Improved Italian pluralization with multi-word inflection #279
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,70 @@ | ||
| <?php | ||
|
|
||
| declare(strict_types=1); | ||
|
|
||
| namespace Doctrine\Inflector; | ||
|
|
||
| use function implode; | ||
| use function in_array; | ||
| use function mb_strlen; | ||
| use function mb_substr; | ||
| use function preg_match; | ||
|
|
||
| /** | ||
| * Decorator that applies inflection to each word in a multi-word phrase. | ||
| */ | ||
| class MultiWordInflector implements WordInflector | ||
| { | ||
| public const WORD_SEPARATORS = [' ', '-']; | ||
|
|
||
| /** @var WordInflector */ | ||
| private $wordInflector; | ||
|
|
||
| public function __construct(WordInflector $wordInflector) | ||
| { | ||
| $this->wordInflector = $wordInflector; | ||
| } | ||
|
|
||
| public function inflect(string $word): string | ||
| { | ||
| // If it's a single word or doesn't contain any word separators, use the original inflector | ||
| if (preg_match('/[\s-]/', $word) !== 1) { | ||
| return $this->wordInflector->inflect($word); | ||
| } | ||
|
|
||
| // Split the phrase into words while preserving separators | ||
| $words = []; | ||
| $currentWord = ''; | ||
| $length = mb_strlen($word); | ||
|
|
||
| for ($i = 0; $i < $length; $i++) { | ||
| $char = mb_substr($word, $i, 1); | ||
| if (in_array($char, self::WORD_SEPARATORS, true)) { | ||
| if ($currentWord !== '') { | ||
| $words[] = $currentWord; | ||
| $currentWord = ''; | ||
| } | ||
|
|
||
| $words[] = $char; | ||
| } else { | ||
| $currentWord .= $char; | ||
| } | ||
| } | ||
|
|
||
| if ($currentWord !== '') { | ||
| $words[] = $currentWord; | ||
| } | ||
|
|
||
| // Process each word | ||
| $result = []; | ||
| foreach ($words as $part) { | ||
| if (in_array($part, self::WORD_SEPARATORS, true)) { | ||
| $result[] = $part; | ||
| } else { | ||
| $result[] = $this->wordInflector->inflect($part); | ||
| } | ||
| } | ||
|
|
||
| return implode('', $result); | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,46 @@ | ||
| <?php | ||
|
|
||
| declare(strict_types=1); | ||
|
|
||
| namespace Doctrine\Inflector\Rules\Italian; | ||
|
|
||
| use Doctrine\Inflector\MultiWordInflector; | ||
|
|
||
| use function implode; | ||
| use function preg_split; | ||
| use function strpos; | ||
|
|
||
| use const PREG_SPLIT_DELIM_CAPTURE; | ||
| use const PREG_SPLIT_NO_EMPTY; | ||
|
|
||
| class RulesetInflector extends \Doctrine\Inflector\RulesetInflector | ||
| { | ||
| public function inflect(string $word): string | ||
| { | ||
| // If it's a single word without spaces or hyphens, use the original inflector | ||
| if (strpos($word, ' ') === false && strpos($word, '-') === false) { | ||
| return parent::inflect($word); | ||
| } | ||
|
|
||
| // Split the phrase into words and process each one | ||
| $regex = '/([' . implode('', MultiWordInflector::WORD_SEPARATORS) . '])/'; | ||
| $words = preg_split($regex, $word, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY); | ||
|
|
||
| if ($words === false) { | ||
| return parent::inflect($word); | ||
|
Member
There was a problem hiding this comment. If this fails, it feels like you should rather throw an exception.
Author
There was a problem hiding this comment. I’d say that as a fallback it’s right for it to handle the string as if it were a single word, so I would leave it like that without raising exceptions, because in Italian there are often compound or multiple words, so if there were any unmanaged cases exceptions would be raised, whereas this way it would still be handled. |
||
| } | ||
|
|
||
| $result = []; | ||
| foreach ($words as $part) { | ||
| if ($part === ' ' || $part === '-') { | ||
| $result[] = $part; | ||
| continue; | ||
| } | ||
|
|
||
| // Process each word individually | ||
| $result[] = parent::inflect($part); | ||
| } | ||
|
|
||
| return implode('', $result); | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This class should come with tests
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I have implemented the tests for the MultiWordInflector class.