elkarte /
Elkarte
Duplicate code is one of the most pungent code smells. A rule that is often used is to re-structure code once it is duplicated in three or more places.
Common duplication problems, and corresponding solutions are:
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. You can also have a look at the cohesion graph to spot any un-connected, or weakly-connected components.
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 |
||
| 29 | class UnTgz |
||
| 30 | { |
||
| 31 | /** |
||
| 32 | * Holds the return array of files processed |
||
| 33 | * @var mixed[] |
||
| 34 | */ |
||
| 35 | protected $return = array(); |
||
| 36 | |||
| 37 | /** |
||
| 38 | * Holds the data found in each tar file header block |
||
| 39 | * @var mixed[] |
||
| 40 | */ |
||
| 41 | protected $_current = array(); |
||
| 42 | |||
| 43 | /** |
||
| 44 | * Holds the file pointer, generally to the 512 block we are working on |
||
| 45 | * @var int |
||
| 46 | */ |
||
| 47 | protected $_offset = 0; |
||
| 48 | |||
| 49 | /** |
||
| 50 | * If the file passes or fails crc check |
||
| 51 | * @var boolean |
||
| 52 | */ |
||
| 53 | protected $_crc_check = false; |
||
| 54 | |||
| 55 | /** |
||
| 56 | * The current crc value of the data |
||
| 57 | * @var string|int |
||
| 58 | */ |
||
| 59 | protected $_crc; |
||
| 60 | |||
| 61 | /** |
||
| 62 | * The claimed size of the data in the tarball |
||
| 63 | * @var int |
||
| 64 | */ |
||
| 65 | protected $_size; |
||
| 66 | |||
| 67 | /** |
||
| 68 | * If we are going to write out the files processed |
||
| 69 | * @var boolean |
||
| 70 | */ |
||
| 71 | protected $_write_this = false; |
||
| 72 | |||
| 73 | /** |
||
| 74 | * If we will skip a file we found |
||
| 75 | * @var boolean |
||
| 76 | */ |
||
| 77 | protected $_skip = false; |
||
| 78 | |||
| 79 | /** |
||
| 80 | * If we found a file that was requested ($files_to_extract) |
||
| 81 | * @var boolean |
||
| 82 | */ |
||
| 83 | protected $_found = false; |
||
| 84 | |||
| 85 | /** |
||
| 86 | * Current file header we are working on |
||
| 87 | * @var mixed[]|string |
||
| 88 | */ |
||
| 89 | protected $_header = array(); |
||
| 90 | |||
| 91 | /** |
||
| 92 | * Array of file names we want to extract from the archive |
||
| 93 | * @var null|string[] |
||
| 94 | */ |
||
| 95 | protected $files_to_extract; |
||
| 96 | |||
| 97 | /** |
||
| 98 | * Holds the data string passed to the function |
||
| 99 | * @var string |
||
| 100 | */ |
||
| 101 | protected $data; |
||
| 102 | |||
| 103 | /** |
||
| 104 | * Location to write the files. |
||
| 105 | * @var string |
||
| 106 | */ |
||
| 107 | protected $destination; |
||
| 108 | |||
| 109 | /** |
||
| 110 | * If we are looking for a single specific file |
||
| 111 | * @var boolean|string |
||
| 112 | */ |
||
| 113 | protected $single_file; |
||
| 114 | |||
| 115 | /** |
||
| 116 | * If we can overwrite a file with the same name in the destination |
||
| 117 | * @var boolean |
||
| 118 | */ |
||
| 119 | protected $overwrite; |
||
| 120 | |||
| 121 | /** |
||
| 122 | * Class initialization, passes variables, loads dependencies |
||
| 123 | * |
||
| 124 | * @param string $data |
||
| 125 | * @param string $destination |
||
| 126 | * @param bool|string $single_file |
||
| 127 | * @param bool $overwrite |
||
| 128 | * @param null|string[] $files_to_extract |
||
| 129 | * |
||
| 130 | * @throws Elk_Exception package_no_zlib |
||
| 131 | */ |
||
| 132 | View Code Duplication | public function __construct($data, $destination, $single_file = false, $overwrite = false, $files_to_extract = null) |
|
| 156 | |||
| 157 | /** |
||
| 158 | * Class controller, calls the ungzip / untar functions in required order |
||
| 159 | * |
||
| 160 | * @return boolean|array |
||
| 161 | */ |
||
| 162 | public function read_tgz_data() |
||
| 192 | |||
| 193 | /** |
||
| 194 | * Loads the 10 byte header and validates its a tgz file |
||
| 195 | * |
||
| 196 | * @return boolean |
||
| 197 | */ |
||
| 198 | public function check_valid_tgz() |
||
| 210 | |||
| 211 | /** |
||
| 212 | * Reads the archive file header |
||
| 213 | * |
||
| 214 | * What it does: |
||
| 215 | * |
||
| 216 | * - validates that the file is a tar.gz |
||
| 217 | * - validates that its compressed with deflate |
||
| 218 | * - processes header information so we can set the start of archive data |
||
| 219 | * - archive comment |
||
| 220 | * - archive filename |
||
| 221 | * - header CRC |
||
| 222 | * |
||
| 223 | * Signature Definition: |
||
| 224 | * - identification byte 1 and 2: 2 bytes, 0x1f 0x8b |
||
| 225 | * - Compression Method: 1 byte |
||
| 226 | * - Flags: 1 byte |
||
| 227 | * - Last modification time Contains a POSIX timestamp, 4 bytes |
||
| 228 | * - Compression flags (or extra flags): 1 byte |
||
| 229 | * - Operating system, Value that indicates on which operating system file was created, 1 byte |
||
| 230 | */ |
||
| 231 | private function _read_header_tgz() |
||
| 273 | |||
| 274 | /** |
||
| 275 | * We now know where the start of the compressed data is in the archive |
||
| 276 | * The data is terminated with 4 bytes of CRC and 4 bytes of the original input size |
||
| 277 | */ |
||
| 278 | public function _ungzip_data() |
||
| 292 | |||
| 293 | /** |
||
| 294 | * Does the work of un tarballing the now ungzip'ed tar file |
||
| 295 | * |
||
| 296 | * What it does |
||
| 297 | * - Assumes its Ustar format |
||
| 298 | */ |
||
| 299 | private function _process_files() |
||
| 354 | |||
| 355 | /** |
||
| 356 | * Reads the tar file header block, its a 512 block and contains the following: |
||
| 357 | * |
||
| 358 | * Signature Definition: |
||
| 359 | * - char filename[100]; File name |
||
| 360 | * - char mode[8]; File mode |
||
| 361 | * - char uid[8]; Owner's numeric user ID |
||
| 362 | * - char gid[8]; Group's numeric user ID |
||
| 363 | * - char size[12]; File size in bytes (octal base) |
||
| 364 | * - char mtime[12]; Last modification time in numeric Unix time format (octal) |
||
| 365 | * - char checksum[8]; Checksum for header record |
||
| 366 | * - char type[1]; Link indicator (file type 0=normal, 1=hard, 2=symlink ... 5=directory ... |
||
| 367 | * - char linkname[100]; Name of linked file |
||
| 368 | * - char magic[6]; UStar indicator "ustar" |
||
| 369 | * - char version[2]; UStar version "00" |
||
| 370 | * - char uname[32]; Owner user name |
||
| 371 | * - char gname[32]; Owner group name |
||
| 372 | * - char devmajor[8]; Device major number |
||
| 373 | * - char devminor[8]; Device minor number |
||
| 374 | * - char path[155]; Filename prefix |
||
| 375 | */ |
||
| 376 | private function _read_current_header() |
||
| 395 | |||
| 396 | /** |
||
| 397 | * Does what it says, determines if we are writing this file or not |
||
| 398 | */ |
||
| 399 | private function _determine_write_this() |
||
| 420 | |||
| 421 | /** |
||
| 422 | * Does the actual writing of the file |
||
| 423 | * |
||
| 424 | * - Writes the extracted file to disk or if we are extracting a single file |
||
| 425 | * - it returns the extracted data |
||
| 426 | */ |
||
| 427 | private function _write_this_file() |
||
| 450 | |||
| 451 | /** |
||
| 452 | * Checks the saved vs calculated crc values |
||
| 453 | */ |
||
| 454 | private function _check_crc() |
||
| 462 | |||
| 463 | /** |
||
| 464 | * Checks the saved vs calculated crc values |
||
| 465 | */ |
||
| 466 | private function _check_header_crc() |
||
| 480 | } |
||
| 481 |
