Modernize for PHP 8.1+ and PHPUnit 11

.github/workflows/ci.yml

@@ -0,0 +1,30 @@
+name: CI
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        php-version: ['8.2', '8.3', '8.4']
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up PHP ${{ matrix.php-version }}
+        uses: shivammathur/setup-php@v2
+        with:
+          php-version: ${{ matrix.php-version }}
+          extensions: mbstring
+
+      - name: Install dependencies
+        run: composer install --no-interaction --prefer-dist
+
+      - name: Run tests
+        run: vendor/bin/phpunit --testdox

.gitignore

@@ -1,4 +1,5 @@
 /.idea
 /composer.lock
 /vendor
+/.phpunit.cache
 .DS_Store

README.md

@@ -1,34 +1,54 @@
-# Strip accents 
-This PHP 7 library removes accent from strings. It is based on the sample code [published here](http://www.infowebmaster.fr/tutoriel/php-enlever-accents).  
+# Strip Accents
 
+[![Packagist Version](https://img.shields.io/packagist/v/codeinc/strip-accents)](https://packagist.org/packages/codeinc/strip-accents)
+[![Packagist Downloads](https://img.shields.io/packagist/dt/codeinc/strip-accents)](https://packagist.org/packages/codeinc/strip-accents)
+[![PHP Version](https://img.shields.io/packagist/dependency-v/codeinc/strip-accents/php)](https://packagist.org/packages/codeinc/strip-accents)
+[![License](https://img.shields.io/packagist/l/codeinc/strip-accents)](LICENSE)
+
+A PHP library to remove accents and diacritics from strings.
+
+## Installation
+
+```bash
+composer require codeinc/strip-accents
+```
+
+Requires PHP 8.2 or later with the `mbstring` extension.
+
+## Usage
+
+### Strip accents
 
-## Usage 
 ```php
-<?php
 use CodeInc\StripAccents\StripAccents;
 
 echo StripAccents::strip("C'est une super chaîne de caractères avec beaucoup d'accents");
-// echoes: C'est une super chaine de caracteres avec beaucoup d'accents
+// "C'est une super chaine de caracteres avec beaucoup d'accents"
 
 echo StripAccents::strip("ÀÁÂÃÄÅÇÈÉÊËÌÍÎÏÒÓÔÕÖÙÚÛÜÝàáâãäåçèéêëìíîïðòóôõöùúûüýÿ");
-// echoes: AAAAAACEEEEIIIIOOOOOUUUUYaaaaaaceeeeiiiioooooouuuuyy
+// "AAAAAACEEEEIIIIOOOOOUUUUYaaaaaaceeeeiiiieooooouuuuyy"
+```
+
+### Strip accents and non-printable characters
+
+```php
+use CodeInc\StripAccents\StripAccents;
 
 echo StripAccents::stripNonPrint("ABC ÀÈÝ 是我这");
-// echoes: ABC AEY ---
+// "ABC AEY "
 
-// You can specify any encoding supported by htmlentities() as a second parameter
-echo StripAccents::strip("A strïng with àccénts", "iso-8859-1");
+echo StripAccents::stripNonPrint("ABC ÀÈÝ 是我这", replaceWith: "-");
+// "ABC AEY ---------" (each multibyte character is replaced per-byte)
 ```
 
+### Custom encoding
 
-## Installation
-This library is available through [Packagist](https://packagist.org/packages/codeinc/strip-accents) and can be installed using [Composer](https://getcomposer.org/): 
+Both methods accept an encoding parameter (any encoding supported by `htmlentities()`):
 
-```bash
-composer require codeinc/strip-accents
+```php
+echo StripAccents::strip("A strïng with àccénts", encoding: "iso-8859-1");
 ```
 
-
 ## License
-This library is published under the MIT license (see the [LICENSE](LICENSE) file). 
 
+This library is published under the MIT license (see the [LICENSE](LICENSE) file).

composer.json

@@ -1,15 +1,15 @@
 {
   "name": "codeinc/strip-accents",
-  "version": "1.1.0",
-  "description": "Removes accents from strings",
-  "homepage": "https://github.com/CodeIncHQ/StripAccents",
+  "description": "A PHP library to remove accents and diacritics from strings",
+  "homepage": "https://github.com/codeinchq/strip-accents",
   "type": "library",
   "license": "MIT",
   "require": {
-    "php": ">=7.1"
+    "php": ">=8.2",
+    "ext-mbstring": "*"
   },
   "require-dev": {
-    "phpunit/phpunit": "^7"
+    "phpunit/phpunit": "^11.0"
   },
   "autoload": {
     "psr-4": {
@@ -34,4 +34,4 @@
       "*": "dist"
     }
   }
-}
+}

phpunit.xml.dist

@@ -0,0 +1,17 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<phpunit xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:noNamespaceSchemaLocation="https://schema.phpunit.de/11.5/phpunit.xsd"
+         bootstrap="vendor/autoload.php"
+         colors="true"
+         cacheDirectory=".phpunit.cache">
+    <testsuites>
+        <testsuite name="default">
+            <directory>tests</directory>
+        </testsuite>
+    </testsuites>
+    <source>
+        <include>
+            <directory>src</directory>
+        </include>
+    </source>
+</phpunit>

src/StripAccents.php

@@ -1,77 +1,48 @@
 <?php
-//
-// +---------------------------------------------------------------------+
-// | CODE INC. SOURCE CODE                                               |
-// +---------------------------------------------------------------------+
-// | Copyright (c) 2017 - Code Inc. SAS - All Rights Reserved.           |
-// | Visit https://www.codeinc.fr for more information about licensing.  |
-// +---------------------------------------------------------------------+
-// | NOTICE:  All information contained herein is, and remains the       |
-// | property of Code Inc. SAS. The intellectual and technical concepts  |
-// | contained herein are proprietary to Code Inc. SAS are protected by  |
-// | trade secret or copyright law. Dissemination of this information or |
-// | reproduction of this material  is strictly forbidden unless prior   |
-// | written permission is obtained from Code Inc. SAS.                  |
-// +---------------------------------------------------------------------+
-//
-// Author:   Joan Fabrégat <joan@codeinc.fr>
-// Date:     15/03/2018
-// Time:     10:52
-// Project:  StipAccents
-//
-declare(strict_types = 1);
-namespace CodeInc\StripAccents;
 
+declare(strict_types=1);
+
+namespace CodeInc\StripAccents;
 
 /**
- * Class StripAccents
- *
- * @link http://www.infowebmaster.fr/tutoriel/php-enlever-accents
- * @package CodeInc\StripAccents
- * @author Joan Fabrégat <joan@codeinc.fr>
+ * Removes accents and diacritics from strings.
  */
 class StripAccents
 {
     public const DEFAULT_ENCODING = 'utf-8';
 
     /**
-     * @param string $string
-     * @param string $encoding
-     * @return string
+     * Strips accents and diacritics from a string.
      */
     public static function strip(string $string, string $encoding = self::DEFAULT_ENCODING): string
     {
-        // converting accents in HTML entities
         $string = htmlentities($string, ENT_NOQUOTES, $encoding);
 
-        // replacing the HTML entities to extract the first letter
-        // examples: "&ecute;" => "e", "&Ecute;" => "E", "à" => "a" ...
+        // replace accented HTML entities with their base letter
+        // e.g. "&eacute;" => "e", "&Eacute;" => "E", "&agrave;" => "a"
         $string = preg_replace(
-            '#&([A-za-z])(?:acute|grave|cedil|circ|orn|ring|slash|th|tilde|uml);#',
+            '#&([A-Za-z])(?:acute|grave|cedil|circ|orn|ring|slash|th|tilde|uml);#',
             '\1',
             $string
         );
 
-        // replacing ligatures
-        // Exemple "œ" => "oe", "Æ" => "AE"
-        $string = preg_replace('#&([A-za-z]{2})(?:lig);#', '\1', $string);
+        // replace ligatures e.g. "&oelig;" => "oe", "&AElig;" => "AE"
+        $string = preg_replace('#&([A-Za-z]{2})(?:lig);#', '\1', $string);
 
-        // removing the remaining bits
+        // remove any remaining HTML entities
         $string = preg_replace('#&[^;]+;#', '', $string);
 
         return $string;
     }
 
     /**
-     * @param string $string
-     * @param string $encoding
-     * @param string $replaceWith
-     * @return string
+     * Strips accents and non-printable characters from a string.
      */
-    public static function stripNonPrint(string $string,
-                                         string $replaceWith = '',
-                                         string $encoding = self::DEFAULT_ENCODING): string
-    {
+    public static function stripNonPrint(
+        string $string,
+        string $replaceWith = '',
+        string $encoding = self::DEFAULT_ENCODING,
+    ): string {
         return preg_replace('/[[:^print:]]/', $replaceWith, self::strip($string, $encoding));
     }
-}
+}

tests/StripAccentsTest.php

@@ -1,63 +1,93 @@
 <?php
-//
-// +---------------------------------------------------------------------+
-// | CODE INC. SOURCE CODE                                               |
-// +---------------------------------------------------------------------+
-// | Copyright (c) 2017 - Code Inc. SAS - All Rights Reserved.           |
-// | Visit https://www.codeinc.fr for more information about licensing.  |
-// +---------------------------------------------------------------------+
-// | NOTICE:  All information contained herein is, and remains the       |
-// | property of Code Inc. SAS. The intellectual and technical concepts  |
-// | contained herein are proprietary to Code Inc. SAS are protected by  |
-// | trade secret or copyright law. Dissemination of this information or |
-// | reproduction of this material  is strictly forbidden unless prior   |
-// | written permission is obtained from Code Inc. SAS.                  |
-// +---------------------------------------------------------------------+
-//
-// Author:   Joan Fabrégat <joan@codeinc.fr>
-// Date:     15/03/2018
-// Time:     10:57
-// Project:  StripAccents
-//
-declare(strict_types = 1);
+
+declare(strict_types=1);
+
 namespace CodeInc\StripAccents\Tests;
+
 use CodeInc\StripAccents\StripAccents;
+use PHPUnit\Framework\Attributes\DataProvider;
 use PHPUnit\Framework\TestCase;
 
-
-/**
- * Class StripAccentsTest
- *
- * @package CodeInc\StripAccents\Tests
- * @author Joan Fabrégat <joan@codeinc.fr>
- */
 class StripAccentsTest extends TestCase
 {
-    public const ACCENTS = [
-        'À', 'Á', 'Â', 'Ã', 'Ä', 'Å', 'Ç', 'È', 'É', 'Ê', 'Ë', 'Ì', 'Í', 'Î',
-        'Ï', 'Ò', 'Ó', 'Ô', 'Õ', 'Ö', 'Ù', 'Ú', 'Û', 'Ü', 'Ý', 'à', 'á', 'â',
-        'ã', 'ä', 'å', 'ç', 'è', 'é', 'ê', 'ë', 'ì', 'í', 'î', 'ï', 'ð', 'ò',
-        'ó', 'ô', 'õ', 'ö', 'ù', 'ú', 'û', 'ü', 'ý', 'ÿ'];
-
-    public const LETTERS = [
-        'A', 'A', 'A', 'A', 'A', 'A', 'C', 'E', 'E', 'E', 'E', 'I', 'I', 'I',
-        'I', 'O', 'O', 'O', 'O', 'O', 'U', 'U', 'U', 'U', 'Y', 'a', 'a', 'a',
-        'a', 'a', 'a', 'c', 'e', 'e', 'e', 'e', 'i', 'i', 'i', 'i', 'e', 'o',
-        'o', 'o', 'o', 'o', 'u', 'u', 'u', 'u', 'y', 'y'
+    private const ACCENT_MAP = [
+        'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A',
+        'Ç' => 'C',
+        'È' => 'E', 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E',
+        'Ì' => 'I', 'Í' => 'I', 'Î' => 'I', 'Ï' => 'I',
+        'Ò' => 'O', 'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O', 'Ö' => 'O',
+        'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ü' => 'U',
+        'Ý' => 'Y',
+        'à' => 'a', 'á' => 'a', 'â' => 'a', 'ã' => 'a', 'ä' => 'a', 'å' => 'a',
+        'ç' => 'c',
+        'è' => 'e', 'é' => 'e', 'ê' => 'e', 'ë' => 'e',
+        'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i',
+        'ð' => 'e',
+        'ò' => 'o', 'ó' => 'o', 'ô' => 'o', 'õ' => 'o', 'ö' => 'o',
+        'ù' => 'u', 'ú' => 'u', 'û' => 'u', 'ü' => 'u',
+        'ý' => 'y', 'ÿ' => 'y',
     ];
 
-    public function testOneByOne():void
+    public static function accentProvider(): iterable
     {
-        foreach (self::ACCENTS as $key => $accent) {
-            self::assertTrue(StripAccents::strip($accent) == self::LETTERS[$key]);
+        foreach (self::ACCENT_MAP as $accented => $expected) {
+            yield $accented => [$accented, $expected];
         }
     }
 
-    public function testAll():void
+    #[DataProvider('accentProvider')]
+    public function testIndividualAccent(string $accented, string $expected): void
+    {
+        $this->assertSame($expected, StripAccents::strip($accented));
+    }
+
+    public function testAllAccentsConcatenated(): void
     {
-        self::assertTrue(
-            StripAccents::strip(implode("", self::ACCENTS))
-            == implode(self::LETTERS)
+        $input = implode('', array_keys(self::ACCENT_MAP));
+        $expected = implode('', array_values(self::ACCENT_MAP));
+        $this->assertSame($expected, StripAccents::strip($input));
+    }
+
+    public function testSentence(): void
+    {
+        $this->assertSame(
+            "C'est une super chaine de caracteres avec beaucoup d'accents",
+            StripAccents::strip("C'est une super chaîne de caractères avec beaucoup d'accents"),
         );
     }
-}
+
+    public function testAsciiPassthrough(): void
+    {
+        $ascii = 'Hello World 123 !@#';
+        $this->assertSame($ascii, StripAccents::strip($ascii));
+    }
+
+    public function testEmptyString(): void
+    {
+        $this->assertSame('', StripAccents::strip(''));
+    }
+
+    public function testLigatures(): void
+    {
+        $this->assertSame('oe', StripAccents::strip('œ'));
+        $this->assertSame('AE', StripAccents::strip('Æ'));
+    }
+
+    public function testStripNonPrint(): void
+    {
+        $this->assertSame('ABC AEY ', StripAccents::stripNonPrint("ABC ÀÈÝ 是我这"));
+    }
+
+    public function testStripNonPrintWithReplacement(): void
+    {
+        $result = StripAccents::stripNonPrint("ABC ÀÈÝ 是我这", '-');
+        $this->assertStringStartsWith('ABC AEY ', $result);
+        // each CJK character is 3 bytes in UTF-8, each non-printable byte is replaced individually
+        $this->assertSame(9, substr_count($result, '-'));
+    }
+
+    public function testStripNonPrintEmptyString(): void
+    {
+        $this->assertSame('', StripAccents::stripNonPrint(''));
+    }
+}