MediaWiki  master
MSCompoundFileReader.php
Go to the documentation of this file.
1 <?php
2 /*
3  * Copyright 2019 Wikimedia Foundation
4  *
5  * Licensed under the Apache License, Version 2.0 (the "License"); you may
6  * not use this file except in compliance with the License.
7  * You may obtain a copy of the License at
8  *
9  * http://www.apache.org/licenses/LICENSE-2.0
10  *
11  * Unless required by applicable law or agreed to in writing, software distributed
12  * under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS
13  * OF ANY KIND, either express or implied. See the License for the
14  * specific language governing permissions and limitations under the License.
15  */
16 
33  private $file;
34  private $header;
35  private $mime;
36  private $mimeFromClsid;
37  private $error;
38  private $errorCode;
39  private $valid = false;
40 
41  private $sectorLength;
42  private $difat;
43  private $fat = [];
44  private $fileLength;
45 
46  const TYPE_UNALLOCATED = 0;
47  const TYPE_STORAGE = 1;
48  const TYPE_STREAM = 2;
49  const TYPE_ROOT = 5;
50 
51  const ERROR_FILE_OPEN = 1;
52  const ERROR_SEEK = 2;
53  const ERROR_READ = 3;
57 
58  private static $mimesByClsid = [
59  // From http://justsolve.archiveteam.org/wiki/Microsoft_Compound_File
60  '00020810-0000-0000-C000-000000000046' => 'application/vnd.ms-excel',
61  '00020820-0000-0000-C000-000000000046' => 'application/vnd.ms-excel',
62  '00020906-0000-0000-C000-000000000046' => 'application/msword',
63  '64818D10-4F9B-11CF-86EA-00AA00B929E8' => 'application/vnd.ms-powerpoint',
64  ];
65 
78  public static function readFile( $fileName ) {
79  $handle = fopen( $fileName, 'r' );
80  if ( $handle === false ) {
81  return [
82  'valid' => false,
83  'error' => 'file does not exist',
84  'errorCode' => self::ERROR_FILE_OPEN
85  ];
86  }
87  return self::readHandle( $handle );
88  }
89 
102  public static function readHandle( $fileHandle ) {
103  $reader = new self( $fileHandle );
104  $info = [
105  'valid' => $reader->valid,
106  'mime' => $reader->mime,
107  'mimeFromClsid' => $reader->mimeFromClsid
108  ];
109  if ( $reader->error ) {
110  $info['error'] = $reader->error;
111  $info['errorCode'] = $reader->errorCode;
112  }
113  return $info;
114  }
115 
116  private function __construct( $fileHandle ) {
117  $this->file = $fileHandle;
118  try {
119  $this->init();
120  } catch ( RuntimeException $e ) {
121  $this->valid = false;
122  $this->error = $e->getMessage();
123  $this->errorCode = $e->getCode();
124  }
125  }
126 
127  private function init() {
128  $this->header = $this->unpackOffset( 0, [
129  'header_signature' => 8,
130  'header_clsid' => 16,
131  'minor_version' => 2,
132  'major_version' => 2,
133  'byte_order' => 2,
134  'sector_shift' => 2,
135  'mini_sector_shift' => 2,
136  'reserved' => 6,
137  'num_dir_sectors' => 4,
138  'num_fat_sectors' => 4,
139  'first_dir_sector' => 4,
140  'transaction_signature_number' => 4,
141  'mini_stream_cutoff_size' => 4,
142  'first_mini_fat_sector' => 4,
143  'num_mini_fat_sectors' => 4,
144  'first_difat_sector' => 4,
145  'num_difat_sectors' => 4,
146  'difat' => 436,
147  ] );
148  if ( $this->header['header_signature'] !== "\xd0\xcf\x11\xe0\xa1\xb1\x1a\xe1" ) {
149  $this->error( 'invalid signature: ' . bin2hex( $this->header['header_signature'] ),
150  self::ERROR_INVALID_SIGNATURE );
151  }
152  $this->sectorLength = 1 << $this->header['sector_shift'];
153  $this->readDifat();
154  $this->readDirectory();
155 
156  $this->valid = true;
157  }
158 
159  private function sectorOffset( $sectorId ) {
160  return $this->sectorLength * ( $sectorId + 1 );
161  }
162 
163  private function decodeClsid( $binaryClsid ) {
164  $parts = unpack( 'Va/vb/vc/C8d', $binaryClsid );
165  return sprintf( "%08X-%04X-%04X-%02X%02X-%02X%02X%02X%02X%02X%02X",
166  $parts['a'],
167  $parts['b'],
168  $parts['c'],
169  $parts['d1'],
170  $parts['d2'],
171  $parts['d3'],
172  $parts['d4'],
173  $parts['d5'],
174  $parts['d6'],
175  $parts['d7'],
176  $parts['d8']
177  );
178  }
179 
180  private function unpackOffset( $offset, $struct ) {
181  $block = $this->readOffset( $offset, array_sum( $struct ) );
182  return $this->unpack( $block, 0, $struct );
183  }
184 
185  private function unpackSector( $sectorNumber, $struct ) {
186  $offset = $this->sectorOffset( $sectorNumber );
187  return $this->unpackOffset( $offset, array_sum( $struct ) );
188  }
189 
190  private function unpack( $block, $offset, $struct ) {
191  $data = [];
192  foreach ( $struct as $key => $length ) {
193  if ( $length > 4 ) {
194  $data[$key] = substr( $block, $offset, $length );
195  } else {
196  $data[$key] = $this->bin2dec( $block, $offset, $length );
197  }
198  $offset += $length;
199  }
200  return $data;
201  }
202 
203  private function bin2dec( $str, $offset, $length ) {
204  $value = 0;
205  for ( $i = $length - 1; $i >= 0; $i-- ) {
206  $value *= 256;
207  $value += ord( $str[$offset + $i] );
208  }
209  return $value;
210  }
211 
212  private function readOffset( $offset, $length ) {
213  $this->fseek( $offset );
214  Wikimedia\suppressWarnings();
215  $block = fread( $this->file, $length );
216  Wikimedia\restoreWarnings();
217  if ( $block === false ) {
218  $this->error( 'error reading from file', self::ERROR_READ );
219  }
220  if ( strlen( $block ) !== $length ) {
221  $this->error( 'unable to read the required number of bytes from the file',
222  self::ERROR_READ_PAST_END );
223  }
224  return $block;
225  }
226 
227  private function readSector( $sectorId ) {
228  return $this->readOffset( $this->sectorOffset( $sectorId ), 1 << $this->header['sector_shift'] );
229  }
230 
231  private function error( $message, $code ) {
232  throw new RuntimeException( $message, $code );
233  }
234 
235  private function fseek( $offset ) {
236  Wikimedia\suppressWarnings();
237  $result = fseek( $this->file, $offset );
238  Wikimedia\restoreWarnings();
239  if ( $result !== 0 ) {
240  $this->error( "unable to seek to offset $offset", self::ERROR_SEEK );
241  }
242  }
243 
244  private function readDifat() {
245  $binaryDifat = $this->header['difat'];
246  $nextDifatSector = $this->header['first_difat_sector'];
247  for ( $i = 0; $i < $this->header['num_difat_sectors']; $i++ ) {
248  $block = $this->readSector( $nextDifatSector );
249  $binaryDifat .= substr( $block, 0, $this->sectorLength - 4 );
250  $nextDifatSector = $this->bin2dec( $block, $this->sectorLength - 4, 4 );
251  if ( $nextDifatSector == 0xFFFFFFFE ) {
252  break;
253  }
254  }
255 
256  $this->difat = [];
257  for ( $pos = 0; $pos < strlen( $binaryDifat ); $pos += 4 ) {
258  $fatSector = $this->bin2dec( $binaryDifat, $pos, 4 );
259  if ( $fatSector < 0xFFFFFFFC ) {
260  $this->difat[] = $fatSector;
261  } else {
262  break;
263  }
264  }
265  }
266 
267  private function getNextSectorIdFromFat( $sectorId ) {
268  $entriesPerSector = intdiv( $this->sectorLength, 4 );
269  $fatSectorId = intdiv( $sectorId, $entriesPerSector );
270  $fatSectorArray = $this->getFatSector( $fatSectorId );
271  return $fatSectorArray[$sectorId % $entriesPerSector];
272  }
273 
274  private function getFatSector( $fatSectorId ) {
275  if ( !isset( $this->fat[$fatSectorId] ) ) {
276  $fat = [];
277  if ( !isset( $this->difat[$fatSectorId] ) ) {
278  $this->error( 'FAT sector requested beyond the end of the DIFAT', self::ERROR_INVALID_FORMAT );
279  }
280  $absoluteSectorId = $this->difat[$fatSectorId];
281  $block = $this->readSector( $absoluteSectorId );
282  for ( $pos = 0; $pos < strlen( $block ); $pos += 4 ) {
283  $fat[] = $this->bin2dec( $block, $pos, 4 );
284  }
285  $this->fat[$fatSectorId] = $fat;
286  }
287  return $this->fat[$fatSectorId];
288  }
289 
290  private function readDirectory() {
291  $dirSectorId = $this->header['first_dir_sector'];
292  $binaryDir = '';
293  $seenSectorIds = [];
294  while ( $dirSectorId !== 0xFFFFFFFE ) {
295  if ( isset( $seenSectorIds[$dirSectorId] ) ) {
296  $this->error( 'FAT loop detected', self::ERROR_INVALID_FORMAT );
297  }
298  $seenSectorIds[$dirSectorId] = true;
299 
300  $binaryDir .= $this->readSector( $dirSectorId );
301  $dirSectorId = $this->getNextSectorIdFromFat( $dirSectorId );
302  }
303 
304  $struct = [
305  'name_raw' => 64,
306  'name_length' => 2,
307  'object_type' => 1,
308  'color' => 1,
309  'sid_left' => 4,
310  'sid_right' => 4,
311  'sid_child' => 4,
312  'clsid' => 16,
313  'state_bits' => 4,
314  'create_time_low' => 4,
315  'create_time_high' => 4,
316  'modify_time_low' => 4,
317  'modify_time_high' => 4,
318  'first_sector' => 4,
319  'size_low' => 4,
320  'size_high' => 4,
321  ];
322  $entryLength = array_sum( $struct );
323 
324  for ( $pos = 0; $pos < strlen( $binaryDir ); $pos += $entryLength ) {
325  $entry = $this->unpack( $binaryDir, $pos, $struct );
326 
327  // According to [MS-CFB] size_high may contain garbage due to a
328  // bug in a writer, it's best to pretend it is zero
329  $entry['size_high'] = 0;
330 
331  $type = $entry['object_type'];
332  if ( $type == self::TYPE_UNALLOCATED ) {
333  continue;
334  }
335 
336  $name = iconv( 'UTF-16', 'UTF-8', substr( $entry['name_raw'], 0, $entry['name_length'] - 2 ) );
337 
338  $clsid = $this->decodeClsid( $entry['clsid'] );
339  if ( $type == self::TYPE_ROOT && isset( self::$mimesByClsid[$clsid] ) ) {
340  $this->mimeFromClsid = self::$mimesByClsid[$clsid];
341  }
342 
343  if ( $name === 'Workbook' ) {
344  $this->mime = 'application/vnd.ms-excel';
345  } elseif ( $name === 'WordDocument' ) {
346  $this->mime = 'application/msword';
347  } elseif ( $name === 'PowerPoint Document' ) {
348  $this->mime = 'application/vnd.ms-powerpoint';
349  }
350  }
351  }
352 }
$data
Utility to generate mapping file used in mw.Title (phpCharToUpper.json)
div flags Integer display flags(NO_ACTION_LINK, NO_EXTRA_USER_LINKS) 'LogException' returning false will NOT prevent logging $e
Definition: hooks.txt:2159
Read the directory of a Microsoft Compound File Binary file, a.k.a.
$value
readOffset( $offset, $length)
unpack( $block, $offset, $struct)
The index of the header message $result[1]=The index of the body text message $result[2 through n]=Parameters passed to body text message. Please note the header message cannot receive/use parameters. 'ImportHandleLogItemXMLTag':When parsing a XML tag in a log item. Return false to stop further processing of the tag $reader:XMLReader object $logInfo:Array of information 'ImportHandlePageXMLTag':When parsing a XML tag in a page. Return false to stop further processing of the tag $reader:XMLReader object & $pageInfo:Array of information 'ImportHandleRevisionXMLTag':When parsing a XML tag in a page revision. Return false to stop further processing of the tag $reader:XMLReader object $pageInfo:Array of page information $revisionInfo:Array of revision information 'ImportHandleToplevelXMLTag':When parsing a top level XML tag. Return false to stop further processing of the tag $reader:XMLReader object 'ImportHandleUnknownUser':When a user doesn 't exist locally, this hook is called to give extensions an opportunity to auto-create it. If the auto-creation is successful, return false. $name:User name 'ImportHandleUploadXMLTag':When parsing a XML tag in a file upload. Return false to stop further processing of the tag $reader:XMLReader object $revisionInfo:Array of information 'ImportLogInterwikiLink':Hook to change the interwiki link used in log entries and edit summaries for transwiki imports. & $fullInterwikiPrefix:Interwiki prefix, may contain colons. & $pageTitle:String that contains page title. 'ImportSources':Called when reading from the $wgImportSources configuration variable. Can be used to lazy-load the import sources list. & $importSources:The value of $wgImportSources. Modify as necessary. See the comment in DefaultSettings.php for the detail of how to structure this array. 'InfoAction':When building information to display on the action=info page. $context:IContextSource object & $pageInfo:Array of information 'InitializeArticleMaybeRedirect':MediaWiki check to see if title is a redirect. & $title:Title object for the current page & $request:WebRequest & $ignoreRedirect:boolean to skip redirect check & $target:Title/string of redirect target & $article:Article object 'InternalParseBeforeLinks':during Parser 's internalParse method before links but after nowiki/noinclude/includeonly/onlyinclude and other processings. & $parser:Parser object & $text:string containing partially parsed text & $stripState:Parser 's internal StripState object 'InternalParseBeforeSanitize':during Parser 's internalParse method just before the parser removes unwanted/dangerous HTML tags and after nowiki/noinclude/includeonly/onlyinclude and other processings. Ideal for syntax-extensions after template/parser function execution which respect nowiki and HTML-comments. & $parser:Parser object & $text:string containing partially parsed text & $stripState:Parser 's internal StripState object 'InterwikiLoadPrefix':When resolving if a given prefix is an interwiki or not. Return true without providing an interwiki to continue interwiki search. $prefix:interwiki prefix we are looking for. & $iwData:output array describing the interwiki with keys iw_url, iw_local, iw_trans and optionally iw_api and iw_wikiid. 'InvalidateEmailComplete':Called after a user 's email has been invalidated successfully. $user:user(object) whose email is being invalidated 'IRCLineURL':When constructing the URL to use in an IRC notification. Callee may modify $url and $query, URL will be constructed as $url . $query & $url:URL to index.php & $query:Query string $rc:RecentChange object that triggered url generation 'IsFileCacheable':Override the result of Article::isFileCacheable()(if true) & $article:article(object) being checked 'IsTrustedProxy':Override the result of IP::isTrustedProxy() & $ip:IP being check & $result:Change this value to override the result of IP::isTrustedProxy() 'IsUploadAllowedFromUrl':Override the result of UploadFromUrl::isAllowedUrl() $url:URL used to upload from & $allowed:Boolean indicating if uploading is allowed for given URL 'isValidEmailAddr':Override the result of Sanitizer::validateEmail(), for instance to return false if the domain name doesn 't match your organization. $addr:The e-mail address entered by the user & $result:Set this and return false to override the internal checks 'isValidPassword':Override the result of User::isValidPassword() $password:The password entered by the user & $result:Set this and return false to override the internal checks $user:User the password is being validated for 'Language::getMessagesFileName':$code:The language code or the language we 're looking for a messages file for & $file:The messages file path, you can override this to change the location. 'LanguageGetNamespaces':Provide custom ordering for namespaces or remove namespaces. Do not use this hook to add namespaces. Use CanonicalNamespaces for that. & $namespaces:Array of namespaces indexed by their numbers 'LanguageGetTranslatedLanguageNames':Provide translated language names. & $names:array of language code=> language name $code:language of the preferred translations 'LanguageLinks':Manipulate a page 's language links. This is called in various places to allow extensions to define the effective language links for a page. $title:The page 's Title. & $links:Array with elements of the form "language:title" in the order that they will be output. & $linkFlags:Associative array mapping prefixed links to arrays of flags. Currently unused, but planned to provide support for marking individual language links in the UI, e.g. for featured articles. 'LanguageSelector':Hook to change the language selector available on a page. $out:The output page. $cssClassName:CSS class name of the language selector. 'LinkBegin':DEPRECATED since 1.28! Use HtmlPageLinkRendererBegin instead. Used when generating internal and interwiki links in Linker::link(), before processing starts. Return false to skip default processing and return $ret. See documentation for Linker::link() for details on the expected meanings of parameters. $skin:the Skin object $target:the Title that the link is pointing to & $html:the contents that the< a > tag should have(raw HTML) $result
Definition: hooks.txt:1980
static readHandle( $fileHandle)
Read from an open seekable handle.
Using a hook running we can avoid having all this option specific stuff in our mainline code Using the function We ve cleaned up the code here by removing clumps of infrequently used code and moving them off somewhere else It s much easier for someone working with this code to see what s _really_ going and make changes or fix bugs In we can take all the code that deals with the little used title reversing we can concentrate it all in an extension file
Definition: hooks.txt:91
unpackSector( $sectorNumber, $struct)
bin2dec( $str, $offset, $length)
unpackOffset( $offset, $struct)
static static readFile( $fileName)
Read a file by name.
this hook is for auditing only or null if authentication failed before getting that far or null if we can t even determine that When $user is not it can be in the form of< username >< more info > e g for bot passwords intended to be added to log contexts Fields it might only if the login was with a bot password it is not rendered in wiki pages or galleries in category pages allow injecting custom HTML after the section Any uses of the hook need to handle escaping see BaseTemplate::getToolbox and BaseTemplate::makeListItem for details on the format of individual items inside of this array or by returning and letting standard HTTP rendering take place modifiable or by returning false and taking over the output modifiable & $code
Definition: hooks.txt:780
This document is intended to provide useful advice for parties seeking to redistribute MediaWiki to end users It s targeted particularly at maintainers for Linux since it s been observed that distribution packages of MediaWiki often break We ve consistently had to recommend that users seeking support use official tarballs instead of their distribution s and this often solves whatever problem the user is having It would be nice if this could such as
Definition: distributors.txt:9
injection txt This is an overview of how MediaWiki makes use of dependency injection The design described here grew from the discussion of RFC T384 The term dependency this means that anything an object needs to operate should be injected from the the object itself should only know narrow no concrete implementation of the logic it relies on The requirement to inject everything typically results in an architecture that based on two main types of and essentially stateless service objects that use other service objects to operate on the value objects As of the beginning MediaWiki is only starting to use the DI approach Much of the code still relies on global state or direct resulting in a highly cyclical dependency which acts as the top level factory for services in MediaWiki which can be used to gain access to default instances of various services MediaWikiServices however also allows new services to be defined and default services to be redefined Services are defined or redefined by providing a callback the instantiator that will return a new instance of the service When it will create an instance of MediaWikiServices and populate it with the services defined in the files listed by thereby bootstrapping the DI framework Per $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:35
Allows to change the fields on the form that will be generated $name
Definition: hooks.txt:271
static $fileHandle
Definition: cdb.php:57