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 CHM 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 CHM, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 14 | class CHM |
||
| 15 | { |
||
| 16 | /** |
||
| 17 | * The reader that provides the data. |
||
| 18 | * |
||
| 19 | * @var \CHMLib\Reader\Reader |
||
| 20 | */ |
||
| 21 | protected $reader; |
||
| 22 | |||
| 23 | /** |
||
| 24 | * The CHM initial header. |
||
| 25 | * |
||
| 26 | * @var \CHMLib\Header\ITSF |
||
| 27 | */ |
||
| 28 | protected $itsf; |
||
| 29 | |||
| 30 | /** |
||
| 31 | * The directory listing header. |
||
| 32 | * |
||
| 33 | * @var \CHMLib\Header\ITSP |
||
| 34 | */ |
||
| 35 | protected $itsp; |
||
| 36 | |||
| 37 | /** |
||
| 38 | * The entries found in this CHM. |
||
| 39 | * |
||
| 40 | * @var \CHMLib\Entry[] |
||
| 41 | */ |
||
| 42 | protected $entries; |
||
| 43 | |||
| 44 | /** |
||
| 45 | * The data sections. |
||
| 46 | * |
||
| 47 | * @var \CHMLib\Section\Section[] |
||
| 48 | */ |
||
| 49 | protected $sections; |
||
| 50 | |||
| 51 | /** |
||
| 52 | * The TOC. |
||
| 53 | * |
||
| 54 | * @var \CHMLib\TOCIndex\Tree|null|false |
||
| 55 | */ |
||
| 56 | protected $toc; |
||
| 57 | |||
| 58 | /** |
||
| 59 | * The index. |
||
| 60 | * |
||
| 61 | * @var \CHMLib\TOCIndex\Tree|null|false |
||
| 62 | */ |
||
| 63 | protected $index; |
||
| 64 | |||
| 65 | /** |
||
| 66 | * Initializes the instance. |
||
| 67 | * |
||
| 68 | * @param \CHMLib\Reader\Reader $reader The reader that provides the data. |
||
| 69 | * |
||
| 70 | * @throws \Exception Throws an Exception in case of errors. |
||
| 71 | */ |
||
| 72 | 4 | public function __construct(Reader $reader) |
|
| 105 | |||
| 106 | /** |
||
| 107 | * Destruct the instance. |
||
| 108 | */ |
||
| 109 | public function __destruct() |
||
| 113 | |||
| 114 | /** |
||
| 115 | * Create a new CHM instance reading a file. |
||
| 116 | * |
||
| 117 | * @param string $filename |
||
| 118 | * |
||
| 119 | * @return static |
||
| 120 | */ |
||
| 121 | 4 | public static function fromFile($filename) |
|
| 127 | |||
| 128 | /** |
||
| 129 | * Get the reader that provides the data. |
||
| 130 | * |
||
| 131 | * @return \CHMLib\Reader\Reader |
||
| 132 | */ |
||
| 133 | 486 | public function getReader() |
|
| 137 | |||
| 138 | /** |
||
| 139 | * Get the CHM initial header. |
||
| 140 | * |
||
| 141 | * @return \CHMLib\Header\ITSF |
||
| 142 | */ |
||
| 143 | 4 | public function getITSF() |
|
| 147 | |||
| 148 | /** |
||
| 149 | * Get the directory listing header. |
||
| 150 | * |
||
| 151 | * @return \CHMLib\Header\ITSP |
||
| 152 | */ |
||
| 153 | public function getITSP() |
||
| 157 | |||
| 158 | /** |
||
| 159 | * Get an entry given its full path. |
||
| 160 | * |
||
| 161 | * @param string $path The full path (case sensitive) of the entry to look for. |
||
| 162 | * |
||
| 163 | * @return \CHMLib\Entry|null |
||
| 164 | */ |
||
| 165 | 491 | public function getEntryByPath($path) |
|
| 169 | |||
| 170 | /** |
||
| 171 | * Get the entries contained in this CHM. |
||
| 172 | * |
||
| 173 | * @param int|null $type One or more Entry::TYPE_... values (defaults to Entry::TYPE_FILE | Entry::TYPE_DIRECTORY if null). |
||
| 174 | */ |
||
| 175 | 3 | public function getEntries($type = null) |
|
| 189 | |||
| 190 | /** |
||
| 191 | * Return a section given its index. |
||
| 192 | * |
||
| 193 | * @param int $i |
||
| 194 | * |
||
| 195 | * @return \CHMLib\Section\Section|null |
||
| 196 | */ |
||
| 197 | 491 | public function getSectionByIndex($i) |
|
| 201 | |||
| 202 | /** |
||
| 203 | * Retrieve the list of the entries contained in this CHM. |
||
| 204 | * |
||
| 205 | * @throws \Exception Throws an Exception in case of errors. |
||
| 206 | * |
||
| 207 | * @return \CHMLib\Entry[] |
||
| 208 | */ |
||
| 209 | 4 | protected function retrieveEntryList() |
|
| 241 | |||
| 242 | /** |
||
| 243 | * Retrieve the list of the data sections contained in this CHM. |
||
| 244 | * |
||
| 245 | * @throws \Exception Throws an Exception in case of errors. |
||
| 246 | */ |
||
| 247 | 4 | protected function retrieveSectionList() |
|
| 248 | { |
||
| 249 | 4 | $nameList = $this->getEntryByPath('::DataSpace/NameList'); |
|
| 250 | |||
| 251 | 4 | if ($nameList === null) { |
|
| 252 | throw new Exception("Missing required entry: '::DataSpace/NameList'"); |
||
| 253 | } |
||
| 254 | 4 | if ($nameList->getContentSectionIndex() !== 0) { |
|
| 255 | throw new Exception("The content of the entry '{$nameList->getPath()}' should be in section 0, but it's in section {$nameList->getContentSection()}"); |
||
|
|
|||
| 256 | } |
||
| 257 | |||
| 258 | 4 | $nameListReader = new StringReader($nameList->getContents()); |
|
| 259 | 4 | /* Length */ $nameListReader->readUInt16(); |
|
| 260 | 4 | $numSections = $nameListReader->readUInt16(); |
|
| 261 | 4 | if ($numSections === 0) { |
|
| 262 | throw new Exception('No content section defined.'); |
||
| 263 | } |
||
| 264 | 4 | for ($i = 0; $i < $numSections; ++$i) { |
|
| 265 | 4 | $nameLength = $nameListReader->readUInt16(); |
|
| 266 | 4 | $utf16name = $nameListReader->readString($nameLength * 2); |
|
| 267 | 4 | $nameListReader->readUInt16(); |
|
| 268 | 4 | $name = iconv('UTF-16LE', 'UTF-8', $utf16name); |
|
| 269 | 4 | switch ($name) { |
|
| 270 | 4 | case 'Uncompressed': |
|
| 271 | 4 | break; |
|
| 272 | 4 | case 'MSCompressed': |
|
| 273 | 4 | if ($i === 0) { |
|
| 274 | throw new Exception('First data section should be Uncompressed'); |
||
| 275 | } else { |
||
| 276 | 4 | $this->sections[$i] = new Section\MSCompressedSection($this); |
|
| 277 | } |
||
| 278 | 4 | break; |
|
| 279 | default: |
||
| 280 | throw new Exception("Unknown data section: $name"); |
||
| 281 | } |
||
| 282 | } |
||
| 283 | 4 | } |
|
| 284 | |||
| 285 | /** |
||
| 286 | * Get the TOC of this CHM file (if available). |
||
| 287 | * |
||
| 288 | * @return \CHMLib\TOCIndex\Tree|null |
||
| 289 | */ |
||
| 290 | 1 | View Code Duplication | public function getTOC() |
| 305 | |||
| 306 | /** |
||
| 307 | * Get the index of this CHM file (if available). |
||
| 308 | * |
||
| 309 | * @return \CHMLib\TOCIndex\Tree|null |
||
| 310 | */ |
||
| 311 | View Code Duplication | public function getIndex() |
|
| 326 | } |
||
| 327 |
This check marks calls to methods that do not seem to exist on an object.
This is most likely the result of a method being renamed without all references to it being renamed likewise.