Added data strict data type, upgraded dependencies

.github/dependabot.yml

@@ -0,0 +1,11 @@
+version: 2
+updates:
+    -
+        package-ecosystem: composer
+        directory: "/"
+        schedule:
+            interval: weekly
+        versioning-strategy: auto
+        groups:
+            dev-dependencies:
+                dependency-type: "development"

.github/workflows/main.yml

@@ -0,0 +1,81 @@
+# GithHub Actions Workflow generated with Ghygen
+# Original configuration: https://ghygen.hi-folks.dev?code=0555902844da5dd5163a69e93327a0aa
+name: PHP NLP Tools
+on:
+  push:
+    branches:
+      - master
+      - main
+      - develop
+  pull_request:
+    branches:
+      - master
+      - main
+      - develop
+
+jobs:
+  tests:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        operating-system: [ ubuntu-latest ]
+        php: [ '8.1', '8.2', '8.3' ]
+        dependency-stability: [ 'prefer-stable' ]
+
+    name: PHP ${{ matrix.php }} - ${{ matrix.dependency-stability }} - ${{ matrix.operating-system}}
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install PHP versions
+        uses: shivammathur/setup-php@v2
+        with:
+          php-version: ${{ matrix.php }}
+          extensions: gd
+
+      - name: Get Composer Cache Directory
+        id: composer-cache
+        run: |
+          echo "dir=$(composer config cache-files-dir)" >> $GITHUB_OUTPUT
+
+      - name: Cache Composer dependencies
+        uses: actions/cache@v4
+        id: actions-cache
+        with:
+          path: ${{ steps.composer-cache.outputs.dir }}
+          key: ${{ runner.os }}-composer-${{ hashFiles('**/composer.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-composer-
+
+      - name: Cache PHP dependencies (vendor)
+        uses: actions/cache@v4
+        id: vendor-cache
+        with:
+          path: vendor
+          key: ${{ runner.OS }}-build-${{ hashFiles('**/composer.lock') }}
+
+      - name: Install Dependencies
+        if: steps.vendor-cache.outputs.cache-hit != 'true'
+        run: |
+          composer update --${{ matrix.dependency-stability }} --prefer-dist --no-interaction --no-suggest
+
+      - name: Update Dependencies with latest stable
+        if: matrix.dependency-stability == 'prefer-stable'
+        run: composer update --prefer-stable
+
+      # Code quality
+      - name: Execute Code Sniffer
+        run: vendor/bin/phpcs
+
+      - name: Execute PHP Stan
+        run: vendor/bin/phpstan
+
+      - name: Execute Rector
+        run: vendor/bin/rector --dry-run
+
+      - name: Execute PHP Unit
+        run: vendor/bin/phpunit --exclude-group Slow
+
+

.gitignore

@@ -1,3 +1,4 @@
-vendor/
-/nbproject/private/
-nbproject
+/vendor/
+/composer.lock
+/.phpunit.result.cache
+

README.markdown

@@ -1,7 +1,7 @@
 [PHP NlpTools](http://php-nlp-tools.com/)
 =============
 
-NlpTools is a set of php 5.3+ classes for beginner to
+NlpTools is a set of php 8.1+ classes for beginner to
 semi advanced natural language processing work.
 
 Documentation
@@ -92,3 +92,29 @@ Lda is still experimental and quite slow but it works. [See an example](http://p
 2. Stop words
 3. Language based normalizers
 4. Classifier based transformation for creating flexible preprocessing pipelines
+
+Testing information
+===================
+
+
+Writing Tests
+-------------
+
+* Test classes should be in the same namespace as the class that is being tested
+* Any data needed for the test or produced by the test should be in the 'data' directory
+  under the same folder as the namespace. Only data needed (not produced) are commited to
+  the repository.
+* Tests should be marked with the groups **Slow** and **VerySlow** if they require more than
+  10 seconds and 1 minute respectively. If a test is marked as VerySlow it should also be marked
+  as Slow.
+* Both functional and unit tests are welcome.
+
+Executing Tests
+---------------
+
+Currently only one testsuite is defined (all tests). Because some tests take a long time to
+run you can try running `phpunit --exclude-group Slow` or `phpunit --exclude-group VerySlow`
+to avoid some slow tests.
+
+PHPUnit should be run from inside the tests folder or the phpunit.xml file should be provided
+as config.

composer.json

@@ -1,25 +1,27 @@
 {
-	"name": "nlp-tools/nlp-tools",
-	"description": "NlpTools is a set of php 5.3+ classes for beginner to semi advanced natural language processing work.",
-	"keywords": ["nlp","machine learning"],
-	"license": "WTFPL",
-	"authors": [
-		{
-			"name": "Angelos Katharopoulos",
-			"email": "[email protected]"
-		}
-	],
-	"require": {
-		"php": ">=5.3"
-	},
-	"autoload": {
-		"psr-0": {
-			"NlpTools\\": "src/"
-		}
-	},
-	"extra": {
-		"branch-alias": {
-			"dev-master": "1.0.x-dev"
-		}
-	}
+    "name": "nlp-tools/nlp-tools",
+    "description": "NlpTools is a set of php 8.1+ classes for beginner to semi advanced natural language processing work.",
+    "keywords": ["nlp","machine learning"],
+    "license": "WTFPL",
+    "authors": [
+        {
+            "name": "Angelos Katharopoulos",
+            "email": "[email protected]"
+        }
+    ],
+    "require": {
+        "php": ">=8.1",
+        "ext-gd": "*"
+    },
+    "require-dev": {
+        "squizlabs/php_codesniffer": "^3.10",
+        "phpstan/phpstan": "^1.10",
+        "phpunit/phpunit": "^10.0 || ^11.0",
+        "rector/rector": "^1.0"
+    },
+    "autoload": {
+        "psr-0": {
+            "NlpTools\\": "src/"
+        }
+    }
 }

phpcs.xml

@@ -0,0 +1,24 @@
+<?xml version="1.0"?>
+<ruleset xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" name="PHP_CodeSniffer" xsi:noNamespaceSchemaLocation="phpcs.xsd">
+    <description>The coding standard.</description>
+
+    <config name="testVersion" value="8.0-"/>
+
+    <file>src</file>
+    <file>tests</file>
+    <exclude-pattern>*/tests/sentiment_maxent.php</exclude-pattern>
+
+    <arg name="basepath" value="./"/>
+    <arg name="colors"/>
+    <arg name="parallel" value="5"/>
+    <arg value="np"/>
+
+    <!-- Don't hide tokenizer exceptions -->
+    <rule ref="Internal.Tokenizer.Exception">
+        <type>error</type>
+    </rule>
+
+    <!-- Include the whole PSR12 standard -->
+    <rule ref="PSR12"/>
+
+</ruleset>

phpstan.neon

@@ -0,0 +1,8 @@
+parameters:
+    paths:
+        - ./src
+        - ./tests
+    excludePaths:
+        - ./tests/sentiment_maxent.php
+    # The level 9 is the highest level (with check for mixed type)
+    level: 6

phpunit.xml

@@ -0,0 +1,5 @@
+<phpunit bootstrap="tests/bootstrap.php" colors="true">
+    <testsuite name="NlpTools" >
+            <directory>./tests/NlpTools/</directory>
+    </testsuite>
+</phpunit>

rector.php

@@ -0,0 +1,51 @@
+<?php
+
+declare(strict_types=1);
+
+use Rector\Config\RectorConfig;
+use Rector\TypeDeclaration\Rector\ClassMethod\AddVoidReturnTypeWhereNoReturnRector;
+use Rector\Visibility\Rector\ClassConst\ChangeConstantVisibilityRector;
+use Rector\Naming\Rector\Foreach_\RenameForeachValueVariableToMatchExprVariableRector;
+use Rector\TypeDeclaration\Rector\ClassMethod\ReturnTypeFromReturnNewRector;
+use Rector\CodingStyle\Rector\FuncCall\CountArrayToEmptyArrayComparisonRector;
+use Rector\CodingStyle\Rector\FuncCall\StrictArraySearchRector;
+use Rector\CodingStyle\Rector\String_\SymplifyQuoteEscapeRector;
+use Rector\TypeDeclaration\Rector\StmtsAwareInterface\DeclareStrictTypesRector;
+use Rector\PHPUnit\Set\PHPUnitSetList;
+
+return RectorConfig::configure()
+    ->withPaths([
+        __DIR__.'/src',
+        __DIR__.'/tests',
+    ])
+    // uncomment to reach your current PHP version
+    ->withPhpSets()
+    ->withRules([
+        AddVoidReturnTypeWhereNoReturnRector::class,
+        ChangeConstantVisibilityRector::class,
+        RenameForeachValueVariableToMatchExprVariableRector::class,
+        ReturnTypeFromReturnNewRector::class,
+        CountArrayToEmptyArrayComparisonRector::class,
+        StrictArraySearchRector::class,
+        SymplifyQuoteEscapeRector::class,
+        DeclareStrictTypesRector::class,
+    ])
+    ->withSets([
+        PHPUnitSetList::PHPUNIT_110,
+    ])
+    ->withPhpSets()
+    ->withPHPStanConfigs(['phpstan.neon'])
+    ->withPreparedSets(
+        deadCode: true,
+        codeQuality: true,
+        codingStyle: true,
+        typeDeclarations: true,
+        privatization: true,
+        naming: true,
+        instanceOf: true,
+        earlyReturn: true,
+        strictBooleans: true
+    )
+    ->withSkip([
+        __DIR__ . '/tests/sentiment_maxent.php'
+    ]);