * $cprefs[$ckey];
1951                         }
1952                 }
1953         }
1954
1955         foreach ( array_keys( $cprefs ) as $type ) {
1956                 $subType = explode( '/', $type )[1];
1957                 if ( $subType != '*' && !array_key_exists( $type, $sprefs ) ) {
1958                         $skey = mimeTypeMatch( $type, $sprefs );
1959                         if ( $skey ) {
1960                                 $combine[$type] = $sprefs[$skey] * $cprefs[$type];
1961                         }
1962                 }
1963         }
1964
1965         $bestq = 0;
1966         $besttype = null;
1967
1968         foreach ( array_keys( $combine ) as $type ) {
1969                 if ( $combine[$type] > $bestq ) {
1970                         $besttype = $type;
1971                         $bestq = $combine[$type];
1972                 }
1973         }
1974
1975         return $besttype;
1976 }
1977
1978 /**
1979  * Reference-counted warning suppression
1980  *
1981  * @deprecated since 1.26, use MediaWiki\suppressWarnings() directly
1982  * @param bool $end
1983  */
1984 function wfSuppressWarnings( $end = false ) {
1985         MediaWiki\suppressWarnings( $end );
1986 }
1987
1988 /**
1989  * @deprecated since 1.26, use MediaWiki\restoreWarnings() directly
1990  * Restore error level to previous value
1991  */
1992 function wfRestoreWarnings() {
1993         MediaWiki\suppressWarnings( true );
1994 }
1995
1996 # Autodetect, convert and provide timestamps of various types
1997
1998 require_once __DIR__ . '/libs/time/defines.php';
1999
2000 /**
2001  * Get a timestamp string in one of various formats
2002  *
2003  * @param mixed $outputtype A timestamp in one of the supported formats, the
2004  *   function will autodetect which format is supplied and act accordingly.
2005  * @param mixed $ts Optional timestamp to convert, default 0 for the current time
2006  * @return string|bool String / false The same date in the format specified in $outputtype or false
2007  */
2008 function wfTimestamp( $outputtype = TS_UNIX, $ts = 0 ) {
2009         $ret = MWTimestamp::convert( $outputtype, $ts );
2010         if ( $ret === false ) {
2011                 wfDebug( "wfTimestamp() fed bogus time value: TYPE=$outputtype; VALUE=$ts\n" );
2012         }
2013         return $ret;
2014 }
2015
2016 /**
2017  * Return a formatted timestamp, or null if input is null.
2018  * For dealing with nullable timestamp columns in the database.
2019  *
2020  * @param int $outputtype
2021  * @param string $ts
2022  * @return string
2023  */
2024 function wfTimestampOrNull( $outputtype = TS_UNIX, $ts = null ) {
2025         if ( is_null( $ts ) ) {
2026                 return null;
2027         } else {
2028                 return wfTimestamp( $outputtype, $ts );
2029         }
2030 }
2031
2032 /**
2033  * Convenience function; returns MediaWiki timestamp for the present time.
2034  *
2035  * @return string
2036  */
2037 function wfTimestampNow() {
2038         # return NOW
2039         return MWTimestamp::now( TS_MW );
2040 }
2041
2042 /**
2043  * Check if the operating system is Windows
2044  *
2045  * @return bool True if it's Windows, false otherwise.
2046  */
2047 function wfIsWindows() {
2048         static $isWindows = null;
2049         if ( $isWindows === null ) {
2050                 $isWindows = strtoupper( substr( PHP_OS, 0, 3 ) ) === 'WIN';
2051         }
2052         return $isWindows;
2053 }
2054
2055 /**
2056  * Check if we are running under HHVM
2057  *
2058  * @return bool
2059  */
2060 function wfIsHHVM() {
2061         return defined( 'HHVM_VERSION' );
2062 }
2063
2064 /**
2065  * Tries to get the system directory for temporary files. First
2066  * $wgTmpDirectory is checked, and then the TMPDIR, TMP, and TEMP
2067  * environment variables are then checked in sequence, then
2068  * sys_get_temp_dir(), then upload_tmp_dir from php.ini.
2069  *
2070  * NOTE: When possible, use instead the tmpfile() function to create
2071  * temporary files to avoid race conditions on file creation, etc.
2072  *
2073  * @return string
2074  */
2075 function wfTempDir() {
2076         global $wgTmpDirectory;
2077
2078         if ( $wgTmpDirectory !== false ) {
2079                 return $wgTmpDirectory;
2080         }
2081
2082         return TempFSFile::getUsableTempDirectory();
2083 }
2084
2085 /**
2086  * Make directory, and make all parent directories if they don't exist
2087  *
2088  * @param string $dir Full path to directory to create
2089  * @param int $mode Chmod value to use, default is $wgDirectoryMode
2090  * @param string $caller Optional caller param for debugging.
2091  * @throws MWException
2092  * @return bool
2093  */
2094 function wfMkdirParents( $dir, $mode = null, $caller = null ) {
2095         global $wgDirectoryMode;
2096
2097         if ( FileBackend::isStoragePath( $dir ) ) { // sanity
2098                 throw new MWException( __FUNCTION__ . " given storage path '$dir'." );
2099         }
2100
2101         if ( !is_null( $caller ) ) {
2102                 wfDebug( "$caller: called wfMkdirParents($dir)\n" );
2103         }
2104
2105         if ( strval( $dir ) === '' || is_dir( $dir ) ) {
2106                 return true;
2107         }
2108
2109         $dir = str_replace( [ '\\', '/' ], DIRECTORY_SEPARATOR, $dir );
2110
2111         if ( is_null( $mode ) ) {
2112                 $mode = $wgDirectoryMode;
2113         }
2114
2115         // Turn off the normal warning, we're doing our own below
2116         MediaWiki\suppressWarnings();
2117         $ok = mkdir( $dir, $mode, true ); // PHP5 <3
2118         MediaWiki\restoreWarnings();
2119
2120         if ( !$ok ) {
2121                 // directory may have been created on another request since we last checked
2122                 if ( is_dir( $dir ) ) {
2123                         return true;
2124                 }
2125
2126                 // PHP doesn't report the path in its warning message, so add our own to aid in diagnosis.
2127                 wfLogWarning( sprintf( "failed to mkdir \"%s\" mode 0%o", $dir, $mode ) );
2128         }
2129         return $ok;
2130 }
2131
2132 /**
2133  * Remove a directory and all its content.
2134  * Does not hide error.
2135  * @param string $dir
2136  */
2137 function wfRecursiveRemoveDir( $dir ) {
2138         wfDebug( __FUNCTION__ . "( $dir )\n" );
2139         // taken from http://de3.php.net/manual/en/function.rmdir.php#98622
2140         if ( is_dir( $dir ) ) {
2141                 $objects = scandir( $dir );
2142                 foreach ( $objects as $object ) {
2143                         if ( $object != "." && $object != ".." ) {
2144                                 if ( filetype( $dir . '/' . $object ) == "dir" ) {
2145                                         wfRecursiveRemoveDir( $dir . '/' . $object );
2146                                 } else {
2147                                         unlink( $dir . '/' . $object );
2148                                 }
2149                         }
2150                 }
2151                 reset( $objects );
2152                 rmdir( $dir );
2153         }
2154 }
2155
2156 /**
2157  * @param int $nr The number to format
2158  * @param int $acc The number of digits after the decimal point, default 2
2159  * @param bool $round Whether or not to round the value, default true
2160  * @return string
2161  */
2162 function wfPercent( $nr, $acc = 2, $round = true ) {
2163         $ret = sprintf( "%.${acc}f", $nr );
2164         return $round ? round( $ret, $acc ) . '%' : "$ret%";
2165 }
2166
2167 /**
2168  * Safety wrapper around ini_get() for boolean settings.
2169  * The values returned from ini_get() are pre-normalized for settings
2170  * set via php.ini or php_flag/php_admin_flag... but *not*
2171  * for those set via php_value/php_admin_value.
2172  *
2173  * It's fairly common for people to use php_value instead of php_flag,
2174  * which can leave you with an 'off' setting giving a false positive
2175  * for code that just takes the ini_get() return value as a boolean.
2176  *
2177  * To make things extra interesting, setting via php_value accepts
2178  * "true" and "yes" as true, but php.ini and php_flag consider them false. :)
2179  * Unrecognized values go false... again opposite PHP's own coercion
2180  * from string to bool.
2181  *
2182  * Luckily, 'properly' set settings will always come back as '0' or '1',
2183  * so we only have to worry about them and the 'improper' settings.
2184  *
2185  * I frickin' hate PHP... :P
2186  *
2187  * @param string $setting
2188  * @return bool
2189  */
2190 function wfIniGetBool( $setting ) {
2191         $val = strtolower( ini_get( $setting ) );
2192         // 'on' and 'true' can't have whitespace around them, but '1' can.
2193         return $val == 'on'
2194                 || $val == 'true'
2195                 || $val == 'yes'
2196                 || preg_match( "/^\s*[+-]?0*[1-9]/", $val ); // approx C atoi() function
2197 }
2198
2199 /**
2200  * Version of escapeshellarg() that works better on Windows.
2201  *
2202  * Originally, this fixed the incorrect use of single quotes on Windows
2203  * (https://bugs.php.net/bug.php?id=26285) and the locale problems on Linux in
2204  * PHP 5.2.6+ (bug backported to earlier distro releases of PHP).
2205  *
2206  * @param string ... strings to escape and glue together, or a single array of strings parameter
2207  * @return string
2208  */
2209 function wfEscapeShellArg( /*...*/ ) {
2210         wfInitShellLocale();
2211
2212         $args = func_get_args();
2213         if ( count( $args ) === 1 && is_array( reset( $args ) ) ) {
2214                 // If only one argument has been passed, and that argument is an array,
2215                 // treat it as a list of arguments
2216                 $args = reset( $args );
2217         }
2218
2219         $first = true;
2220         $retVal = '';
2221         foreach ( $args as $arg ) {
2222                 if ( !$first ) {
2223                         $retVal .= ' ';
2224                 } else {
2225                         $first = false;
2226                 }
2227
2228                 if ( wfIsWindows() ) {
2229                         // Escaping for an MSVC-style command line parser and CMD.EXE
2230                         // @codingStandardsIgnoreStart For long URLs
2231                         // Refs:
2232                         //  * http://web.archive.org/web/20020708081031/http://mailman.lyra.org/pipermail/scite-interest/2002-March/000436.html
2233                         //  * http://technet.microsoft.com/en-us/library/cc723564.aspx
2234                         //  * T15518
2235                         //  * CR r63214
2236                         // Double the backslashes before any double quotes. Escape the double quotes.
2237                         // @codingStandardsIgnoreEnd
2238                         $tokens = preg_split( '/(\\\\*")/', $arg, -1, PREG_SPLIT_DELIM_CAPTURE );
2239                         $arg = '';
2240                         $iteration = 0;
2241                         foreach ( $tokens as $token ) {
2242                                 if ( $iteration % 2 == 1 ) {
2243                                         // Delimiter, a double quote preceded by zero or more slashes
2244                                         $arg .= str_replace( '\\', '\\\\', substr( $token, 0, -1 ) ) . '\\"';
2245                                 } elseif ( $iteration % 4 == 2 ) {
2246                                         // ^ in $token will be outside quotes, need to be escaped
2247                                         $arg .= str_replace( '^', '^^', $token );
2248                                 } else { // $iteration % 4 == 0
2249                                         // ^ in $token will appear inside double quotes, so leave as is
2250                                         $arg .= $token;
2251                                 }
2252                                 $iteration++;
2253                         }
2254                         // Double the backslashes before the end of the string, because
2255                         // we will soon add a quote
2256                         $m = [];
2257                         if ( preg_match( '/^(.*?)(\\\\+)$/', $arg, $m ) ) {
2258                                 $arg = $m[1] . str_replace( '\\', '\\\\', $m[2] );
2259                         }
2260
2261                         // Add surrounding quotes
2262                         $retVal .= '"' . $arg . '"';
2263                 } else {
2264                         $retVal .= escapeshellarg( $arg );
2265                 }
2266         }
2267         return $retVal;
2268 }
2269
2270 /**
2271  * Check if wfShellExec() is effectively disabled via php.ini config
2272  *
2273  * @return bool|string False or 'disabled'
2274  * @since 1.22
2275  */
2276 function wfShellExecDisabled() {
2277         static $disabled = null;
2278         if ( is_null( $disabled ) ) {
2279                 if ( !function_exists( 'proc_open' ) ) {
2280                         wfDebug( "proc_open() is disabled\n" );
2281                         $disabled = 'disabled';
2282                 } else {
2283                         $disabled = false;
2284                 }
2285         }
2286         return $disabled;
2287 }
2288
2289 /**
2290  * Execute a shell command, with time and memory limits mirrored from the PHP
2291  * configuration if supported.
2292  *
2293  * @param string|string[] $cmd If string, a properly shell-escaped command line,
2294  *   or an array of unescaped arguments, in which case each value will be escaped
2295  *   Example:   [ 'convert', '-font', 'font name' ] would produce "'convert' '-font' 'font name'"
2296  * @param null|mixed &$retval Optional, will receive the program's exit code.
2297  *   (non-zero is usually failure). If there is an error from
2298  *   read, select, or proc_open(), this will be set to -1.
2299  * @param array $environ Optional environment variables which should be
2300  *   added to the executed command environment.
2301  * @param array $limits Optional array with limits(filesize, memory, time, walltime)
2302  *   this overwrites the global wgMaxShell* limits.
2303  * @param array $options Array of options:
2304  *   - duplicateStderr: Set this to true to duplicate stderr to stdout,
2305  *     including errors from limit.sh
2306  *   - profileMethod: By default this function will profile based on the calling
2307  *     method. Set this to a string for an alternative method to profile from
2308  *
2309  * @return string Collected stdout as a string
2310  */
2311 function wfShellExec( $cmd, &$retval = null, $environ = [],
2312         $limits = [], $options = []
2313 ) {
2314         global $IP, $wgMaxShellMemory, $wgMaxShellFileSize, $wgMaxShellTime,
2315                 $wgMaxShellWallClockTime, $wgShellCgroup;
2316
2317         $disabled = wfShellExecDisabled();
2318         if ( $disabled ) {
2319                 $retval = 1;
2320                 return 'Unable to run external programs, proc_open() is disabled.';
2321         }
2322
2323         $includeStderr = isset( $options['duplicateStderr'] ) && $options['duplicateStderr'];
2324         $profileMethod = isset( $options['profileMethod'] ) ? $options['profileMethod'] : wfGetCaller();
2325
2326         wfInitShellLocale();
2327
2328         $envcmd = '';
2329         foreach ( $environ as $k => $v ) {
2330                 if ( wfIsWindows() ) {
2331                         /* Surrounding a set in quotes (method used by wfEscapeShellArg) makes the quotes themselves
2332                          * appear in the environment variable, so we must use carat escaping as documented in
2333                          * http://technet.microsoft.com/en-us/library/cc723564.aspx
2334                          * Note however that the quote isn't listed there, but is needed, and the parentheses
2335                          * are listed there but doesn't appear to need it.
2336                          */
2337                         $envcmd .= "set $k=" . preg_replace( '/([&|()<>^"])/', '^\\1', $v ) . '&& ';
2338                 } else {
2339                         /* Assume this is a POSIX shell, thus required to accept variable assignments before the command
2340                          * http://www.opengroup.org/onlinepubs/009695399/utilities/xcu_chap02.html#tag_02_09_01
2341                          */
2342                         $envcmd .= "$k=" . escapeshellarg( $v ) . ' ';
2343                 }
2344         }
2345         if ( is_array( $cmd ) ) {
2346                 $cmd = wfEscapeShellArg( $cmd );
2347         }
2348
2349         $cmd = $envcmd . $cmd;
2350
2351         $useLogPipe = false;
2352         if ( is_executable( '/bin/bash' ) ) {
2353                 $time = intval( isset( $limits['time'] ) ? $limits['time'] : $wgMaxShellTime );
2354                 if ( isset( $limits['walltime'] ) ) {
2355                         $wallTime = intval( $limits['walltime'] );
2356                 } elseif ( isset( $limits['time'] ) ) {
2357                         $wallTime = $time;
2358                 } else {
2359                         $wallTime = intval( $wgMaxShellWallClockTime );
2360                 }
2361                 $mem = intval( isset( $limits['memory'] ) ? $limits['memory'] : $wgMaxShellMemory );
2362                 $filesize = intval( isset( $limits['filesize'] ) ? $limits['filesize'] : $wgMaxShellFileSize );
2363
2364                 if ( $time > 0 || $mem > 0 || $filesize > 0 || $wallTime > 0 ) {
2365                         $cmd = '/bin/bash ' . escapeshellarg( "$IP/includes/limit.sh" ) . ' ' .
2366                                 escapeshellarg( $cmd ) . ' ' .
2367                                 escapeshellarg(
2368                                         "MW_INCLUDE_STDERR=" . ( $includeStderr ? '1' : '' ) . ';' .
2369                                         "MW_CPU_LIMIT=$time; " .
2370                                         'MW_CGROUP=' . escapeshellarg( $wgShellCgroup ) . '; ' .
2371                                         "MW_MEM_LIMIT=$mem; " .
2372                                         "MW_FILE_SIZE_LIMIT=$filesize; " .
2373                                         "MW_WALL_CLOCK_LIMIT=$wallTime; " .
2374                                         "MW_USE_LOG_PIPE=yes"
2375                                 );
2376                         $useLogPipe = true;
2377                 } elseif ( $includeStderr ) {
2378                         $cmd .= ' 2>&1';
2379                 }
2380         } elseif ( $includeStderr ) {
2381                 $cmd .= ' 2>&1';
2382         }
2383         wfDebug( "wfShellExec: $cmd\n" );
2384
2385         // Don't try to execute commands that exceed Linux's MAX_ARG_STRLEN.
2386         // Other platforms may be more accomodating, but we don't want to be
2387         // accomodating, because very long commands probably include user
2388         // input. See T129506.
2389         if ( strlen( $cmd ) > SHELL_MAX_ARG_STRLEN ) {
2390                 throw new Exception( __METHOD__ .
2391                         '(): total length of $cmd must not exceed SHELL_MAX_ARG_STRLEN' );
2392         }
2393
2394         $desc = [
2395                 0 => [ 'file', 'php://stdin', 'r' ],
2396                 1 => [ 'pipe', 'w' ],
2397                 2 => [ 'file', 'php://stderr', 'w' ] ];
2398         if ( $useLogPipe ) {
2399                 $desc[3] = [ 'pipe', 'w' ];
2400         }
2401         $pipes = null;
2402         $scoped = Profiler::instance()->scopedProfileIn( __FUNCTION__ . '-' . $profileMethod );
2403         $proc = proc_open( $cmd, $desc, $pipes );
2404         if ( !$proc ) {
2405                 wfDebugLog( 'exec', "proc_open() failed: $cmd" );
2406                 $retval = -1;
2407                 return '';
2408         }
2409         $outBuffer = $logBuffer = '';
2410         $emptyArray = [];
2411         $status = false;
2412         $logMsg = false;
2413
2414         /* According to the documentation, it is possible for stream_select()
2415          * to fail due to EINTR. I haven't managed to induce this in testing
2416          * despite sending various signals. If it did happen, the error
2417          * message would take the form:
2418          *
2419          * stream_select(): unable to select [4]: Interrupted system call (max_fd=5)
2420          *
2421          * where [4] is the value of the macro EINTR and "Interrupted system
2422          * call" is string which according to the Linux manual is "possibly"
2423          * localised according to LC_MESSAGES.
2424          */
2425         $eintr = defined( 'SOCKET_EINTR' ) ? SOCKET_EINTR : 4;
2426         $eintrMessage = "stream_select(): unable to select [$eintr]";
2427
2428         $running = true;
2429         $timeout = null;
2430         $numReadyPipes = 0;
2431
2432         while ( $running === true || $numReadyPipes !== 0 ) {
2433                 if ( $running ) {
2434                         $status = proc_get_status( $proc );
2435                         // If the process has terminated, switch to nonblocking selects
2436                         // for getting any data still waiting to be read.
2437                         if ( !$status['running'] ) {
2438                                 $running = false;
2439                                 $timeout = 0;
2440                         }
2441                 }
2442
2443                 $readyPipes = $pipes;
2444
2445                 // Clear last error
2446                 // @codingStandardsIgnoreStart Generic.PHP.NoSilencedErrors.Discouraged
2447                 @trigger_error( '' );
2448                 $numReadyPipes = @stream_select( $readyPipes, $emptyArray, $emptyArray, $timeout );
2449                 if ( $numReadyPipes === false ) {
2450                         // @codingStandardsIgnoreEnd
2451                         $error = error_get_last();
2452                         if ( strncmp( $error['message'], $eintrMessage, strlen( $eintrMessage ) ) == 0 ) {
2453                                 continue;
2454                         } else {
2455                                 trigger_error( $error['message'], E_USER_WARNING );
2456                                 $logMsg = $error['message'];
2457                                 break;
2458                         }
2459                 }
2460                 foreach ( $readyPipes as $fd => $pipe ) {
2461                         $block = fread( $pipe, 65536 );
2462                         if ( $block === '' ) {
2463                                 // End of file
2464                                 fclose( $pipes[$fd] );
2465                                 unset( $pipes[$fd] );
2466                                 if ( !$pipes ) {
2467                                         break 2;
2468                                 }
2469                         } elseif ( $block === false ) {
2470                                 // Read error
2471                                 $logMsg = "Error reading from pipe";
2472                                 break 2;
2473                         } elseif ( $fd == 1 ) {
2474                                 // From stdout
2475                                 $outBuffer .= $block;
2476                         } elseif ( $fd == 3 ) {
2477                                 // From log FD
2478                                 $logBuffer .= $block;
2479                                 if ( strpos( $block, "\n" ) !== false ) {
2480                                         $lines = explode( "\n", $logBuffer );
2481                                         $logBuffer = array_pop( $lines );
2482                                         foreach ( $lines as $line ) {
2483                                                 wfDebugLog( 'exec', $line );
2484                                         }
2485                                 }
2486                         }
2487                 }
2488         }
2489
2490         foreach ( $pipes as $pipe ) {
2491                 fclose( $pipe );
2492         }
2493
2494         // Use the status previously collected if possible, since proc_get_status()
2495         // just calls waitpid() which will not return anything useful the second time.
2496         if ( $running ) {
2497                 $status = proc_get_status( $proc );
2498         }
2499
2500         if ( $logMsg !== false ) {
2501                 // Read/select error
2502                 $retval = -1;
2503                 proc_close( $proc );
2504         } elseif ( $status['signaled'] ) {
2505                 $logMsg = "Exited with signal {$status['termsig']}";
2506                 $retval = 128 + $status['termsig'];
2507                 proc_close( $proc );
2508         } else {
2509                 if ( $status['running'] ) {
2510                         $retval = proc_close( $proc );
2511                 } else {
2512                         $retval = $status['exitcode'];
2513                         proc_close( $proc );
2514                 }
2515                 if ( $retval == 127 ) {
2516                         $logMsg = "Possibly missing executable file";
2517                 } elseif ( $retval >= 129 && $retval <= 192 ) {
2518                         $logMsg = "Probably exited with signal " . ( $retval - 128 );
2519                 }
2520         }
2521
2522         if ( $logMsg !== false ) {
2523                 wfDebugLog( 'exec', "$logMsg: $cmd" );
2524         }
2525
2526         return $outBuffer;
2527 }
2528
2529 /**
2530  * Execute a shell command, returning both stdout and stderr. Convenience
2531  * function, as all the arguments to wfShellExec can become unwieldy.
2532  *
2533  * @note This also includes errors from limit.sh, e.g. if $wgMaxShellFileSize is exceeded.
2534  * @param string|string[] $cmd If string, a properly shell-escaped command line,
2535  *   or an array of unescaped arguments, in which case each value will be escaped
2536  *   Example:   [ 'convert', '-font', 'font name' ] would produce "'convert' '-font' 'font name'"
2537  * @param null|mixed &$retval Optional, will receive the program's exit code.
2538  *   (non-zero is usually failure)
2539  * @param array $environ Optional environment variables which should be
2540  *   added to the executed command environment.
2541  * @param array $limits Optional array with limits(filesize, memory, time, walltime)
2542  *   this overwrites the global wgMaxShell* limits.
2543  * @return string Collected stdout and stderr as a string
2544  */
2545 function wfShellExecWithStderr( $cmd, &$retval = null, $environ = [], $limits = [] ) {
2546         return wfShellExec( $cmd, $retval, $environ, $limits,
2547                 [ 'duplicateStderr' => true, 'profileMethod' => wfGetCaller() ] );
2548 }
2549
2550 /**
2551  * Workaround for http://bugs.php.net/bug.php?id=45132
2552  * escapeshellarg() destroys non-ASCII characters if LANG is not a UTF-8 locale
2553  */
2554 function wfInitShellLocale() {
2555         static $done = false;
2556         if ( $done ) {
2557                 return;
2558         }
2559         $done = true;
2560         global $wgShellLocale;
2561         putenv( "LC_CTYPE=$wgShellLocale" );
2562         setlocale( LC_CTYPE, $wgShellLocale );
2563 }
2564
2565 /**
2566  * Generate a shell-escaped command line string to run a MediaWiki cli script.
2567  * Note that $parameters should be a flat array and an option with an argument
2568  * should consist of two consecutive items in the array (do not use "--option value").
2569  *
2570  * @param string $script MediaWiki cli script path
2571  * @param array $parameters Arguments and options to the script
2572  * @param array $options Associative array of options:
2573  *              'php': The path to the php executable
2574  *              'wrapper': Path to a PHP wrapper to handle the maintenance script
2575  * @return string
2576  */
2577 function wfShellWikiCmd( $script, array $parameters = [], array $options = [] ) {
2578         global $wgPhpCli;
2579         // Give site config file a chance to run the script in a wrapper.
2580         // The caller may likely want to call wfBasename() on $script.
2581         Hooks::run( 'wfShellWikiCmd', [ &$script, &$parameters, &$options ] );
2582         $cmd = isset( $options['php'] ) ? [ $options['php'] ] : [ $wgPhpCli ];
2583         if ( isset( $options['wrapper'] ) ) {
2584                 $cmd[] = $options['wrapper'];
2585         }
2586         $cmd[] = $script;
2587         // Escape each parameter for shell
2588         return wfEscapeShellArg( array_merge( $cmd, $parameters ) );
2589 }
2590
2591 /**
2592  * wfMerge attempts to merge differences between three texts.
2593  * Returns true for a clean merge and false for failure or a conflict.
2594  *
2595  * @param string $old
2596  * @param string $mine
2597  * @param string $yours
2598  * @param string $result
2599  * @return bool
2600  */
2601 function wfMerge( $old, $mine, $yours, &$result ) {
2602         global $wgDiff3;
2603
2604         # This check may also protect against code injection in
2605         # case of broken installations.
2606         MediaWiki\suppressWarnings();
2607         $haveDiff3 = $wgDiff3 && file_exists( $wgDiff3 );
2608         MediaWiki\restoreWarnings();
2609
2610         if ( !$haveDiff3 ) {
2611                 wfDebug( "diff3 not found\n" );
2612                 return false;
2613         }
2614
2615         # Make temporary files
2616         $td = wfTempDir();
2617         $oldtextFile = fopen( $oldtextName = tempnam( $td, 'merge-old-' ), 'w' );
2618         $mytextFile = fopen( $mytextName = tempnam( $td, 'merge-mine-' ), 'w' );
2619         $yourtextFile = fopen( $yourtextName = tempnam( $td, 'merge-your-' ), 'w' );
2620
2621         # NOTE: diff3 issues a warning to stderr if any of the files does not end with
2622         #       a newline character. To avoid this, we normalize the trailing whitespace before
2623         #       creating the diff.
2624
2625         fwrite( $oldtextFile, rtrim( $old ) . "\n" );
2626         fclose( $oldtextFile );
2627         fwrite( $mytextFile, rtrim( $mine ) . "\n" );
2628         fclose( $mytextFile );
2629         fwrite( $yourtextFile, rtrim( $yours ) . "\n" );
2630         fclose( $yourtextFile );
2631
2632         # Check for a conflict
2633         $cmd = wfEscapeShellArg( $wgDiff3, '-a', '--overlap-only', $mytextName,
2634                 $oldtextName, $yourtextName );
2635         $handle = popen( $cmd, 'r' );
2636
2637         if ( fgets( $handle, 1024 ) ) {
2638                 $conflict = true;
2639         } else {
2640                 $conflict = false;
2641         }
2642         pclose( $handle );
2643
2644         # Merge differences
2645         $cmd = wfEscapeShellArg( $wgDiff3, '-a', '-e', '--merge', $mytextName,
2646                 $oldtextName, $yourtextName );
2647         $handle = popen( $cmd, 'r' );
2648         $result = '';
2649         do {
2650                 $data = fread( $handle, 8192 );
2651                 if ( strlen( $data ) == 0 ) {
2652                         break;
2653                 }
2654                 $result .= $data;
2655         } while ( true );
2656         pclose( $handle );
2657         unlink( $mytextName );
2658         unlink( $oldtextName );
2659         unlink( $yourtextName );
2660
2661         if ( $result === '' && $old !== '' && !$conflict ) {
2662                 wfDebug( "Unexpected null result from diff3. Command: $cmd\n" );
2663                 $conflict = true;
2664         }
2665         return !$conflict;
2666 }
2667
2668 /**
2669  * Returns unified plain-text diff of two texts.
2670  * "Useful" for machine processing of diffs.
2671  *
2672  * @deprecated since 1.25, use DiffEngine/UnifiedDiffFormatter directly
2673  *
2674  * @param string $before The text before the changes.
2675  * @param string $after The text after the changes.
2676  * @param string $params Command-line options for the diff command.
2677  * @return string Unified diff of $before and $after
2678  */
2679 function wfDiff( $before, $after, $params = '-u' ) {
2680         if ( $before == $after ) {
2681                 return '';
2682         }
2683
2684         global $wgDiff;
2685         MediaWiki\suppressWarnings();
2686         $haveDiff = $wgDiff && file_exists( $wgDiff );
2687         MediaWiki\restoreWarnings();
2688
2689         # This check may also protect against code injection in
2690         # case of broken installations.
2691         if ( !$haveDiff ) {
2692                 wfDebug( "diff executable not found\n" );
2693                 $diffs = new Diff( explode( "\n", $before ), explode( "\n", $after ) );
2694                 $format = new UnifiedDiffFormatter();
2695                 return $format->format( $diffs );
2696         }
2697
2698         # Make temporary files
2699         $td = wfTempDir();
2700         $oldtextFile = fopen( $oldtextName = tempnam( $td, 'merge-old-' ), 'w' );
2701         $newtextFile = fopen( $newtextName = tempnam( $td, 'merge-your-' ), 'w' );
2702
2703         fwrite( $oldtextFile, $before );
2704         fclose( $oldtextFile );
2705         fwrite( $newtextFile, $after );
2706         fclose( $newtextFile );
2707
2708         // Get the diff of the two files
2709         $cmd = "$wgDiff " . $params . ' ' . wfEscapeShellArg( $oldtextName, $newtextName );
2710
2711         $h = popen( $cmd, 'r' );
2712         if ( !$h ) {
2713                 unlink( $oldtextName );
2714                 unlink( $newtextName );
2715                 throw new Exception( __METHOD__ . '(): popen() failed' );
2716         }
2717
2718         $diff = '';
2719
2720         do {
2721                 $data = fread( $h, 8192 );
2722                 if ( strlen( $data ) == 0 ) {
2723                         break;
2724                 }
2725                 $diff .= $data;
2726         } while ( true );
2727
2728         // Clean up
2729         pclose( $h );
2730         unlink( $oldtextName );
2731         unlink( $newtextName );
2732
2733         // Kill the --- and +++ lines. They're not useful.
2734         $diff_lines = explode( "\n", $diff );
2735         if ( isset( $diff_lines[0] ) && strpos( $diff_lines[0], '---' ) === 0 ) {
2736                 unset( $diff_lines[0] );
2737         }
2738         if ( isset( $diff_lines[1] ) && strpos( $diff_lines[1], '+++' ) === 0 ) {
2739                 unset( $diff_lines[1] );
2740         }
2741
2742         $diff = implode( "\n", $diff_lines );
2743
2744         return $diff;
2745 }
2746
2747 /**
2748  * This function works like "use VERSION" in Perl, the program will die with a
2749  * backtrace if the current version of PHP is less than the version provided
2750  *
2751  * This is useful for extensions which due to their nature are not kept in sync
2752  * with releases, and might depend on other versions of PHP than the main code
2753  *
2754  * Note: PHP might die due to parsing errors in some cases before it ever
2755  *       manages to call this function, such is life
2756  *
2757  * @see perldoc -f use
2758  *
2759  * @param string|int|float $req_ver The version to check, can be a string, an integer, or a float
2760  * @throws MWException
2761  */
2762 function wfUsePHP( $req_ver ) {
2763         $php_ver = PHP_VERSION;
2764
2765         if ( version_compare( $php_ver, (string)$req_ver, '<' ) ) {
2766                 throw new MWException( "PHP $req_ver required--this is only $php_ver" );
2767         }
2768 }
2769
2770 /**
2771  * This function works like "use VERSION" in Perl except it checks the version
2772  * of MediaWiki, the program will die with a backtrace if the current version
2773  * of MediaWiki is less than the version provided.
2774  *
2775  * This is useful for extensions which due to their nature are not kept in sync
2776  * with releases
2777  *
2778  * Note: Due to the behavior of PHP's version_compare() which is used in this
2779  * function, if you want to allow the 'wmf' development versions add a 'c' (or
2780  * any single letter other than 'a', 'b' or 'p') as a post-fix to your
2781  * targeted version number. For example if you wanted to allow any variation
2782  * of 1.22 use `wfUseMW( '1.22c' )`. Using an 'a' or 'b' instead of 'c' will
2783  * not result in the same comparison due to the internal logic of
2784  * version_compare().
2785  *
2786  * @see perldoc -f use
2787  *
2788  * @deprecated since 1.26, use the "requires' property of extension.json
2789  * @param string|int|float $req_ver The version to check, can be a string, an integer, or a float
2790  * @throws MWException
2791  */
2792 function wfUseMW( $req_ver ) {
2793         global $wgVersion;
2794
2795         if ( version_compare( $wgVersion, (string)$req_ver, '<' ) ) {
2796                 throw new MWException( "MediaWiki $req_ver required--this is only $wgVersion" );
2797         }
2798 }
2799
2800 /**
2801  * Return the final portion of a pathname.
2802  * Reimplemented because PHP5's "basename()" is buggy with multibyte text.
2803  * http://bugs.php.net/bug.php?id=33898
2804  *
2805  * PHP's basename() only considers '\' a pathchar on Windows and Netware.
2806  * We'll consider it so always, as we don't want '\s' in our Unix paths either.
2807  *
2808  * @param string $path
2809  * @param string $suffix String to remove if present
2810  * @return string
2811  */
2812 function wfBaseName( $path, $suffix = '' ) {
2813         if ( $suffix == '' ) {
2814                 $encSuffix = '';
2815         } else {
2816                 $encSuffix = '(?:' . preg_quote( $suffix, '#' ) . ')?';
2817         }
2818
2819         $matches = [];
2820         if ( preg_match( "#([^/\\\\]*?){$encSuffix}[/\\\\]*$#", $path, $matches ) ) {
2821                 return $matches[1];
2822         } else {
2823                 return '';
2824         }
2825 }
2826
2827 /**
2828  * Generate a relative path name to the given file.
2829  * May explode on non-matching case-insensitive paths,
2830  * funky symlinks, etc.
2831  *
2832  * @param string $path Absolute destination path including target filename
2833  * @param string $from Absolute source path, directory only
2834  * @return string
2835  */
2836 function wfRelativePath( $path, $from ) {
2837         // Normalize mixed input on Windows...
2838         $path = str_replace( '/', DIRECTORY_SEPARATOR, $path );
2839         $from = str_replace( '/', DIRECTORY_SEPARATOR, $from );
2840
2841         // Trim trailing slashes -- fix for drive root
2842         $path = rtrim( $path, DIRECTORY_SEPARATOR );
2843         $from = rtrim( $from, DIRECTORY_SEPARATOR );
2844
2845         $pieces = explode( DIRECTORY_SEPARATOR, dirname( $path ) );
2846         $against = explode( DIRECTORY_SEPARATOR, $from );
2847
2848         if ( $pieces[0] !== $against[0] ) {
2849                 // Non-matching Windows drive letters?
2850                 // Return a full path.
2851                 return $path;
2852         }
2853
2854         // Trim off common prefix
2855         while ( count( $pieces ) && count( $against )
2856                 && $pieces[0] == $against[0] ) {
2857                 array_shift( $pieces );
2858                 array_shift( $against );
2859         }
2860
2861         // relative dots to bump us to the parent
2862         while ( count( $against ) ) {
2863                 array_unshift( $pieces, '..' );
2864                 array_shift( $against );
2865         }
2866
2867         array_push( $pieces, wfBaseName( $path ) );
2868
2869         return implode( DIRECTORY_SEPARATOR, $pieces );
2870 }
2871
2872 /**
2873  * Convert an arbitrarily-long digit string from one numeric base
2874  * to another, optionally zero-padding to a minimum column width.
2875  *
2876  * Supports base 2 through 36; digit values 10-36 are represented
2877  * as lowercase letters a-z. Input is case-insensitive.
2878  *
2879  * @deprecated since 1.27 Use Wikimedia\base_convert() directly
2880  *
2881  * @param string $input Input number
2882  * @param int $sourceBase Base of the input number
2883  * @param int $destBase Desired base of the output
2884  * @param int $pad Minimum number of digits in the output (pad with zeroes)
2885  * @param bool $lowercase Whether to output in lowercase or uppercase
2886  * @param string $engine Either "gmp", "bcmath", or "php"
2887  * @return string|bool The output number as a string, or false on error
2888  */
2889 function wfBaseConvert( $input, $sourceBase, $destBase, $pad = 1,
2890         $lowercase = true, $engine = 'auto'
2891 ) {
2892         return Wikimedia\base_convert( $input, $sourceBase, $destBase, $pad, $lowercase, $engine );
2893 }
2894
2895 /**
2896  * @deprecated since 1.27, PHP's session generation isn't used with
2897  *  MediaWiki\Session\SessionManager
2898  */
2899 function wfFixSessionID() {
2900         wfDeprecated( __FUNCTION__, '1.27' );
2901 }
2902
2903 /**
2904  * Reset the session id
2905  *
2906  * @deprecated since 1.27, use MediaWiki\Session\SessionManager instead
2907  * @since 1.22
2908  */
2909 function wfResetSessionID() {
2910         wfDeprecated( __FUNCTION__, '1.27' );
2911         $session = SessionManager::getGlobalSession();
2912         $delay = $session->delaySave();
2913
2914         $session->resetId();
2915
2916         // Make sure a session is started, since that's what the old
2917         // wfResetSessionID() did.
2918         if ( session_id() !== $session->getId() ) {
2919                 wfSetupSession( $session->getId() );
2920         }
2921
2922         ScopedCallback::consume( $delay );
2923 }
2924
2925 /**
2926  * Initialise php session
2927  *
2928  * @deprecated since 1.27, use MediaWiki\Session\SessionManager instead.
2929  *  Generally, "using" SessionManager will be calling ->getSessionById() or
2930  *  ::getGlobalSession() (depending on whether you were passing $sessionId
2931  *  here), then calling $session->persist().
2932  * @param bool|string $sessionId
2933  */
2934 function wfSetupSession( $sessionId = false ) {
2935         wfDeprecated( __FUNCTION__, '1.27' );
2936
2937         if ( $sessionId ) {
2938                 session_id( $sessionId );
2939         }
2940
2941         $session = SessionManager::getGlobalSession();
2942         $session->persist();
2943
2944         if ( session_id() !== $session->getId() ) {
2945                 session_id( $session->getId() );
2946         }
2947         MediaWiki\quietCall( 'session_start' );
2948 }
2949
2950 /**
2951  * Get an object from the precompiled serialized directory
2952  *
2953  * @param string $name
2954  * @return mixed The variable on success, false on failure
2955  */
2956 function wfGetPrecompiledData( $name ) {
2957         global $IP;
2958
2959         $file = "$IP/serialized/$name";
2960         if ( file_exists( $file ) ) {
2961                 $blob = file_get_contents( $file );
2962                 if ( $blob ) {
2963                         return unserialize( $blob );
2964                 }
2965         }
2966         return false;
2967 }
2968
2969 /**
2970  * Make a cache key for the local wiki.
2971  *
2972  * @param string $args,...
2973  * @return string
2974  */
2975 function wfMemcKey( /*...*/ ) {
2976         return call_user_func_array(
2977                 [ ObjectCache::getLocalClusterInstance(), 'makeKey' ],
2978                 func_get_args()
2979         );
2980 }
2981
2982 /**
2983  * Make a cache key for a foreign DB.
2984  *
2985  * Must match what wfMemcKey() would produce in context of the foreign wiki.
2986  *
2987  * @param string $db
2988  * @param string $prefix
2989  * @param string $args,...
2990  * @return string
2991  */
2992 function wfForeignMemcKey( $db, $prefix /*...*/ ) {
2993         $args = array_slice( func_get_args(), 2 );
2994         $keyspace = $prefix ? "$db-$prefix" : $db;
2995         return call_user_func_array(
2996                 [ ObjectCache::getLocalClusterInstance(), 'makeKeyInternal' ],
2997                 [ $keyspace, $args ]
2998         );
2999 }
3000
3001 /**
3002  * Make a cache key with database-agnostic prefix.
3003  *
3004  * Doesn't have a wiki-specific namespace. Uses a generic 'global' prefix
3005  * instead. Must have a prefix as otherwise keys that use a database name
3006  * in the first segment will clash with wfMemcKey/wfForeignMemcKey.
3007  *
3008  * @since 1.26
3009  * @param string $args,...
3010  * @return string
3011  */
3012 function wfGlobalCacheKey( /*...*/ ) {
3013         return call_user_func_array(
3014                 [ ObjectCache::getLocalClusterInstance(), 'makeGlobalKey' ],
3015                 func_get_args()
3016         );
3017 }
3018
3019 /**
3020  * Get an ASCII string identifying this wiki
3021  * This is used as a prefix in memcached keys
3022  *
3023  * @return string
3024  */
3025 function wfWikiID() {
3026         global $wgDBprefix, $wgDBname;
3027         if ( $wgDBprefix ) {
3028                 return "$wgDBname-$wgDBprefix";
3029         } else {
3030                 return $wgDBname;
3031         }
3032 }
3033
3034 /**
3035  * Split a wiki ID into DB name and table prefix
3036  *
3037  * @param string $wiki
3038  *
3039  * @return array
3040  */
3041 function wfSplitWikiID( $wiki ) {
3042         $bits = explode( '-', $wiki, 2 );
3043         if ( count( $bits ) < 2 ) {
3044                 $bits[] = '';
3045         }
3046         return $bits;
3047 }
3048
3049 /**
3050  * Get a Database object.
3051  *
3052  * @param int $db Index of the connection to get. May be DB_MASTER for the
3053  *            master (for write queries), DB_REPLICA for potentially lagged read
3054  *            queries, or an integer >= 0 for a particular server.
3055  *
3056  * @param string|string[] $groups Query groups. An array of group names that this query
3057  *                belongs to. May contain a single string if the query is only
3058  *                in one group.
3059  *
3060  * @param string|bool $wiki The wiki ID, or false for the current wiki
3061  *
3062  * Note: multiple calls to wfGetDB(DB_REPLICA) during the course of one request
3063  * will always return the same object, unless the underlying connection or load
3064  * balancer is manually destroyed.
3065  *
3066  * Note 2: use $this->getDB() in maintenance scripts that may be invoked by
3067  * updater to ensure that a proper database is being updated.
3068  *
3069  * @todo Replace calls to wfGetDB with calls to LoadBalancer::getConnection()
3070  *       on an injected instance of LoadBalancer.
3071  *
3072  * @return Database
3073  */
3074 function wfGetDB( $db, $groups = [], $wiki = false ) {
3075         return wfGetLB( $wiki )->getConnection( $db, $groups, $wiki );
3076 }
3077
3078 /**
3079  * Get a load balancer object.
3080  *
3081  * @deprecated since 1.27, use MediaWikiServices::getDBLoadBalancer()
3082  *              or MediaWikiServices::getDBLoadBalancerFactory() instead.
3083  *
3084  * @param string|bool $wiki Wiki ID, or false for the current wiki
3085  * @return LoadBalancer
3086  */
3087 function wfGetLB( $wiki = false ) {
3088         if ( $wiki === false ) {
3089                 return \MediaWiki\MediaWikiServices::getInstance()->getDBLoadBalancer();
3090         } else {
3091                 $factory = \MediaWiki\MediaWikiServices::getInstance()->getDBLoadBalancerFactory();
3092                 return $factory->getMainLB( $wiki );
3093         }
3094 }
3095
3096 /**
3097  * Get the load balancer factory object
3098  *
3099  * @deprecated since 1.27, use MediaWikiServices::getDBLoadBalancerFactory() instead.
3100  *
3101  * @return LBFactory
3102  */
3103 function wfGetLBFactory() {
3104         return \MediaWiki\MediaWikiServices::getInstance()->getDBLoadBalancerFactory();
3105 }
3106
3107 /**
3108  * Find a file.
3109  * Shortcut for RepoGroup::singleton()->findFile()
3110  *
3111  * @param string $title String or Title object
3112  * @param array $options Associative array of options (see RepoGroup::findFile)
3113  * @return File|bool File, or false if the file does not exist
3114  */
3115 function wfFindFile( $title, $options = [] ) {
3116         return RepoGroup::singleton()->findFile( $title, $options );
3117 }
3118
3119 /**
3120  * Get an object referring to a locally registered file.
3121  * Returns a valid placeholder object if the file does not exist.
3122  *
3123  * @param Title|string $title
3124  * @return LocalFile|null A File, or null if passed an invalid Title
3125  */
3126 function wfLocalFile( $title ) {
3127         return RepoGroup::singleton()->getLocalRepo()->newFile( $title );
3128 }
3129
3130 /**
3131  * Should low-performance queries be disabled?
3132  *
3133  * @return bool
3134  * @codeCoverageIgnore
3135  */
3136 function wfQueriesMustScale() {
3137         global $wgMiserMode;
3138         return $wgMiserMode
3139                 || ( SiteStats::pages() > 100000
3140                 && SiteStats::edits() > 1000000
3141                 && SiteStats::users() > 10000 );
3142 }
3143
3144 /**
3145  * Get the path to a specified script file, respecting file
3146  * extensions; this is a wrapper around $wgScriptPath etc.
3147  * except for 'index' and 'load' which use $wgScript/$wgLoadScript
3148  *
3149  * @param string $script Script filename, sans extension
3150  * @return string
3151  */
3152 function wfScript( $script = 'index' ) {
3153         global $wgScriptPath, $wgScript, $wgLoadScript;
3154         if ( $script === 'index' ) {
3155                 return $wgScript;
3156         } elseif ( $script === 'load' ) {
3157                 return $wgLoadScript;
3158         } else {
3159                 return "{$wgScriptPath}/{$script}.php";
3160         }
3161 }
3162
3163 /**
3164  * Get the script URL.
3165  *
3166  * @return string Script URL
3167  */
3168 function wfGetScriptUrl() {
3169         if ( isset( $_SERVER['SCRIPT_NAME'] ) ) {
3170                 /* as it was called, minus the query string.
3171                  *
3172                  * Some sites use Apache rewrite rules to handle subdomains,
3173                  * and have PHP set up in a weird way that causes PHP_SELF
3174                  * to contain the rewritten URL instead of the one that the
3175                  * outside world sees.
3176                  *
3177                  * If in this mode, use SCRIPT_URL instead, which mod_rewrite
3178                  * provides containing the "before" URL.
3179                  */
3180                 return $_SERVER['SCRIPT_NAME'];
3181         } else {
3182                 return $_SERVER['URL'];
3183         }
3184 }
3185
3186 /**
3187  * Convenience function converts boolean values into "true"
3188  * or "false" (string) values
3189  *
3190  * @param bool $value
3191  * @return string
3192  */
3193 function wfBoolToStr( $value ) {
3194         return $value ? 'true' : 'false';
3195 }
3196
3197 /**
3198  * Get a platform-independent path to the null file, e.g. /dev/null
3199  *
3200  * @return string
3201  */
3202 function wfGetNull() {
3203         return wfIsWindows() ? 'NUL' : '/dev/null';
3204 }
3205
3206 /**
3207  * Waits for the replica DBs to catch up to the master position
3208  *
3209  * Use this when updating very large numbers of rows, as in maintenance scripts,
3210  * to avoid causing too much lag. Of course, this is a no-op if there are no replica DBs.
3211  *
3212  * By default this waits on the main DB cluster of the current wiki.
3213  * If $cluster is set to "*" it will wait on all DB clusters, including
3214  * external ones. If the lag being waiting on is caused by the code that
3215  * does this check, it makes since to use $ifWritesSince, particularly if
3216  * cluster is "*", to avoid excess overhead.
3217  *
3218  * Never call this function after a big DB write that is still in a transaction.
3219  * This only makes sense after the possible lag inducing changes were committed.
3220  *
3221  * @param float|null $ifWritesSince Only wait if writes were done since this UNIX timestamp
3222  * @param string|bool $wiki Wiki identifier accepted by wfGetLB
3223  * @param string|bool $cluster Cluster name accepted by LBFactory. Default: false.
3224  * @param int|null $timeout Max wait time. Default: 1 day (cli), ~10 seconds (web)
3225  * @return bool Success (able to connect and no timeouts reached)
3226  * @deprecated since 1.27 Use LBFactory::waitForReplication
3227  */
3228 function wfWaitForSlaves(
3229         $ifWritesSince = null, $wiki = false, $cluster = false, $timeout = null
3230 ) {
3231         if ( $timeout === null ) {
3232                 $timeout = ( PHP_SAPI === 'cli' ) ? 86400 : 10;
3233         }
3234
3235         if ( $cluster === '*' ) {
3236                 $cluster = false;
3237                 $wiki = false;
3238         } elseif ( $wiki === false ) {
3239                 $wiki = wfWikiID();
3240         }
3241
3242         try {
3243                 wfGetLBFactory()->waitForReplication( [
3244                         'wiki' => $wiki,
3245                         'cluster' => $cluster,
3246                         'timeout' => $timeout,
3247                         // B/C: first argument used to be "max seconds of lag"; ignore such values
3248                         'ifWritesSince' => ( $ifWritesSince > 1e9 ) ? $ifWritesSince : null
3249                 ] );
3250         } catch ( DBReplicationWaitError $e ) {
3251                 return false;
3252         }
3253
3254         return true;
3255 }
3256
3257 /**
3258  * Count down from $seconds to zero on the terminal, with a one-second pause
3259  * between showing each number. For use in command-line scripts.
3260  *
3261  * @codeCoverageIgnore
3262  * @param int $seconds
3263  */
3264 function wfCountDown( $seconds ) {
3265         for ( $i = $seconds; $i >= 0; $i-- ) {
3266                 if ( $i != $seconds ) {
3267                         echo str_repeat( "\x08", strlen( $i + 1 ) );
3268                 }
3269                 echo $i;
3270                 flush();
3271                 if ( $i ) {
3272                         sleep( 1 );
3273                 }
3274         }
3275         echo "\n";
3276 }
3277
3278 /**
3279  * Replace all invalid characters with '-'.
3280  * Additional characters can be defined in $wgIllegalFileChars (see T22489).
3281  * By default, $wgIllegalFileChars includes ':', '/', '\'.
3282  *
3283  * @param string $name Filename to process
3284  * @return string
3285  */
3286 function wfStripIllegalFilenameChars( $name ) {
3287         global $wgIllegalFileChars;
3288         $illegalFileChars = $wgIllegalFileChars ? "|[" . $wgIllegalFileChars . "]" : '';
3289         $name = preg_replace(
3290                 "/[^" . Title::legalChars() . "]" . $illegalFileChars . "/",
3291                 '-',
3292                 $name
3293         );
3294         // $wgIllegalFileChars may not include '/' and '\', so we still need to do this
3295         $name = wfBaseName( $name );
3296         return $name;
3297 }
3298
3299 /**
3300  * Set PHP's memory limit to the larger of php.ini or $wgMemoryLimit
3301  *
3302  * @return int Resulting value of the memory limit.
3303  */
3304 function wfMemoryLimit() {
3305         global $wgMemoryLimit;
3306         $memlimit = wfShorthandToInteger( ini_get( 'memory_limit' ) );
3307         if ( $memlimit != -1 ) {
3308                 $conflimit = wfShorthandToInteger( $wgMemoryLimit );
3309                 if ( $conflimit == -1 ) {
3310                         wfDebug( "Removing PHP's memory limit\n" );
3311                         MediaWiki\suppressWarnings();
3312                         ini_set( 'memory_limit', $conflimit );
3313                         MediaWiki\restoreWarnings();
3314                         return $conflimit;
3315                 } elseif ( $conflimit > $memlimit ) {
3316                         wfDebug( "Raising PHP's memory limit to $conflimit bytes\n" );
3317                         MediaWiki\suppressWarnings();
3318                         ini_set( 'memory_limit', $conflimit );
3319                         MediaWiki\restoreWarnings();
3320                         return $conflimit;
3321                 }
3322         }
3323         return $memlimit;
3324 }
3325
3326 /**
3327  * Set PHP's time limit to the larger of php.ini or $wgTransactionalTimeLimit
3328  *
3329  * @return int Prior time limit
3330  * @since 1.26
3331  */
3332 function wfTransactionalTimeLimit() {
3333         global $wgTransactionalTimeLimit;
3334
3335         $timeLimit = ini_get( 'max_execution_time' );
3336         // Note that CLI scripts use 0
3337         if ( $timeLimit > 0 && $wgTransactionalTimeLimit > $timeLimit ) {
3338                 set_time_limit( $wgTransactionalTimeLimit );
3339         }
3340
3341         ignore_user_abort( true ); // ignore client disconnects
3342
3343         return $timeLimit;
3344 }
3345
3346 /**
3347  * Converts shorthand byte notation to integer form
3348  *
3349  * @param string $string
3350  * @param int $default Returned if $string is empty
3351  * @return int
3352  */
3353 function wfShorthandToInteger( $string = '', $default = -1 ) {
3354         $string = trim( $string );
3355         if ( $string === '' ) {
3356                 return $default;
3357         }
3358         $last = $string[strlen( $string ) - 1];
3359         $val = intval( $string );
3360         switch ( $last ) {
3361                 case 'g':
3362                 case 'G':
3363                         $val *= 1024;
3364                         // break intentionally missing
3365                 case 'm':
3366                 case 'M':
3367                         $val *= 1024;
3368                         // break intentionally missing
3369                 case 'k':
3370                 case 'K':
3371                         $val *= 1024;
3372         }
3373
3374         return $val;
3375 }
3376
3377 /**
3378  * Get the normalised IETF language tag
3379  * See unit test for examples.
3380  *
3381  * @param string $code The language code.
3382  * @return string The language code which complying with BCP 47 standards.
3383  */
3384 function wfBCP47( $code ) {
3385         $codeSegment = explode( '-', $code );
3386         $codeBCP = [];
3387         foreach ( $codeSegment as $segNo => $seg ) {
3388                 // when previous segment is x, it is a private segment and should be lc
3389                 if ( $segNo > 0 && strtolower( $codeSegment[( $segNo - 1 )] ) == 'x' ) {
3390                         $codeBCP[$segNo] = strtolower( $seg );
3391                 // ISO 3166 country code
3392                 } elseif ( ( strlen( $seg ) == 2 ) && ( $segNo > 0 ) ) {
3393                         $codeBCP[$segNo] = strtoupper( $seg );
3394                 // ISO 15924 script code
3395                 } elseif ( ( strlen( $seg ) == 4 ) && ( $segNo > 0 ) ) {
3396                         $codeBCP[$segNo] = ucfirst( strtolower( $seg ) );
3397                 // Use lowercase for other cases
3398                 } else {
3399                         $codeBCP[$segNo] = strtolower( $seg );
3400                 }
3401         }
3402         $langCode = implode( '-', $codeBCP );
3403         return $langCode;
3404 }
3405
3406 /**
3407  * Get a specific cache object.
3408  *
3409  * @param int|string $cacheType A CACHE_* constants, or other key in $wgObjectCaches
3410  * @return BagOStuff
3411  */
3412 function wfGetCache( $cacheType ) {
3413         return ObjectCache::getInstance( $cacheType );
3414 }
3415
3416 /**
3417  * Get the main cache object
3418  *
3419  * @return BagOStuff
3420  */
3421 function wfGetMainCache() {
3422         global $wgMainCacheType;
3423         return ObjectCache::getInstance( $wgMainCacheType );
3424 }
3425
3426 /**
3427  * Get the cache object used by the message cache
3428  *
3429  * @return BagOStuff
3430  */
3431 function wfGetMessageCacheStorage() {
3432         global $wgMessageCacheType;
3433         return ObjectCache::getInstance( $wgMessageCacheType );
3434 }
3435
3436 /**
3437  * Get the cache object used by the parser cache
3438  *
3439  * @return BagOStuff
3440  */
3441 function wfGetParserCacheStorage() {
3442         global $wgParserCacheType;
3443         return ObjectCache::getInstance( $wgParserCacheType );
3444 }
3445
3446 /**
3447  * Call hook functions defined in $wgHooks
3448  *
3449  * @param string $event Event name
3450  * @param array $args Parameters passed to hook functions
3451  * @param string|null $deprecatedVersion Optionally mark hook as deprecated with version number
3452  *
3453  * @return bool True if no handler aborted the hook
3454  * @deprecated since 1.25 - use Hooks::run
3455  */
3456 function wfRunHooks( $event, array $args = [], $deprecatedVersion = null ) {
3457         return Hooks::run( $event, $args, $deprecatedVersion );
3458 }
3459
3460 /**
3461  * Wrapper around php's unpack.
3462  *
3463  * @param string $format The format string (See php's docs)
3464  * @param string $data A binary string of binary data
3465  * @param int|bool $length The minimum length of $data or false. This is to
3466  *      prevent reading beyond the end of $data. false to disable the check.
3467  *
3468  * Also be careful when using this function to read unsigned 32 bit integer
3469  * because php might make it negative.
3470  *
3471  * @throws MWException If $data not long enough, or if unpack fails
3472  * @return array Associative array of the extracted data
3473  */
3474 function wfUnpack( $format, $data, $length = false ) {
3475         if ( $length !== false ) {
3476                 $realLen = strlen( $data );
3477                 if ( $realLen < $length ) {
3478                         throw new MWException( "Tried to use wfUnpack on a "
3479                                 . "string of length $realLen, but needed one "
3480                                 . "of at least length $length."
3481                         );
3482                 }
3483         }
3484
3485         MediaWiki\suppressWarnings();
3486         $result = unpack( $format, $data );
3487         MediaWiki\restoreWarnings();
3488
3489         if ( $result === false ) {
3490                 // If it cannot extract the packed data.
3491                 throw new MWException( "unpack could not unpack binary data" );
3492         }
3493         return $result;
3494 }
3495
3496 /**
3497  * Determine if an image exists on the 'bad image list'.
3498  *
3499  * The format of MediaWiki:Bad_image_list is as follows:
3500  *    * Only list items (lines starting with "*") are considered
3501  *    * The first link on a line must be a link to a bad image
3502  *    * Any subsequent links on the same line are considered to be exceptions,
3503  *      i.e. articles where the image may occur inline.
3504  *
3505  * @param string $name The image name to check
3506  * @param Title|bool $contextTitle The page on which the image occurs, if known
3507  * @param string $blacklist Wikitext of a file blacklist
3508  * @return bool
3509  */
3510 function wfIsBadImage( $name, $contextTitle = false, $blacklist = null ) {
3511         # Handle redirects; callers almost always hit wfFindFile() anyway,
3512         # so just use that method because it has a fast process cache.
3513         $file = wfFindFile( $name ); // get the final name
3514         $name = $file ? $file->getTitle()->getDBkey() : $name;
3515
3516         # Run the extension hook
3517         $bad = false;
3518         if ( !Hooks::run( 'BadImage', [ $name, &$bad ] ) ) {
3519                 return $bad;
3520         }
3521
3522         $cache = ObjectCache::getLocalServerInstance( 'hash' );
3523         $key = wfMemcKey( 'bad-image-list', ( $blacklist === null ) ? 'default' : md5( $blacklist ) );
3524         $badImages = $cache->get( $key );
3525
3526         if ( $badImages === false ) { // cache miss
3527                 if ( $blacklist === null ) {
3528                         $blacklist = wfMessage( 'bad_image_list' )->inContentLanguage()->plain(); // site list
3529                 }
3530                 # Build the list now
3531                 $badImages = [];
3532                 $lines = explode( "\n", $blacklist );
3533                 foreach ( $lines as $line ) {
3534                         # List items only
3535                         if ( substr( $line, 0, 1 ) !== '*' ) {
3536                                 continue;
3537                         }
3538
3539                         # Find all links
3540                         $m = [];
3541                         if ( !preg_match_all( '/\[\[:?(.*?)\]\]/', $line, $m ) ) {
3542                                 continue;
3543                         }
3544
3545                         $exceptions = [];
3546                         $imageDBkey = false;
3547                         foreach ( $m[1] as $i => $titleText ) {
3548                                 $title = Title::newFromText( $titleText );
3549                                 if ( !is_null( $title ) ) {
3550                                         if ( $i == 0 ) {
3551                                                 $imageDBkey = $title->getDBkey();
3552                                         } else {
3553                                                 $exceptions[$title->getPrefixedDBkey()] = true;
3554                                         }
3555                                 }
3556                         }
3557
3558                         if ( $imageDBkey !== false ) {
3559                                 $badImages[$imageDBkey] = $exceptions;
3560                         }
3561                 }
3562                 $cache->set( $key, $badImages, 60 );
3563         }
3564
3565         $contextKey = $contextTitle ? $contextTitle->getPrefixedDBkey() : false;
3566         $bad = isset( $badImages[$name] ) && !isset( $badImages[$name][$contextKey] );
3567
3568         return $bad;
3569 }
3570
3571 /**
3572  * Determine whether the client at a given source IP is likely to be able to
3573  * access the wiki via HTTPS.
3574  *
3575  * @param string $ip The IPv4/6 address in the normal human-readable form
3576  * @return bool
3577  */
3578 function wfCanIPUseHTTPS( $ip ) {
3579         $canDo = true;
3580         Hooks::run( 'CanIPUseHTTPS', [ $ip, &$canDo ] );
3581         return !!$canDo;
3582 }
3583
3584 /**
3585  * Determine input string is represents as infinity
3586  *
3587  * @param string $str The string to determine
3588  * @return bool
3589  * @since 1.25
3590  */
3591 function wfIsInfinity( $str ) {
3592         $infinityValues = [ 'infinite', 'indefinite', 'infinity', 'never' ];
3593         return in_array( $str, $infinityValues );
3594 }
3595
3596 /**
3597  * Returns true if these thumbnail parameters match one that MediaWiki
3598  * requests from file description pages and/or parser output.
3599  *
3600  * $params is considered non-standard if they involve a non-standard
3601  * width or any non-default parameters aside from width and page number.
3602  * The number of possible files with standard parameters is far less than
3603  * that of all combinations; rate-limiting for them can thus be more generious.
3604  *
3605  * @param File $file
3606  * @param array $params
3607  * @return bool
3608  * @since 1.24 Moved from thumb.php to GlobalFunctions in 1.25
3609  */
3610 function wfThumbIsStandard( File $file, array $params ) {
3611         global $wgThumbLimits, $wgImageLimits, $wgResponsiveImages;
3612
3613         $multipliers = [ 1 ];
3614         if ( $wgResponsiveImages ) {
3615                 // These available sizes are hardcoded currently elsewhere in MediaWiki.
3616                 // @see Linker::processResponsiveImages
3617                 $multipliers[] = 1.5;
3618                 $multipliers[] = 2;
3619         }
3620
3621         $handler = $file->getHandler();
3622         if ( !$handler || !isset( $params['width'] ) ) {
3623                 return false;
3624         }
3625
3626         $basicParams = [];
3627         if ( isset( $params['page'] ) ) {
3628                 $basicParams['page'] = $params['page'];
3629         }
3630
3631         $thumbLimits = [];
3632         $imageLimits = [];
3633         // Expand limits to account for multipliers
3634         foreach ( $multipliers as $multiplier ) {
3635                 $thumbLimits = array_merge( $thumbLimits, array_map(
3636                         function ( $width ) use ( $multiplier ) {
3637                                 return round( $width * $multiplier );
3638                         }, $wgThumbLimits )
3639                 );
3640                 $imageLimits = array_merge( $imageLimits, array_map(
3641                         function ( $pair ) use ( $multiplier ) {
3642                                 return [
3643                                         round( $pair[0] * $multiplier ),
3644                                         round( $pair[1] * $multiplier ),
3645                                 ];
3646                         }, $wgImageLimits )
3647                 );
3648         }
3649
3650         // Check if the width matches one of $wgThumbLimits
3651         if ( in_array( $params['width'], $thumbLimits ) ) {
3652                 $normalParams = $basicParams + [ 'width' => $params['width'] ];
3653                 // Append any default values to the map (e.g. "lossy", "lossless", ...)
3654                 $handler->normaliseParams( $file, $normalParams );
3655         } else {
3656                 // If not, then check if the width matchs one of $wgImageLimits
3657                 $match = false;
3658                 foreach ( $imageLimits as $pair ) {
3659                         $normalParams = $basicParams + [ 'width' => $pair[0], 'height' => $pair[1] ];
3660                         // Decide whether the thumbnail should be scaled on width or height.
3661                         // Also append any default values to the map (e.g. "lossy", "lossless", ...)
3662                         $handler->normaliseParams( $file, $normalParams );
3663                         // Check if this standard thumbnail size maps to the given width
3664                         if ( $normalParams['width'] == $params['width'] ) {
3665                                 $match = true;
3666                                 break;
3667                         }
3668                 }
3669                 if ( !$match ) {
3670                         return false; // not standard for description pages
3671                 }
3672         }
3673
3674         // Check that the given values for non-page, non-width, params are just defaults
3675         foreach ( $params as $key => $value ) {
3676                 if ( !isset( $normalParams[$key] ) || $normalParams[$key] != $value ) {
3677                         return false;
3678                 }
3679         }
3680
3681         return true;
3682 }
3683
3684 /**
3685  * Merges two (possibly) 2 dimensional arrays into the target array ($baseArray).
3686  *
3687  * Values that exist in both values will be combined with += (all values of the array
3688  * of $newValues will be added to the values of the array of $baseArray, while values,
3689  * that exists in both, the value of $baseArray will be used).
3690  *
3691  * @param array $baseArray The array where you want to add the values of $newValues to
3692  * @param array $newValues An array with new values
3693  * @return array The combined array
3694  * @since 1.26
3695  */
3696 function wfArrayPlus2d( array $baseArray, array $newValues ) {
3697         // First merge items that are in both arrays
3698         foreach ( $baseArray as $name => &$groupVal ) {
3699                 if ( isset( $newValues[$name] ) ) {
3700                         $groupVal += $newValues[$name];
3701                 }
3702         }
3703         // Now add items that didn't exist yet
3704         $baseArray += $newValues;
3705
3706         return $baseArray;
3707 }