Add Gherkin support to CPD

pmd-dist/pom.xml

@@ -149,6 +149,11 @@
             <artifactId>pmd-fortran</artifactId>
             <version>${project.version}</version>
         </dependency>
+        <dependency>
+            <groupId>net.sourceforge.pmd</groupId>
+            <artifactId>pmd-gherkin</artifactId>
+            <version>${project.version}</version>
+        </dependency>
         <dependency>
             <groupId>net.sourceforge.pmd</groupId>
             <artifactId>pmd-go</artifactId>

pmd-dist/src/test/java/net/sourceforge/pmd/it/BinaryDistributionIT.java

@@ -28,10 +28,10 @@ public class BinaryDistributionIT extends AbstractBinaryDistributionTest {
     static {
         // note: apex, javascript, visualforce, and scala require java8
         if (PMDExecutor.isJava7Test()) {
-            SUPPORTED_LANGUAGES_CPD = "Supported languages: [cpp, cs, dart, fortran, go, groovy, java, jsp, kotlin, lua, matlab, modelica, objectivec, perl, php, plsql, python, ruby, swift, xml]";
+            SUPPORTED_LANGUAGES_CPD = "Supported languages: [cpp, cs, dart, fortran, gherkin, go, groovy, java, jsp, kotlin, lua, matlab, modelica, objectivec, perl, php, plsql, python, ruby, swift, xml]";
             SUPPORTED_LANGUAGES_PMD = "java, jsp, modelica, plsql, pom, vm, wsdl, xml, xsl";
         } else {
-            SUPPORTED_LANGUAGES_CPD = "Supported languages: [apex, cpp, cs, dart, ecmascript, fortran, go, groovy, html, java, jsp, kotlin, lua, matlab, modelica, objectivec, perl, php, plsql, python, ruby, scala, swift, vf, xml]";
+            SUPPORTED_LANGUAGES_CPD = "Supported languages: [apex, cpp, cs, dart, ecmascript, fortran, gherkin, go, groovy, html, java, jsp, kotlin, lua, matlab, modelica, objectivec, perl, php, plsql, python, ruby, scala, swift, vf, xml]";
             SUPPORTED_LANGUAGES_PMD = "apex, ecmascript, html, java, jsp, modelica, plsql, pom, scala, vf, vm, wsdl, xml, xsl";
         }
     }

pmd-gherkin/pom.xml

@@ -0,0 +1,59 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <artifactId>pmd-gherkin</artifactId>
+    <name>PMD Gherkin</name>
+
+    <parent>
+        <groupId>net.sourceforge.pmd</groupId>
+        <artifactId>pmd</artifactId>
+        <version>6.46.0</version>
+        <relativePath>../</relativePath>
+    </parent>
+
+    <build>
+        <plugins>
+            <plugin>
+                <groupId>org.antlr</groupId>
+                <artifactId>antlr4-maven-plugin</artifactId>
+            </plugin>
+
+            <plugin>
+                <artifactId>maven-resources-plugin</artifactId>
+                <configuration>
+                    <useDefaultDelimiters>false</useDefaultDelimiters>
+                    <delimiters>
+                        <delimiter>${*}</delimiter>
+                    </delimiters>
+                </configuration>
+            </plugin>
+        </plugins>
+    </build>
+
+    <dependencies>
+        <dependency>
+            <groupId>net.sourceforge.pmd</groupId>
+            <artifactId>pmd-core</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>org.antlr</groupId>
+            <artifactId>antlr4-runtime</artifactId>
+        </dependency>
+
+        <dependency>
+            <groupId>junit</groupId>
+            <artifactId>junit</artifactId>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>net.sourceforge.pmd</groupId>
+            <artifactId>pmd-test</artifactId>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>net.sourceforge.pmd</groupId>
+            <artifactId>pmd-lang-test</artifactId>
+            <scope>test</scope>
+        </dependency>
+    </dependencies>
+</project>

pmd-gherkin/src/main/antlr4/net/sourceforge/pmd/lang/gherkin/antlr4/Gherkin.g4

@@ -0,0 +1,118 @@
+grammar Gherkin;
+
+// PARSER
+
+main
+    // start comment needed because each comment should start on a new line except for the start comment
+    : STARTCOMMENT? feature description* instructionLine* NL* EOF
+    ;
+
+feature
+    : (NL* tagline)* NL* FEATURE?
+    ;
+
+instructionLine
+    : NL+ (instruction | datatable)
+    ;
+
+instruction
+    : rulex description* // the name "rule" is not allowed by ANTLR (used for internal usage), so calling it rulex
+    | stepInstruction description* (NL+ stepDescription description*)* (NL+ step)*
+    | tagline
+    | instructionDescription description*
+    ;
+
+stepInstruction
+    : background
+    | scenario
+    | scenarioOutline
+    ;
+
+background: BACKGROUND ;
+rulex: RULEX ;
+scenario: SCENARIO ;
+scenarioOutline : SCENARIOOUTLINE ;
+
+step : stepItem description*;
+
+stepItem
+    : and
+    | anystep
+    | but
+    | datatable
+    | given
+    | then
+    | when
+    | (NL* tagline )* NL* examples
+    ;
+
+tagline
+    : TAG+
+    ;
+
+and: AND ;
+anystep: ANYSTEP ;
+but: BUT ;
+datatable: DATATABLE+ ;
+given: GIVEN ;
+then: THEN ;
+when: WHEN ;
+examples: EXAMPLES ;
+
+// Descriptions
+instructionDescription: text | PARAMETER | AND | ANYSTEP | BUT | GIVEN | THEN | WHEN | SCENARIO ; // We have to deal with overlaps with keywords
+stepDescription: text | PARAMETER ; // We have to deal with overlaps with keywords
+description: text | PARAMETER | TAG | AND | ANYSTEP | BUT | DATATABLE | GIVEN | THEN | WHEN | SCENARIO | SCENARIOOUTLINE | STARTCOMMENT ; // We have to deal with overlaps with keywords
+
+text: TOKEN+ ;
+
+// LEXER
+
+// skipped
+
+BOMUTF8 : '\u00EF\u00BB\u00BF' -> skip ;
+
+BOMUTF16 : '\uFEFF' -> skip ;
+
+WHITESPACE: [ \t]+ -> channel(1) ;
+
+COMMENT: '\r'?'\n' [ \t]* '#' ~[\r\n]* -> channel(2) ;
+
+STARTCOMMENT: '#' ~[\r\n]* ;
+
+DOCSTRING1
+    : '"""' .*? '"""' ;
+
+DOCSTRING2
+    : '```' .*? '```' ;
+
+// Instructions
+BACKGROUND: 'Background:' ;
+EXAMPLES: ('Examples:' | 'Scenarios:') ;
+FEATURE: 'Feature:';
+RULEX: 'Rule:' ;
+SCENARIO: ('Example:' | 'Scenario:') ;
+SCENARIOOUTLINE : 'Scenario ' ('Outline:' | 'Template:') ;
+
+// Steps
+AND: 'And' ;
+ANYSTEP: '*' ;
+BUT: 'But' ;
+DATATABLE: '|' DATATABLEID? ; // must be an ID because it can contain a space
+GIVEN: 'Given' ;
+THEN: 'Then' ;
+WHEN: 'When' ;
+
+TAG: '@' ELEMENT+ ;
+PARAMETER: '<' PARID '>' | '"' '<' PARID '>' '"' | '\'' '<' PARID '>' '\'';
+fragment PARID: [A-Za-z0-9] ([!-=?-~ ]* [!-=?-~])?; // start with an alpha numerical and then all printable characters and end with a non-space
+fragment ID: (IDELEMENT | ' ')* IDELEMENT (IDELEMENT | ' ')*; // ID should contain at least one non-whitespace character otherwise the trailing | with a trailing space will match
+fragment DATATABLEID: (DATATABLEELEMENT | ' ')* DATATABLEELEMENT (DATATABLEELEMENT | ' ')*; // ID should contain at least one non-whitespace character otherwise the trailing | with a trailing space will match
+fragment DATATABLEELEMENT: ELEMENT | '<' | '>' | '"' | '\'' | '\\|' ;
+fragment IDELEMENT: ELEMENT | '|' ;
+fragment ELEMENT: [!-&(-;=?-{}~\u00A0-\uFFFF] ;
+
+NL: '\r'? '\n' ;
+TOKEN: [!-{}-~\u00A0-\uFFFF]+ ; // match everything that isn't matched yet
+
+

pmd-gherkin/src/main/java/net/sourceforge/pmd/cpd/GherkinLanguage.java

@@ -0,0 +1,18 @@
+/**
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.cpd;
+
+/**
+ * Language implementation for Gherkin
+ */
+public class GherkinLanguage extends AbstractLanguage {
+
+    /**
+     * Creates a new Gherkin Language instance.
+     */
+    public GherkinLanguage() {
+        super("Gherkin", "gherkin", new GherkinTokenizer(), ".feature");
+    }
+}

pmd-gherkin/src/main/java/net/sourceforge/pmd/cpd/GherkinTokenizer.java

@@ -0,0 +1,28 @@
+/**
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.cpd;
+
+import org.antlr.v4.runtime.CharStream;
+
+import net.sourceforge.pmd.cpd.token.AntlrTokenFilter;
+import net.sourceforge.pmd.lang.antlr.AntlrTokenManager;
+import net.sourceforge.pmd.lang.gherkin.antlr4.GherkinLexer;
+
+/**
+ * The Gherkin Tokenizer
+ */
+public class GherkinTokenizer extends AntlrTokenizer {
+
+    @Override
+    protected AntlrTokenManager getLexerForSource(SourceCode sourceCode) {
+        CharStream charStream = AntlrTokenizer.getCharStreamFromSourceCode(sourceCode);
+        return new AntlrTokenManager(new GherkinLexer(charStream), sourceCode.getFileName());
+    }
+
+    @Override
+    protected AntlrTokenFilter getTokenFilter(final AntlrTokenManager tokenManager) {
+        return new AntlrTokenFilter(tokenManager);
+    }
+}

pmd-gherkin/src/main/java/net/sourceforge/pmd/lang/gherkin/antlr4/package-info.java

@@ -0,0 +1,11 @@
+/*
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+/**
+ * The class {@link net.sourceforge.pmd.lang.gherkin.antlr4.GherkinLexer} will be moved to
+ * package {@code net.sourceforge.pmd.lang.gherkin.ast} with PMD 7.
+ * 
+ * <p>All other classes will be removed.
+ */
+package net.sourceforge.pmd.lang.gherkin.antlr4;

pmd-gherkin/src/main/resources/META-INF/services/net.sourceforge.pmd.cpd.Language

@@ -0,0 +1 @@
+net.sourceforge.pmd.cpd.GherkinLanguage

pmd-gherkin/src/test/java/net/sourceforge/pmd/cpd/GherkinTokenizerTest.java

@@ -0,0 +1,43 @@
+/*
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.cpd;
+
+import java.util.Properties;
+
+import org.junit.Test;
+import org.junit.rules.ExpectedException;
+
+import net.sourceforge.pmd.cpd.test.CpdTextComparisonTest;
+
+public class GherkinTokenizerTest extends CpdTextComparisonTest {
+
+    @org.junit.Rule
+    public ExpectedException ex = ExpectedException.none();
+
+    public GherkinTokenizerTest() {
+        super(".feature");
+    }
+
+    @Override
+    protected String getResourcePrefix() {
+        return "../lang/gherkin/cpd/testdata";
+    }
+
+    @Override
+    public Tokenizer newTokenizer(Properties properties) {
+        GherkinTokenizer tok = new GherkinTokenizer();
+        return tok;
+    }
+
+    @Test
+    public void testAnnotatedSource() {
+        doTest("annotatedSource");
+    }
+
+    @Test
+    public void testDocstring() {
+        doTest("docstring");
+    }
+}

pmd-gherkin/src/test/resources/net/sourceforge/pmd/lang/gherkin/cpd/testdata/annotatedSource.feature

@@ -0,0 +1,73 @@
+@AnnotatedSource 
+Feature: Annotated Source
+  The annotated source displays violations in the source file. It opens in a new window.
+  
+  Rules:
+  1 Annotation metrics can be selected with a dropdown menu. Only enabled metrics must be shown.
+  2 When the annotated source is opened while a specific metric is selected, only that metric should be selected.
+  3 A user can scroll through the violations using two buttons (illustrated by up and down arrows). The arrows wrap around the document.
+  4 The table collumn "Type" is only shown when multiple metrics are selected
+
+  Scenario: Select a metric type
+   Given the Annotated Source for file "HIE://11261-37/main/monop/execute.c"
+    When a user opens the dropdown menu containing "Metric:"
+     And the user clicks on the dropdown option "Violations/Coding Standard Violations"
+    Then the selected annotation in the source code should be on line 38 
+     And the selected annotation in the table should be on line 38
+
+  Scenario: The user can use the arrows, or "a" and "z" keys, to scroll through the annotations
+  Given the Annotated Source for file "HIE://11261-37/main/monop/execute.c"
+    And metric "Coding Standard Violation Annotations" is selected
+   When the user clicks on the down arrow
+    And the user presses the "Z" key
+    And the user clicks on the up arrow
+    And the user clicks on the up arrow
+    And the user presses the "A" key
+   Then the selected annotation in the source code should be on line 254 
+
+  @Rule2
+  Scenario Outline: If the user opens the annotated source from e.g. the dashboard for a metric,
+    only the related annotations should be shown.
+  Given the Dashboard
+    And filtering by Project "17607"
+    And grouping by "File"
+    And metric "<metric>" is selected
+   When a user opens the file "clalgorithm_settings.c" using the metric table
+   Then a new browser window with an "Annotated Source" should be opened  
+   Then only the annotations "<annotations>" should be selected
+   
+  Examples:
+  | metric                     | annotations                           |
+  | TQI Coding Standards       | Coding Standard Violation Annotations |  
+  | Coding Standard Violations | Coding Standard Violation Annotations |  
+  | TQI Compiler Warnings      | Compiler Warning Annotations          |  
+  | Fan Out (%)                | Fan Out Annotations                   |  
+  | TQI Dead Code              | Dead Code Annotations                 |  
+  | TQI Code Duplication       | Code Duplication Annotations          |
+  
+  Scenario: The user should be able to filter Coding Standard Violations by Level
+    Given the Annotated Source for file "HIE://11514/trunk/components/java/BuildUtil/src/com/tiobe/util/BuildProperties.java"
+    And   the metric "Coding Standard Violations" is selected
+    When  the user opens the dropdown menu "Level"
+    And   the user clicks on the dropdown option "5"
+    Then  there should be 1 violation
+    And   the selected annotation in the source code should be on line 57
+    And   the annotation should be of level 5 
+
+  @PR27030
+  Scenario Outline: The user should be able to filter Coding Standard Violations by Level, Category, Rule, etc
+    Given the Annotated Source for file "HIE://12939/main/Implementatie/DRGL/src/DirectDoorvoerenAdmin.cpp"
+    And metric "<metric>" is selected
+    When the user opens the dropdown menu containing "<filter>" inside the filter bar
+    And the user clicks on the dropdown option "<option>"
+    Then there should be <number> violations
+    
+  Examples:
+    | metric                      | filter        | option      | number  |
+    | Coding Standard Violations  | Level         | 2           | 7       | 
+    | Coding Standard Violations  | Category      | Comments    | 1       |
+    | Coding Standard Violations  | Rule          | CFL#011     | 2       |
+    | Coding Standard Violations  | Suppressions  | Yes         | 0       |
+    | TQI Code Coverage           | Coverage Type | Decision    | 7       |
+    | TQI Code Coverage           | Kind          | Issue       | 10      |
+

pmd-gherkin/src/test/resources/net/sourceforge/pmd/lang/gherkin/cpd/testdata/docstring.feature

@@ -0,0 +1,6 @@
+Given I have a lot to say:
+"""
+ One
+ Two
+ Three
+ """

pmd-gherkin/src/test/resources/net/sourceforge/pmd/lang/gherkin/cpd/testdata/docstring.txt

@@ -0,0 +1,15 @@
+    [Image] or [Truncated image[            Bcol      Ecol
+L1
+    [Given]                                 1         5
+    [I]                                     7         7
+    [have]                                  9         12
+    [a]                                     14        14
+    [lot]                                   16        18
+    [to]                                    20        21
+    [say:]                                  23        26
+    [\n]                                    27        27
+L2
+    ["""\n One\n Two\n Three\n """]         1         4
+L6
+    [\n]                                    5         5
+EOF

pom.xml

@@ -1067,6 +1067,7 @@
         <module>pmd-dart</module>
         <module>pmd-dist</module>
         <module>pmd-fortran</module>
+        <module>pmd-gherkin</module>
         <module>pmd-go</module>
         <module>pmd-groovy</module>
         <module>pmd-lua</module>