NEW(cpd): @W-16866828@: Implemented the runRules method for CPD (with no configuration yet) (#118)

Author: stephen-carter-at-sf

…-pmd-engine/pmd-wrapper/build.gradle.kts …engine/pmd-cpd-wrappers/build.gradle.ktspackages/code-analyzer-pmd-engine/pmd-wrapper/build.gradle.kts renamed to packages/code-analyzer-pmd-engine/pmd-cpd-wrappers/build.gradle.kts packages/code-analyzer-pmd-engine/pmd-wrapper/build.gradle.kts renamed to packages/code-analyzer-pmd-engine/pmd-cpd-wrappers/build.gradle.kts

@@ -42,7 +42,7 @@ application {
 
 
 // Directories of interest
-val pmdWrapperDistDir: String = layout.projectDirectory.dir("../dist/pmd-wrapper").asFile.path;
+val pmdCpdWrappersDistDir: String = layout.projectDirectory.dir("../dist/pmd-cpd-wrappers").asFile.path;
 val reportsDir: String = layout.buildDirectory.dir("reports").get().asFile.path
 
 
@@ -59,7 +59,7 @@ tasks.distTar {
 // During assemble, we want to run the installDist task (which comes from the distribution plugin which comes from the application plugin)
 // instead ... but first we need to modify the location where the jar files should be placed.
 tasks.installDist {
-    into(pmdWrapperDistDir)
+    into(pmdCpdWrappersDistDir)
     includeEmptyDirs = false
 }
 tasks.assemble {
@@ -102,9 +102,9 @@ tasks.register("showCoverageReport") {
 
 
 // ======== CLEAN RELATED TASKS ========================================================================================
-tasks.register<Delete>("deletePmdWrapperFromDist") {
-    delete(pmdWrapperDistDir)
+tasks.register<Delete>("deletePmdCpdWrappersFromDist") {
+    delete(pmdCpdWrappersDistDir)
 }
 tasks.named("clean") {
-    dependsOn("deletePmdWrapperFromDist")
+    dependsOn("deletePmdCpdWrappersFromDist")
 }

packages/code-analyzer-pmd-engine/pmd-cpd-wrappers/src/main/java/com/salesforce/sfca/cpdwrapper/CpdLanguageRunResults.java

@@ -0,0 +1,34 @@
+package com.salesforce.sfca.cpdwrapper;
+
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ * Java object to help build cpd results for a specific language.
+ * We will serialize Map<String, CpdLanguageRunResults> to json to create the overall results for all languages.
+ */
+public class CpdLanguageRunResults {
+    public List<Match> matches = new ArrayList<>();
+    public List<ProcessingError> processingErrors = new ArrayList<>();
+
+    public static class Match {
+        public int numTokensInBlock;
+        public int numNonemptyLinesInBlock;
+        public int numBlocks;
+        public List<BlockLocation> blockLocations = new ArrayList<>();
+
+        public static class BlockLocation {
+            public String file;
+            public int startLine;
+            public int startCol;
+            public int endLine;
+            public int endCol;
+        }
+    }
+
+    public static class ProcessingError {
+        public String file;
+        public String message;
+        public String detail;
+    }
+}

…rce/sfca/cpdwrapper/CpdRunInputData.java …rce/sfca/cpdwrapper/CpdRunInputData.javapackages/code-analyzer-pmd-engine/pmd-wrapper/src/main/java/com/salesforce/sfca/cpdwrapper/CpdRunInputData.java renamed to packages/code-analyzer-pmd-engine/pmd-cpd-wrappers/src/main/java/com/salesforce/sfca/cpdwrapper/CpdRunInputData.java packages/code-analyzer-pmd-engine/pmd-wrapper/src/main/java/com/salesforce/sfca/cpdwrapper/CpdRunInputData.java renamed to packages/code-analyzer-pmd-engine/pmd-cpd-wrappers/src/main/java/com/salesforce/sfca/cpdwrapper/CpdRunInputData.java

@@ -15,7 +15,6 @@
 import java.nio.file.Path;
 import java.nio.file.Paths;
 import java.text.MessageFormat;
-import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
@@ -25,10 +24,10 @@
  * Class to help us invoke CPD - once for each language that should be processed
  */
 class CpdRunner {
-    public Map<String, List<CpdMatch>> run(CpdRunInputData runInputData) throws IOException {
+    public Map<String, CpdLanguageRunResults> run(CpdRunInputData runInputData) throws IOException {
         validateRunInputData(runInputData);
 
-        Map<String, List<CpdMatch>> results = new HashMap<>();
+        Map<String, CpdLanguageRunResults> results = new HashMap<>();
 
         for (Map.Entry<String, List<String>> entry : runInputData.filesToScanPerLanguage.entrySet()) {
             String language = entry.getKey();
@@ -37,17 +36,17 @@ public Map<String, List<CpdMatch>> run(CpdRunInputData runInputData) throws IOEx
                 continue;
             }
             List<Path> pathsToScan = filesToScan.stream().map(Paths::get).collect(Collectors.toList());
-            List<CpdMatch> languageMatches = runLanguage(language, pathsToScan, runInputData.minimumTokens, runInputData.skipDuplicateFiles);
+            CpdLanguageRunResults languageRunResults = runLanguage(language, pathsToScan, runInputData.minimumTokens, runInputData.skipDuplicateFiles);
 
-            if (!languageMatches.isEmpty()) {
-                results.put(language, languageMatches);
+            if (!languageRunResults.matches.isEmpty() || !languageRunResults.processingErrors.isEmpty()) {
+                results.put(language, languageRunResults);
             }
         }
 
         return results;
     }
 
-    private List<CpdMatch> runLanguage(String language, List<Path> pathsToScan, int minimumTokens, boolean skipDuplicateFiles) throws IOException {
+    private CpdLanguageRunResults runLanguage(String language, List<Path> pathsToScan, int minimumTokens, boolean skipDuplicateFiles) throws IOException {
         // Note that the name "minimumTokens" comes from the public facing documentation and the cli but
         // behind the scenes, it maps to MinimumTileSize. To learn more about the mappings to the config, see:
         // https://github.com/pmd/pmd/blob/main/pmd-cli/src/main/java/net/sourceforge/pmd/cli/commands/internal/CpdCommand.java
@@ -62,23 +61,27 @@ private List<CpdMatch> runLanguage(String language, List<Path> pathsToScan, int
         config.setSkipDuplicates(skipDuplicateFiles);
         config.setReporter(new CpdErrorListener());
 
-        List<CpdMatch> cpdMatches = new ArrayList<>();
+        CpdLanguageRunResults languageRunResults = new CpdLanguageRunResults();
 
         try (CpdAnalysis cpd = CpdAnalysis.create(config)) {
             cpd.performAnalysis(report -> {
-                for (Report.ProcessingError processingError : report.getProcessingErrors()) {
-                    // We don't expect any processing errors, but if there are any, then we can push them
-                    // to stdOut so that they ultimately get logged. But we should continue as normal here.
-                    System.out.println("Unexpected CPD processing error: " + processingError.getError().getMessage());
+
+                for (Report.ProcessingError reportProcessingError : report.getProcessingErrors()) {
+                    CpdLanguageRunResults.ProcessingError processingErr = new CpdLanguageRunResults.ProcessingError();
+                    processingErr.file = reportProcessingError.getFileId().getAbsolutePath();
+                    processingErr.message = reportProcessingError.getMsg();
+                    processingErr.detail = reportProcessingError.getDetail();
+                    languageRunResults.processingErrors.add(processingErr);
                 }
+
                 for (Match match : report.getMatches()) {
-                    CpdMatch cpdMatch = new CpdMatch();
+                    CpdLanguageRunResults.Match cpdMatch = new CpdLanguageRunResults.Match();
                     cpdMatch.numBlocks = match.getMarkCount();
                     cpdMatch.numTokensInBlock = match.getTokenCount();
                     cpdMatch.numNonemptyLinesInBlock = match.getLineCount();
 
                     for (Mark mark : match.getMarkSet()) {
-                        CpdMatch.BlockLocation blockLocation = new CpdMatch.BlockLocation();
+                        CpdLanguageRunResults.Match.BlockLocation blockLocation = new CpdLanguageRunResults.Match.BlockLocation();
                         FileLocation location = mark.getLocation();
                         blockLocation.file = location.getFileId().getAbsolutePath();
                         blockLocation.startLine = location.getStartLine();
@@ -89,12 +92,12 @@ private List<CpdMatch> runLanguage(String language, List<Path> pathsToScan, int
                         cpdMatch.blockLocations.add(blockLocation);
                     }
 
-                    cpdMatches.add(cpdMatch);
+                    languageRunResults.matches.add(cpdMatch);
                 }
             });
         }
 
-        return cpdMatches;
+        return languageRunResults;
     }
 
     private void validateRunInputData(CpdRunInputData runInputData) {

…alesforce/sfca/cpdwrapper/CpdRunner.java …alesforce/sfca/cpdwrapper/CpdRunner.javapackages/code-analyzer-pmd-engine/pmd-wrapper/src/main/java/com/salesforce/sfca/cpdwrapper/CpdRunner.java renamed to packages/code-analyzer-pmd-engine/pmd-cpd-wrappers/src/main/java/com/salesforce/sfca/cpdwrapper/CpdRunner.java packages/code-analyzer-pmd-engine/pmd-wrapper/src/main/java/com/salesforce/sfca/cpdwrapper/CpdRunner.java renamed to packages/code-analyzer-pmd-engine/pmd-cpd-wrappers/src/main/java/com/salesforce/sfca/cpdwrapper/CpdRunner.java

@@ -4,7 +4,6 @@
 import java.io.FileWriter;
 import java.io.IOException;
 import java.util.Arrays;
-import java.util.List;
 import java.util.Map;
 
 import com.google.gson.Gson;
@@ -29,24 +28,27 @@
  *         - {resultsOutputFile} is a JSON file to write CPD results to.
  *             Example:
  *                 {
- *                     "apex": [
- *                         {
- *                             "numTokensInBlock": 18,
- *                             "numNonemptyLinesInBlock": 5,
- *                             "numBlocks": 2,
- *                             "blockLocations": [
- *                                 {
- *                                     "file": "/full/path/to/file1.cls",
- *                                     "startLine": 1, "startCol": 1, "endLine": 5, "endCol": 2
- *                                 },
- *                                 {
- *                                     "file": "/full/path/to/file2.cls",
- *                                     "startLine": 18, "startCol": 6, "endLine": 22, "endCol": 8
- *                                 }
- *                             ]
- *                         },
- *                         ...
- *                     ],
+ *                     "apex": {
+ *                         matches: [
+ *                             {
+ *                                 "numTokensInBlock": 18,
+ *                                 "numNonemptyLinesInBlock": 5,
+ *                                 "numBlocks": 2,
+ *                                 "blockLocations": [
+ *                                     {
+ *                                         "file": "/full/path/to/file1.cls",
+ *                                         "startLine": 1, "startCol": 1, "endLine": 5, "endCol": 2
+ *                                     },
+ *                                     {
+ *                                         "file": "/full/path/to/file2.cls",
+ *                                         "startLine": 18, "startCol": 6, "endLine": 22, "endCol": 8
+ *                                     }
+ *                                 ]
+ *                             },
+ *                             ...
+ *                         ],
+ *                         processingErrors: []
+ *                     },
  *                     "xml": ...
  *                 }
  */
@@ -84,7 +86,7 @@ private static void invokeRunCommand(String[] args) {
         }
 
         CpdRunner cpdRunner = new CpdRunner();
-        Map<String, List<CpdMatch>> results;
+        Map<String, CpdLanguageRunResults> results;
         try {
             results = cpdRunner.run(inputData);
         } catch (Exception e) {