Static Analysis, Linting & Refactoring Tools

.github/workflows/formats.yml

@@ -0,0 +1,49 @@
+name: Formats
+
+on: ['push', 'pull_request']
+
+jobs:
+  ci:
+    runs-on: ${{ matrix.os }}
+
+    strategy:
+      fail-fast: true
+      matrix:
+        os: [ubuntu-latest]
+        php: [8.4]
+        dependency-version: [prefer-lowest, prefer-stable]
+
+    name: Formats P${{ matrix.php }} - ${{ matrix.os }} - ${{ matrix.dependency-version }}
+
+    steps:
+
+    - name: Checkout
+      uses: actions/checkout@v3
+
+    - name: Setup PHP
+      uses: shivammathur/setup-php@v2
+      with:
+        php-version: ${{ matrix.php }}
+        extensions: dom, mbstring, zip
+        coverage: pcov
+
+    - name: Get Composer cache directory
+      id: composer-cache
+      shell: bash
+      run: echo "dir=$(composer config cache-files-dir)" >> $GITHUB_OUTPUT
+
+    - name: Cache dependencies
+      uses: actions/cache@v3
+      with:
+        path: ${{ steps.composer-cache.outputs.dir }}
+        key: dependencies-php-${{ matrix.php }}-os-${{ matrix.os }}-version-${{ matrix.dependency-version }}-composer-${{ hashFiles('composer.json') }}
+        restore-keys: dependencies-php-${{ matrix.php }}-os-${{ matrix.os }}-version-${{ matrix.dependency-version }}-composer-
+
+    - name: Install Composer dependencies
+      run: composer update --${{ matrix.dependency-version }} --no-interaction --prefer-dist
+
+    - name: Coding Style Checks
+      run: composer test:lint
+
+    - name: Type Checks
+      run: composer test:types

.github/workflows/tests.yml

@@ -0,0 +1,45 @@
+name: Tests
+
+on: ['push', 'pull_request']
+
+jobs:
+  ci:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: true
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        php: ['8.3', '8.4']
+        dependency-version: [prefer-lowest, prefer-stable]
+
+    name: Tests P${{ matrix.php }} - ${{ matrix.os }} - ${{ matrix.dependency-version }}
+
+    steps:
+
+    - name: Checkout
+      uses: actions/checkout@v3
+
+    - name: Setup PHP
+      uses: shivammathur/setup-php@v2
+      with:
+        php-version: ${{ matrix.php }}
+        extensions: dom, mbstring, zip
+        coverage: xdebug
+
+    - name: Get Composer cache directory
+      id: composer-cache
+      shell: bash
+      run: echo "dir=$(composer config cache-files-dir)" >> $GITHUB_OUTPUT
+
+    - name: Cache dependencies
+      uses: actions/cache@v3
+      with:
+        path: ${{ steps.composer-cache.outputs.dir }}
+        key: dependencies-php-${{ matrix.php }}-os-${{ matrix.os }}-version-${{ matrix.dependency-version }}-composer-${{ hashFiles('composer.json') }}
+        restore-keys: dependencies-php-${{ matrix.php }}-os-${{ matrix.os }}-version-${{ matrix.dependency-version }}-composer-
+
+    - name: Install Composer dependencies
+      run: composer update --${{ matrix.dependency-version }} --no-interaction --prefer-dist
+
+    - name: Integration Tests
+      run: php ./vendor/phpunit/phpunit/phpunit --testsuite default

composer.json

@@ -1,25 +1,61 @@
 {
-    "name": "edgaras/strsim",
-    "description": "Collection of string similarity and distance algorithms in PHP including Levenshtein, Damerau-Levenshtein, Jaro-Winkler, and more",
-    "type": "library",
-    "homepage": "https://github.com/Edgaras0x4E/StrSim",
-    "license": "MIT",
-    "keywords": ["string", "similarity", "distance", "levenshtein", "damerau-levenshtein", "jaro", "jaro-winkler", "lcs", "smith-waterman", "needleman-wunsch", "cosine", "jaccard", "monge-elkan", "text", "fuzzy", "comparison", "algorithm", "multibyte"],
-    "autoload": {
-        "psr-4": {
-            "Edgaras\\StrSim\\": "src/"
-        }
-    }, 
-    "autoload-dev": {
-        "psr-4": {
-            "Edgaras\\StrSim\\Tests\\": "tests/"
-        }
-    },
-    "minimum-stability": "stable",
-    "require": {
-        "php": ">=8.3.0"
-    },
-    "require-dev": {
-        "phpunit/phpunit": "^11.5"
+  "name": "edgaras/strsim",
+  "description": "Collection of string similarity and distance algorithms in PHP including Levenshtein, Damerau-Levenshtein, Jaro-Winkler, and more",
+  "type": "library",
+  "homepage": "https://github.com/Edgaras0x4E/StrSim",
+  "license": "MIT",
+  "keywords": [
+    "string",
+    "similarity",
+    "distance",
+    "levenshtein",
+    "damerau-levenshtein",
+    "jaro",
+    "jaro-winkler",
+    "lcs",
+    "smith-waterman",
+    "needleman-wunsch",
+    "cosine",
+    "jaccard",
+    "monge-elkan",
+    "text",
+    "fuzzy",
+    "comparison",
+    "algorithm",
+    "multibyte"
+  ],
+  "autoload": {
+    "psr-4": {
+      "Edgaras\\StrSim\\": "src/"
     }
+  },
+  "autoload-dev": {
+    "psr-4": {
+      "Edgaras\\StrSim\\Tests\\": "tests/"
+    }
+  },
+  "minimum-stability": "stable",
+  "require": {
+    "php": ">=8.3.0"
+  },
+  "require-dev": {
+    "phpunit/phpunit": "^11.5",
+    "phpstan/phpstan": "^2.1",
+    "rector/rector": "^2.0",
+    "laravel/pint": "^1.19"
+  },
+  "scripts": {
+    "refacto": "rector",
+    "lint": "pint",
+    "test:refacto": "rector --dry-run",
+    "test:lint": "pint --test",
+    "test:types": "phpstan analyse --ansi",
+    "test:unit": "phpunit",
+    "test": [
+      "@test:refacto",
+      "@test:lint",
+      "@test:types",
+      "@test:unit"
+    ]
+  }
 }

phpstan.neon

@@ -0,0 +1,6 @@
+parameters:
+    level: max
+    paths:
+        - src
+
+    reportUnmatchedIgnoredErrors: true

phpunit.xml

@@ -0,0 +1,31 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<phpunit xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:noNamespaceSchemaLocation="vendor/phpunit/phpunit/phpunit.xsd"
+         bootstrap="vendor/autoload.php"
+         cacheDirectory=".phpunit.cache"
+         executionOrder="depends,defects"
+         shortenArraysForExportThreshold="10"
+         requireCoverageMetadata="true"
+         beStrictAboutCoverageMetadata="true"
+         beStrictAboutOutputDuringTests="true"
+         displayDetailsOnPhpunitDeprecations="true"
+         displayDetailsOnTestsThatTriggerDeprecations="true"
+         failOnPhpunitDeprecation="true"
+         failOnRisky="true"
+         failOnWarning="true">
+    <testsuites>
+        <testsuite name="default">
+            <directory>tests</directory>
+        </testsuite>
+    </testsuites>
+    <source ignoreIndirectDeprecations="true" restrictNotices="true" restrictWarnings="true">
+        <include>
+            <directory>src</directory>
+        </include>
+    </source>
+    <coverage>
+        <report>
+            <html outputDirectory=".phpunit.cache/code-coverage" />
+        </report>
+    </coverage>
+</phpunit>

pint.json

@@ -0,0 +1,6 @@
+{
+  "preset": "psr12",
+  "rules": {
+    "declare_strict_types": true
+  }
+}

rector.php

@@ -0,0 +1,18 @@
+<?php
+
+declare(strict_types=1);
+
+use Rector\Config\RectorConfig;
+
+return RectorConfig::configure()
+    ->withPaths([
+        __DIR__.'/src',
+        __DIR__.'/tests',
+    ])
+    ->withPreparedSets(
+        deadCode: true,
+        codeQuality: true,
+        typeDeclarations: true,
+        privatization: true,
+        earlyReturn: true,
+    );

src/Cosine.php

@@ -1,43 +1,57 @@
 <?php
+
+declare(strict_types=1);
+
 namespace Edgaras\StrSim;
 
-class Cosine {
-    public static function similarity(string $a, string $b): float {
+class Cosine
+{
+    public static function similarity(string $a, string $b): float
+    {
         if (!mb_check_encoding($a, 'UTF-8') || !mb_check_encoding($b, 'UTF-8')) {
             throw new \InvalidArgumentException("Input strings must be valid UTF-8.");
         }
-        
+
         $tokensA = self::countMbChars($a);
         $tokensB = self::countMbChars($b);
-        $dot = 0;
-        $normA = 0;
-        $normB = 0;
+        $dot = 0.0;
+        $normA = 0.0;
+        $normB = 0.0;
 
         foreach ($tokensA as $k => $v) {
-            $dot += $v * ($tokensB[$k] ?? 0);
-            $normA += $v * $v;
+            $dot += (float)$v * (float)($tokensB[$k] ?? 0);
+            $normA += (float)$v * (float)$v;
         }
 
         foreach ($tokensB as $v) {
-            $normB += $v * $v;
+            $normB += (float)$v * (float)$v;
         }
 
         return ($normA && $normB) ? $dot / (sqrt($normA) * sqrt($normB)) : 0;
     }
 
-    private static function countMbChars(string $str): array {
+    /**
+     * @return array<string, int>
+     */
+    private static function countMbChars(string $str): array
+    {
         $chars = [];
         $length = mb_strlen($str, 'UTF-8');
-        
+
         for ($i = 0; $i < $length; $i++) {
             $char = mb_substr($str, $i, 1, 'UTF-8');
             $chars[$char] = ($chars[$char] ?? 0) + 1;
         }
-        
+
         return $chars;
     }
 
-    public static function similarityFromVectors(array $vecA, array $vecB): float {
+    /**
+     * @param array<int|string, int|float> $vecA
+     * @param array<int|string, int|float> $vecB
+     */
+    public static function similarityFromVectors(array $vecA, array $vecB): float
+    {
         if (count($vecA) !== count($vecB)) {
             throw new \InvalidArgumentException("Vectors must be the same length.");
         }
@@ -48,9 +62,9 @@ public static function similarityFromVectors(array $vecA, array $vecB): float {
 
         foreach ($vecA as $i => $valA) {
             $valB = $vecB[$i];
-            $dot += $valA * $valB;
-            $normA += $valA * $valA;
-            $normB += $valB * $valB;
+            $dot += (float)$valA * (float)$valB;
+            $normA += (float)$valA * (float)$valA;
+            $normB += (float)$valB * (float)$valB;
         }
 
         return ($normA && $normB) ? $dot / (sqrt($normA) * sqrt($normB)) : 0.0;

src/DamerauLevenshtein.php

@@ -1,31 +1,40 @@
 <?php
+
+declare(strict_types=1);
+
 namespace Edgaras\StrSim;
 
-class DamerauLevenshtein {
-    public static function distance(string $a, string $b): int {
+class DamerauLevenshtein
+{
+    public static function distance(string $a, string $b): int
+    {
         if (!mb_check_encoding($a, 'UTF-8') || !mb_check_encoding($b, 'UTF-8')) {
             throw new \InvalidArgumentException("Input strings must be valid UTF-8.");
         }
-        
+
         $lenA = mb_strlen($a, 'UTF-8');
         $lenB = mb_strlen($b, 'UTF-8');
         $dp = [];
 
-        for ($i = 0; $i <= $lenA; $i++) $dp[$i][0] = $i;
-        for ($j = 0; $j <= $lenB; $j++) $dp[0][$j] = $j;
+        for ($i = 0; $i <= $lenA; $i++) {
+            $dp[$i][0] = $i;
+        }
+        for ($j = 0; $j <= $lenB; $j++) {
+            $dp[0][$j] = $j;
+        }
 
         for ($i = 1; $i <= $lenA; $i++) {
             for ($j = 1; $j <= $lenB; $j++) {
                 $charA = mb_substr($a, $i - 1, 1, 'UTF-8');
                 $charB = mb_substr($b, $j - 1, 1, 'UTF-8');
                 $cost = ($charA === $charB) ? 0 : 1;
-                
+
                 $dp[$i][$j] = min(
                     $dp[$i - 1][$j] + 1,
                     $dp[$i][$j - 1] + 1,
                     $dp[$i - 1][$j - 1] + $cost
                 );
-                
+
                 if ($i > 1 && $j > 1) {
                     $charA2 = mb_substr($a, $i - 2, 1, 'UTF-8');
                     $charB2 = mb_substr($b, $j - 2, 1, 'UTF-8');