elkarte /
Elkarte
| Total Complexity | 70 |
| Total Lines | 510 |
| Duplicated Lines | 0 % |
| Changes | 0 | ||
Complex classes like UnTgz often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use UnTgz, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 33 | class UnTgz |
||
| 34 | { |
||
| 35 | /** @var array Holds the return array of files processed */ |
||
| 36 | protected $return = []; |
||
| 37 | |||
| 38 | /** @var array Holds the data found in each tar file header block */ |
||
| 39 | protected $_current = []; |
||
| 40 | |||
| 41 | /** @var int Holds the file pointer, generally to the 512 block we are working on */ |
||
| 42 | protected $_offset = 0; |
||
| 43 | |||
| 44 | /** @var bool If the file passes or fails crc check */ |
||
| 45 | protected $_crc_check = false; |
||
| 46 | |||
| 47 | /** @var string|int The current crc value of the data */ |
||
| 48 | protected $_crc; |
||
| 49 | |||
| 50 | /** @var int The claimed size of the data in the tarball */ |
||
| 51 | protected $_size; |
||
| 52 | |||
| 53 | /** @var bool If we are going to write out the files processed */ |
||
| 54 | protected $_write_this = false; |
||
| 55 | |||
| 56 | /** @var bool If to skip a file we found */ |
||
| 57 | protected $_skip = false; |
||
| 58 | |||
| 59 | /** @var bool If we found a file that was requested ($files_to_extract) */ |
||
| 60 | protected $_found = false; |
||
| 61 | |||
| 62 | /** @var array|string Current file header we are working on */ |
||
| 63 | protected $_header = []; |
||
| 64 | |||
| 65 | /** @var null|string[] Array of file names we want to extract from the archive */ |
||
| 66 | protected $files_to_extract; |
||
| 67 | |||
| 68 | /** @var FileFunctions The file functions class */ |
||
| 69 | protected $fileFunc; |
||
| 70 | |||
| 71 | /** @var string Holds the data string passed to the function */ |
||
| 72 | protected $data; |
||
| 73 | |||
| 74 | /** @var string Location to write the files. */ |
||
| 75 | protected $destination; |
||
| 76 | |||
| 77 | /** @var bool|string If we are looking for a single specific file */ |
||
| 78 | protected $single_file; |
||
| 79 | |||
| 80 | /** @var bool If we can overwrite a file with the same name in the destination */ |
||
| 81 | protected $overwrite; |
||
| 82 | |||
| 83 | /** |
||
| 84 | * Class initialization, passes variables, loads dependencies |
||
| 85 | * |
||
| 86 | * @param string $data |
||
| 87 | * @param string $destination |
||
| 88 | * @param bool|string $single_file |
||
| 89 | * @param bool $overwrite |
||
| 90 | * @param null|string[] $files_to_extract |
||
| 91 | * |
||
| 92 | * @throws Exception package_no_zlib |
||
| 93 | */ |
||
| 94 | public function __construct($data, $destination, $single_file = false, $overwrite = false, $files_to_extract = null) |
||
| 134 | } |
||
| 135 | |||
| 136 | /** |
||
| 137 | * Class controller, calls the ungzip / untar functions in required order |
||
| 138 | * |
||
| 139 | * @return bool|array |
||
| 140 | */ |
||
| 141 | public function read_tgz_data() |
||
| 142 | { |
||
| 143 | // Snif test that this is a .tgz tar.gz file |
||
| 144 | if (empty($this->_header) && !$this->check_valid_tgz()) |
||
| 145 | { |
||
| 146 | return false; |
||
| 147 | } |
||
| 148 | |||
| 149 | // The tgz information for this archive |
||
| 150 | if ($this->_read_header_tgz() === false) |
||
| 151 | { |
||
| 152 | return false; |
||
| 153 | } |
||
| 154 | |||
| 155 | // With the offset found, read and deflate the archive data |
||
| 156 | if ($this->_ungzip_data() === false) |
||
| 157 | { |
||
| 158 | return false; |
||
| 159 | } |
||
| 160 | |||
| 161 | // With the archive data in hand, we need to un tarball it |
||
| 162 | $this->_process_files(); |
||
| 163 | |||
| 164 | // Looking for a single file and this is it |
||
| 165 | if ($this->_found && $this->single_file) |
||
| 166 | { |
||
| 167 | return $this->_crc_check ? $this->_found : false; |
||
| 168 | } |
||
| 169 | |||
| 170 | // Wanted many files then we need to clean up |
||
| 171 | if ($this->destination !== null && !$this->single_file) |
||
| 172 | { |
||
| 173 | package_flush_cache(); |
||
| 174 | } |
||
| 175 | |||
| 176 | if ($this->single_file) |
||
| 177 | { |
||
| 178 | return false; |
||
| 179 | } |
||
| 180 | |||
| 181 | return $this->return; |
||
| 182 | } |
||
| 183 | |||
| 184 | /** |
||
| 185 | * Loads the 10 byte header and validates its a tgz file |
||
| 186 | * |
||
| 187 | * @return bool |
||
| 188 | */ |
||
| 189 | public function check_valid_tgz() |
||
| 190 | { |
||
| 191 | // No signature? |
||
| 192 | if (strlen($this->data) < 10) |
||
| 193 | { |
||
| 194 | return false; |
||
| 195 | } |
||
| 196 | |||
| 197 | // Unpack the 10 byte signature so we can see what we have |
||
| 198 | $this->_header = unpack('H2a/H2b/Ct/Cf/Vmtime/Cxtra/Cos', substr($this->data, 0, 10)); |
||
| 199 | |||
| 200 | // The IDentification number, gzip must be 1f8b |
||
| 201 | return strtolower($this->_header['a'] . $this->_header['b']) === '1f8b'; |
||
| 202 | } |
||
| 203 | |||
| 204 | /** |
||
| 205 | * Reads the archive file header |
||
| 206 | * |
||
| 207 | * What it does: |
||
| 208 | * |
||
| 209 | * - validates that the file is a tar.gz |
||
| 210 | * - validates that it is compressed with deflate |
||
| 211 | * - processes header information such that we can set the start of archive data |
||
| 212 | * - archive comment |
||
| 213 | * - archive filename |
||
| 214 | * - header CRC |
||
| 215 | * |
||
| 216 | * Signature Definition: |
||
| 217 | * - identification byte 1 and 2: 2 bytes, 0x1f 0x8b |
||
| 218 | * - Compression Method: 1 byte |
||
| 219 | * - Flags: 1 byte |
||
| 220 | * - Last modification time Contains a POSIX timestamp, 4 bytes |
||
| 221 | * - Compression flags (or extra flags): 1 byte |
||
| 222 | * - Operating system, Value that indicates on which operating system file was created, 1 byte |
||
| 223 | */ |
||
| 224 | private function _read_header_tgz() |
||
| 225 | { |
||
| 226 | // Compression method needs to be 8 = deflate! |
||
| 227 | if ($this->_header['t'] !== 8) |
||
| 228 | { |
||
| 229 | return false; |
||
| 230 | } |
||
| 231 | |||
| 232 | // Each bit of this byte represents a processing flag as follows |
||
| 233 | // 0 fTEXT, 1 fHCRC, 2 fEXTRA, 3 fNAME, 4 fCOMMENT, 5 fENCRYPT, 6-7 reserved |
||
| 234 | $flags = $this->_header['f']; |
||
| 235 | |||
| 236 | // Start to read any data defined by the flags, its the data after the 10 byte header |
||
| 237 | $this->_offset = 10; |
||
| 238 | |||
| 239 | // fEXTRA flag set we simply skip over its entry and the length of its data |
||
| 240 | if (($flags & 4) !== 0) |
||
| 241 | { |
||
| 242 | $xlen = unpack('vxlen', substr($this->data, $this->_offset, 2)); |
||
| 243 | $this->_offset += $xlen['xlen'] + 2; |
||
| 244 | } |
||
| 245 | |||
| 246 | // Read the filename, its zero terminated |
||
| 247 | if (($flags & 8) !== 0) |
||
| 248 | { |
||
| 249 | $this->_header['filename'] = ''; |
||
| 250 | while ($this->data[$this->_offset] !== "\0") |
||
| 251 | { |
||
| 252 | $this->_header['filename'] .= $this->data[$this->_offset++]; |
||
| 253 | } |
||
| 254 | |||
| 255 | $this->_offset++; |
||
| 256 | } |
||
| 257 | |||
| 258 | // Read the comment, its also zero terminated |
||
| 259 | if (($flags & 16) !== 0) |
||
| 260 | { |
||
| 261 | $this->_header['comment'] = ''; |
||
| 262 | while ($this->data[$this->_offset] !== "\0") |
||
| 263 | { |
||
| 264 | $this->_header['comment'] .= $this->data[$this->_offset++]; |
||
| 265 | } |
||
| 266 | |||
| 267 | $this->_offset++; |
||
| 268 | } |
||
| 269 | |||
| 270 | // "Read" the header CRC $crc16 = unpack('vcrc16', substr($data, $this->_offset, 2)); |
||
| 271 | if (($flags & 2) !== 0) |
||
| 272 | { |
||
| 273 | $this->_offset += 2; |
||
| 274 | } |
||
| 275 | } |
||
| 276 | |||
| 277 | /** |
||
| 278 | * We now know where the start of the compressed data is in the archive |
||
| 279 | * The data is terminated with 4 bytes of CRC and 4 bytes of the original input size |
||
| 280 | */ |
||
| 281 | public function _ungzip_data() |
||
| 282 | { |
||
| 283 | // Unpack the crc and original size, its the trailing 8 bytes |
||
| 284 | $check = unpack('Vcrc32/Visize', substr($this->data, strlen($this->data) - 8)); |
||
| 285 | $this->_crc = $check['crc32']; |
||
| 286 | $this->_size = $check['isize']; |
||
| 287 | |||
| 288 | // Extract the data, in this case its the tarball |
||
| 289 | $this->data = @gzinflate(substr($this->data, $this->_offset, strlen($this->data) - 8 - $this->_offset)); |
||
| 290 | |||
| 291 | // Check the crc and the data size |
||
| 292 | if (!$this->_check_crc() || (strlen($this->data) !== $check['isize'])) |
||
| 293 | { |
||
| 294 | return false; |
||
| 295 | } |
||
| 296 | } |
||
| 297 | |||
| 298 | /** |
||
| 299 | * Checks the saved vs calculated crc values |
||
| 300 | */ |
||
| 301 | private function _check_crc() |
||
| 302 | { |
||
| 303 | // Make sure we have unsigned crc padded hex. |
||
| 304 | $crc_uncompressed = hash('crc32b', $this->data); |
||
| 305 | $this->_crc = str_pad(dechex($this->_crc), 8, '0', STR_PAD_LEFT); |
||
| 306 | |||
| 307 | return $this->data !== false && $this->_crc === $crc_uncompressed; |
||
| 308 | } |
||
| 309 | |||
| 310 | /** |
||
| 311 | * Does the work of un tarballing the now ungzip'ed tar file |
||
| 312 | * |
||
| 313 | * What it does |
||
| 314 | * - Assumes its Ustar format |
||
| 315 | */ |
||
| 316 | private function _process_files() |
||
| 317 | { |
||
| 318 | // Tar files are written in 512 byte chunks |
||
| 319 | $blocks = strlen($this->data) / 512 - 1; |
||
| 320 | $this->_offset = 0; |
||
| 321 | |||
| 322 | // While we have blocks to process |
||
| 323 | while ($this->_offset < $blocks) |
||
| 324 | { |
||
| 325 | $this->_read_current_header(); |
||
| 326 | |||
| 327 | // Blank record? This is probably at the end of the file. |
||
| 328 | if (empty($this->_current['filename'])) |
||
| 329 | { |
||
| 330 | $this->_offset += 512; |
||
| 331 | continue; |
||
| 332 | } |
||
| 333 | |||
| 334 | // If its a directory, lets make sure it ends in a / |
||
| 335 | if ($this->_current['type'] == 5 && substr($this->_current['filename'], -1) !== '/') |
||
| 336 | { |
||
| 337 | $this->_current['filename'] .= '/'; |
||
| 338 | } |
||
| 339 | |||
| 340 | // Figure out what we will do with the data once we have it |
||
| 341 | $this->_determine_write_this(); |
||
| 342 | |||
| 343 | // Read the files data, move the offset to the start of the following 512 block |
||
| 344 | $size = ceil($this->_current['size'] / 512); |
||
| 345 | $this->_current['data'] = substr($this->data, ++$this->_offset << 9, $this->_current['size']); |
||
| 346 | $this->_offset += $size; |
||
| 347 | |||
| 348 | // We can write this file or return its data or ... |
||
| 349 | if ($this->_write_this && $this->destination !== null) |
||
| 350 | { |
||
| 351 | $this->_write_this_file(); |
||
| 352 | |||
| 353 | if ($this->_skip) |
||
| 354 | { |
||
| 355 | continue; |
||
| 356 | } |
||
| 357 | |||
| 358 | if ($this->_found) |
||
| 359 | { |
||
| 360 | return; |
||
| 361 | } |
||
| 362 | } |
||
| 363 | |||
| 364 | if (substr($this->_current['filename'], -1) !== '/') |
||
| 365 | { |
||
| 366 | $this->return[] = [ |
||
| 367 | 'filename' => $this->_current['filename'], |
||
| 368 | 'md5' => md5($this->_current['data']), |
||
| 369 | 'preview' => substr($this->_current['data'], 0, 100), |
||
| 370 | 'size' => $this->_current['size'], |
||
| 371 | 'formatted_size' => byte_format($this->_current['size']), |
||
| 372 | 'skipped' => false, |
||
| 373 | 'crc' => $this->_crc_check, |
||
| 374 | ]; |
||
| 375 | } |
||
| 376 | } |
||
| 377 | } |
||
| 378 | |||
| 379 | /** |
||
| 380 | * Reads the tar file header block, its a 512 block and contains the following: |
||
| 381 | * |
||
| 382 | * Signature Definition: |
||
| 383 | * - char filename[100]; File name |
||
| 384 | * - char mode[8]; File mode |
||
| 385 | * - char uid[8]; Owner's numeric user ID |
||
| 386 | * - char gid[8]; Group's numeric user ID |
||
| 387 | * - char size[12]; File size in bytes (octal base) |
||
| 388 | * - char mtime[12]; Last modification time in numeric Unix time format (octal) |
||
| 389 | * - char checksum[8]; Checksum for header record |
||
| 390 | * - char type[1]; Link indicator (file type 0=normal, 1=hard, 2=symlink ... 5=directory ... |
||
| 391 | * - char linkname[100]; Name of linked file |
||
| 392 | * - char magic[6]; UStar indicator "ustar" |
||
| 393 | * - char version[2]; UStar version "00" |
||
| 394 | * - char uname[32]; Owner user name |
||
| 395 | * - char gname[32]; Owner group name |
||
| 396 | * - char devmajor[8]; Device major number |
||
| 397 | * - char devminor[8]; Device minor number |
||
| 398 | * - char path[155]; Filename prefix |
||
| 399 | */ |
||
| 400 | private function _read_current_header() |
||
| 401 | { |
||
| 402 | $octdec = ['mode', 'uid', 'gid', 'size', 'mtime', 'checksum', 'type']; |
||
| 403 | |||
| 404 | // Each file object is preceded by a 512-byte header record on 512 boundaries |
||
| 405 | $this->_header = substr($this->data, $this->_offset << 9, 512); |
||
| 406 | |||
| 407 | // Unpack |
||
| 408 | $this->_current = unpack('a100filename/a8mode/a8uid/a8gid/a12size/a12mtime/a8checksum/a1type/a100linkname/a6magic/a2version/a32uname/a32gname/a8devmajor/a8devminor/a155path', $this->_header); |
||
| 409 | |||
| 410 | // Clean the header fields, convert octal to decimal as needed |
||
| 411 | foreach ($this->_current as $key => $value) |
||
| 412 | { |
||
| 413 | if (in_array($key, $octdec)) |
||
| 414 | { |
||
| 415 | $value = trim($value); |
||
| 416 | if (!empty($value) && is_numeric($value)) |
||
| 417 | { |
||
| 418 | if (($value % 10) >= 8) |
||
| 419 | { |
||
| 420 | $value = decoct($value); |
||
| 421 | } |
||
| 422 | |||
| 423 | $value = octdec($value); |
||
| 424 | } |
||
| 425 | |||
| 426 | $this->_current[$key] = $value; |
||
| 427 | } |
||
| 428 | else |
||
| 429 | { |
||
| 430 | $this->_current[$key] = trim($value); |
||
| 431 | } |
||
| 432 | } |
||
| 433 | } |
||
| 434 | |||
| 435 | /** |
||
| 436 | * Does what it says, determines if we are writing this file or not |
||
| 437 | */ |
||
| 438 | private function _determine_write_this() |
||
| 466 | } |
||
| 467 | } |
||
| 468 | |||
| 469 | /** |
||
| 470 | * Does the actual writing of the file |
||
| 471 | * |
||
| 472 | * - Writes the extracted file to disk or if we are extracting a single file |
||
| 473 | * - it returns the extracted data |
||
| 474 | */ |
||
| 475 | private function _write_this_file() |
||
| 520 | } |
||
| 521 | |||
| 522 | /** |
||
| 523 | * Checks the saved vs calculated crc values |
||
| 524 | */ |
||
| 525 | private function _check_header_crc() |
||
| 543 | } |
||
| 544 | } |
||
| 545 |
Loading history...
The issue could also be caused by a filter entry in the build configuration. If the path has been excluded in your configuration, e.g.
excluded_paths: ["lib/*"], you can move it to the dependency path list as follows:For further information see https://scrutinizer-ci.com/docs/tools/php/php-scrutinizer/#list-dependency-paths