wikimedia /
mediawiki
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 MediaWikiTitleCodec 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 MediaWikiTitleCodec, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 37 | class MediaWikiTitleCodec implements TitleFormatter, TitleParser { |
||
| 38 | /** |
||
| 39 | * @var Language |
||
| 40 | */ |
||
| 41 | protected $language; |
||
| 42 | |||
| 43 | /** |
||
| 44 | * @var GenderCache |
||
| 45 | */ |
||
| 46 | protected $genderCache; |
||
| 47 | |||
| 48 | /** |
||
| 49 | * @var string[] |
||
| 50 | */ |
||
| 51 | protected $localInterwikis; |
||
| 52 | |||
| 53 | /** |
||
| 54 | * @param Language $language The language object to use for localizing namespace names. |
||
| 55 | * @param GenderCache $genderCache The gender cache for generating gendered namespace names |
||
| 56 | * @param string[]|string $localInterwikis |
||
| 57 | */ |
||
| 58 | public function __construct( Language $language, GenderCache $genderCache, |
||
| 65 | |||
| 66 | /** |
||
| 67 | * @see TitleFormatter::getNamespaceName() |
||
| 68 | * |
||
| 69 | * @param int $namespace |
||
| 70 | * @param string $text |
||
| 71 | * |
||
| 72 | * @throws InvalidArgumentException If the namespace is invalid |
||
| 73 | * @return string |
||
| 74 | */ |
||
| 75 | public function getNamespaceName( $namespace, $text ) { |
||
| 93 | |||
| 94 | /** |
||
| 95 | * @see TitleFormatter::formatTitle() |
||
| 96 | * |
||
| 97 | * @param int|bool $namespace The namespace ID (or false, if the namespace should be ignored) |
||
| 98 | * @param string $text The page title. Should be valid. Only minimal normalization is applied. |
||
| 99 | * Underscores will be replaced. |
||
| 100 | * @param string $fragment The fragment name (may be empty). |
||
| 101 | * @param string $interwiki The interwiki name (may be empty). |
||
| 102 | * |
||
| 103 | * @throws InvalidArgumentException If the namespace is invalid |
||
| 104 | * @return string |
||
| 105 | */ |
||
| 106 | public function formatTitle( $namespace, $text, $fragment = '', $interwiki = '' ) { |
||
| 107 | if ( $namespace !== false ) { |
||
| 108 | $namespace = $this->getNamespaceName( $namespace, $text ); |
||
|
|
|||
| 109 | |||
| 110 | if ( $namespace !== '' ) { |
||
| 111 | $text = $namespace . ':' . $text; |
||
| 112 | } |
||
| 113 | } |
||
| 114 | |||
| 115 | if ( $fragment !== '' ) { |
||
| 116 | $text = $text . '#' . $fragment; |
||
| 117 | } |
||
| 118 | |||
| 119 | if ( $interwiki !== '' ) { |
||
| 120 | $text = $interwiki . ':' . $text; |
||
| 121 | } |
||
| 122 | |||
| 123 | $text = str_replace( '_', ' ', $text ); |
||
| 124 | |||
| 125 | return $text; |
||
| 126 | } |
||
| 127 | |||
| 128 | /** |
||
| 129 | * Parses the given text and constructs a TitleValue. Normalization |
||
| 130 | * is applied according to the rules appropriate for the form specified by $form. |
||
| 131 | * |
||
| 132 | * @param string $text The text to parse |
||
| 133 | * @param int $defaultNamespace Namespace to assume per default (usually NS_MAIN) |
||
| 134 | * |
||
| 135 | * @throws MalformedTitleException |
||
| 136 | * @return TitleValue |
||
| 137 | */ |
||
| 138 | public function parseTitle( $text, $defaultNamespace ) { |
||
| 139 | // NOTE: this is an ugly cludge that allows this class to share the |
||
| 140 | // code for parsing with the old Title class. The parser code should |
||
| 141 | // be refactored to avoid this. |
||
| 142 | $parts = $this->splitTitleString( $text, $defaultNamespace ); |
||
| 143 | |||
| 144 | // Relative fragment links are not supported by TitleValue |
||
| 145 | if ( $parts['dbkey'] === '' ) { |
||
| 146 | throw new MalformedTitleException( 'title-invalid-empty', $text ); |
||
| 147 | } |
||
| 148 | |||
| 149 | return new TitleValue( |
||
| 150 | $parts['namespace'], |
||
| 151 | $parts['dbkey'], |
||
| 152 | $parts['fragment'], |
||
| 153 | $parts['interwiki'] |
||
| 154 | ); |
||
| 155 | } |
||
| 156 | |||
| 157 | /** |
||
| 158 | * @see TitleFormatter::getText() |
||
| 159 | * |
||
| 160 | * @param LinkTarget $title |
||
| 161 | * |
||
| 162 | * @return string $title->getText() |
||
| 163 | */ |
||
| 164 | public function getText( LinkTarget $title ) { |
||
| 167 | |||
| 168 | /** |
||
| 169 | * @see TitleFormatter::getText() |
||
| 170 | * |
||
| 171 | * @param LinkTarget $title |
||
| 172 | * |
||
| 173 | * @return string |
||
| 174 | */ |
||
| 175 | public function getPrefixedText( LinkTarget $title ) { |
||
| 183 | |||
| 184 | /** |
||
| 185 | * @since 1.27 |
||
| 186 | * @see TitleFormatter::getPrefixedDBkey() |
||
| 187 | * @param LinkTarget $target |
||
| 188 | * @return string |
||
| 189 | */ |
||
| 190 | public function getPrefixedDBkey( LinkTarget $target ) { |
||
| 214 | |||
| 215 | /** |
||
| 216 | * @see TitleFormatter::getText() |
||
| 217 | * |
||
| 218 | * @param LinkTarget $title |
||
| 219 | * |
||
| 220 | * @return string |
||
| 221 | */ |
||
| 222 | public function getFullText( LinkTarget $title ) { |
||
| 230 | |||
| 231 | /** |
||
| 232 | * Normalizes and splits a title string. |
||
| 233 | * |
||
| 234 | * This function removes illegal characters, splits off the interwiki and |
||
| 235 | * namespace prefixes, sets the other forms, and canonicalizes |
||
| 236 | * everything. |
||
| 237 | * |
||
| 238 | * @todo this method is only exposed as a temporary measure to ease refactoring. |
||
| 239 | * It was copied with minimal changes from Title::secureAndSplit(). |
||
| 240 | * |
||
| 241 | * @todo This method should be split up and an appropriate interface |
||
| 242 | * defined for use by the Title class. |
||
| 243 | * |
||
| 244 | * @param string $text |
||
| 245 | * @param int $defaultNamespace |
||
| 246 | * |
||
| 247 | * @throws MalformedTitleException If $text is not a valid title string. |
||
| 248 | * @return array A map with the fields 'interwiki', 'fragment', 'namespace', |
||
| 249 | * 'user_case_dbkey', and 'dbkey'. |
||
| 250 | */ |
||
| 251 | public function splitTitleString( $text, $defaultNamespace = NS_MAIN ) { |
||
| 449 | |||
| 450 | /** |
||
| 451 | * Returns a simple regex that will match on characters and sequences invalid in titles. |
||
| 452 | * Note that this doesn't pick up many things that could be wrong with titles, but that |
||
| 453 | * replacing this regex with something valid will make many titles valid. |
||
| 454 | * Previously Title::getTitleInvalidRegex() |
||
| 455 | * |
||
| 456 | * @return string Regex string |
||
| 457 | * @since 1.25 |
||
| 458 | */ |
||
| 459 | public static function getTitleInvalidRegex() { |
||
| 478 | } |
||
| 479 |
If a method or function can return multiple different values and unless you are sure that you only can receive a single value in this context, we recommend to add an additional type check:
If this a common case that PHP Analyzer should handle natively, please let us know by opening an issue.