Add gherkin to work with exact values (#21)

* add test for multiline different

* add gehrking parser to be sure

Author: TomasVotruba

README.md

@@ -108,7 +108,7 @@ This rule spots definitions that are no longer needed, so you can  remove them.
 
 <br>
 
-### 4. Find duplicate scenario names (`duplicate-scenario-names`)
+### 4. Find duplicate scenario titles (`duplicate-scenario-titles`)
 
 In Behat, each scenario should have a unique name to ensure clarity and avoid confusion during test execution and later debugging. This rule identifies scenarios that share the same name within your feature files:
 

composer.json

@@ -7,8 +7,9 @@
     ],
     "require": {
         "php": "^8.3",
-        "nette/utils": "^4.0",
+        "behat/gherkin": "^4.16",
         "entropy/entropy": "dev-main",
+        "nette/utils": "^4.0",
         "nikic/php-parser": "^5.6",
         "symfony/finder": "^7.0",
         "webmozart/assert": "^1.12"
@@ -19,6 +20,7 @@
         "phpunit/phpunit": "^12.5",
         "rector/jack": "^0.5.1",
         "rector/rector": "^2.3.2",
+        "shipmonk/composer-dependency-analyser": "^1.8",
         "symplify/easy-coding-standard": "^13.0",
         "tomasvotruba/class-leak": "^2.1",
         "tracy/tracy": "^2.10"

…yzer/DuplicatedScenarioNamesAnalyzer.php …zer/DuplicatedScenarioTitlesAnalyzer.phpsrc/Analyzer/DuplicatedScenarioNamesAnalyzer.php renamed to src/Analyzer/DuplicatedScenarioTitlesAnalyzer.php src/Analyzer/DuplicatedScenarioNamesAnalyzer.php renamed to src/Analyzer/DuplicatedScenarioTitlesAnalyzer.php

@@ -5,14 +5,17 @@
 namespace Rector\Behastan\Analyzer;
 
 use Entropy\Attributes\RelatedTest;
-use Entropy\Utils\Regex;
-use Rector\Behastan\Tests\Analyzer\DuplicatedScenarioNamesAnalyzer\DuplicatedScenarioNamesAnalyzerTest;
+use Rector\Behastan\Gherkin\GherkinParser;
+use Rector\Behastan\Tests\Analyzer\DuplicatedScenarioNamesAnalyzer\DuplicatedScenarioTitlesAnalyzerTest;
 use Symfony\Component\Finder\SplFileInfo;
 
-#[RelatedTest(DuplicatedScenarioNamesAnalyzerTest::class)]
-final class DuplicatedScenarioNamesAnalyzer
+#[RelatedTest(DuplicatedScenarioTitlesAnalyzerTest::class)]
+final readonly class DuplicatedScenarioTitlesAnalyzer
 {
-    private const string SCENARIO_NAME_REGEX = '#\s+Scenario:\s+(?<name>.*?)\n#';
+    public function __construct(
+        private GherkinParser $gherkinParser
+    ) {
+    }
 
     /**
      * @param SplFileInfo[] $featureFiles
@@ -23,12 +26,10 @@ public function analyze(array $featureFiles): array
         $scenarioNamesToFiles = [];
 
         foreach ($featureFiles as $featureFile) {
-            // match Scenario: "<name>"
-            $matches = Regex::matchAll($featureFile->getContents(), self::SCENARIO_NAME_REGEX);
+            $featureGherkin = $this->gherkinParser->parseFile($featureFile->getRealPath());
 
-            foreach ($matches as $match) {
-                $scenarioName = $match['name'];
-                $scenarioNamesToFiles[$scenarioName][] = $featureFile->getRealPath();
+            foreach ($featureGherkin->getScenarios() as $scenario) {
+                $scenarioNamesToFiles[$scenario->getTitle()][] = $featureFile->getRealPath();
             }
         }
 

src/Enum/RuleIdentifier.php

@@ -8,7 +8,7 @@ final class RuleIdentifier
 {
     public const string DUPLICATED_CONTENTS = 'duplicated-contents';
 
-    public const string DUPLICATED_SCENARIO_NAMES = 'duplicated-scenario-names';
+    public const string DUPLICATED_SCENARIO_TITLES = 'duplicated-scenario-titles';
 
     public const string DUPLICATED_PATTERNS = 'duplicated-patterns';
 

src/Gherkin/GherkinParser.php

@@ -0,0 +1,44 @@
+<?php
+
+declare(strict_types=1);
+
+namespace Rector\Behastan\Gherkin;
+
+use Behat\Gherkin\Keywords\ArrayKeywords;
+use Behat\Gherkin\Lexer;
+use Behat\Gherkin\Node\FeatureNode;
+use Behat\Gherkin\Parser;
+use Webmozart\Assert\Assert;
+
+final class GherkinParser
+{
+    private Parser $parser;
+
+    public function __construct()
+    {
+        $arrayKeywords = new ArrayKeywords([
+            'en' => [
+                'feature' => 'Feature',
+                'background' => 'Background',
+                'scenario' => 'Scenario',
+                'scenario_outline' => 'Scenario Outline|Scenario Template',
+                'examples' => 'Examples|Scenarios',
+                'given' => 'Given',
+                'when' => 'When',
+                'then' => 'Then',
+                'and' => 'And',
+                'but' => 'But',
+            ],
+        ]);
+
+        $this->parser = new Parser(new Lexer($arrayKeywords));
+    }
+
+    public function parseFile(string $filePath): FeatureNode
+    {
+        $featureNode = $this->parser->parseFile($filePath);
+        Assert::isInstanceOf($featureNode, FeatureNode::class);
+
+        return $featureNode;
+    }
+}

src/Rule/DuplicatedScenarioNamesRule.php src/Rule/DuplicatedScenarioTitleRule.phpsrc/Rule/DuplicatedScenarioNamesRule.php renamed to src/Rule/DuplicatedScenarioTitleRule.php

@@ -4,17 +4,17 @@
 
 namespace Rector\Behastan\Rule;
 
-use Rector\Behastan\Analyzer\DuplicatedScenarioNamesAnalyzer;
+use Rector\Behastan\Analyzer\DuplicatedScenarioTitlesAnalyzer;
 use Rector\Behastan\Contract\RuleInterface;
 use Rector\Behastan\Enum\RuleIdentifier;
 use Rector\Behastan\ValueObject\PatternCollection;
 use Rector\Behastan\ValueObject\RuleError;
 use Symfony\Component\Finder\SplFileInfo;
 
-final readonly class DuplicatedScenarioNamesRule implements RuleInterface
+final readonly class DuplicatedScenarioTitleRule implements RuleInterface
 {
     public function __construct(
-        private DuplicatedScenarioNamesAnalyzer $duplicatedScenarioNamesAnalyzer
+        private DuplicatedScenarioTitlesAnalyzer $duplicatedScenarioNamesAnalyzer
     ) {
     }
 
@@ -47,6 +47,6 @@ public function process(
 
     public function getIdentifier(): string
     {
-        return RuleIdentifier::DUPLICATED_SCENARIO_NAMES;
+        return RuleIdentifier::DUPLICATED_SCENARIO_TITLES;
     }
 }

tests/Analyzer/DuplicatedScenarioNamesAnalyzer/DuplicatedScenarioNamesAnalyzerTest.php

@@ -0,0 +1,49 @@
+<?php
+
+declare(strict_types=1);
+
+namespace Rector\Behastan\Tests\Analyzer\DuplicatedScenarioNamesAnalyzer;
+
+use Rector\Behastan\Analyzer\DuplicatedScenarioTitlesAnalyzer;
+use Rector\Behastan\Finder\BehatMetafilesFinder;
+use Rector\Behastan\Tests\AbstractTestCase;
+
+final class DuplicatedScenarioTitlesAnalyzerTest extends AbstractTestCase
+{
+    private DuplicatedScenarioTitlesAnalyzer $duplicatedScenarioNamesAnalyzer;
+
+    protected function setUp(): void
+    {
+        parent::setUp();
+
+        $this->duplicatedScenarioNamesAnalyzer = $this->make(DuplicatedScenarioTitlesAnalyzer::class);
+    }
+
+    public function testSpot(): void
+    {
+        $featureFiles = BehatMetafilesFinder::findFeatureFiles([__DIR__ . '/Fixture/simple']);
+        $this->assertCount(2, $featureFiles);
+
+        $duplicatedScenarioNamesToFiles = $this->duplicatedScenarioNamesAnalyzer->analyze($featureFiles);
+
+        $this->assertCount(1, $duplicatedScenarioNamesToFiles);
+        $this->assertArrayHasKey('Same scenario name', $duplicatedScenarioNamesToFiles);
+
+        $givenFiles = $duplicatedScenarioNamesToFiles['Same scenario name'];
+
+        $this->assertSame(
+            [__DIR__ . '/Fixture/simple/some.feature', __DIR__ . '/Fixture/simple/another.feature'],
+            $givenFiles
+        );
+    }
+
+    public function testSkipSecondLineDifferent(): void
+    {
+        $featureFiles = BehatMetafilesFinder::findFeatureFiles([__DIR__ . '/Fixture/no-multi-line']);
+        $this->assertCount(2, $featureFiles);
+
+        $duplicatedScenarioNamesToFiles = $this->duplicatedScenarioNamesAnalyzer->analyze($featureFiles);
+
+        $this->assertCount(0, $duplicatedScenarioNamesToFiles);
+    }
+}

tests/Analyzer/DuplicatedScenarioNamesAnalyzer/DuplicatedScenarioTitlesAnalyzerTest.php

@@ -0,0 +1,4 @@
+Feature: Some feature
+
+  Scenario: Same scenario name But second line is different
+    Given that

tests/Analyzer/DuplicatedScenarioNamesAnalyzer/Fixture/no-multi-line/another.feature

@@ -0,0 +1,4 @@
+Feature: Another feature
+
+  Scenario: Same scenario name But second line is not the same
+    Given This