Improve percentages

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

@@ -32,11 +32,12 @@ class CpdRunner {
     public Map<String, CpdLanguageRunResults> run(CpdRunInputData runInputData) throws IOException {
         validateRunInputData(runInputData);
 
-        List<String> languagesToProcess = new ArrayList<>(runInputData.runDataPerLanguage.keySet());
-        progressReporter.initialize(languagesToProcess);
+        Map<String, Integer> languageFileCounts = runInputData.runDataPerLanguage.entrySet().stream()
+                .collect(Collectors.toMap(Map.Entry::getKey, entry -> entry.getValue().filesToScan.size()));
+        progressReporter.initialize(languageFileCounts);
 
         Map<String, CpdLanguageRunResults> results = new HashMap<>();
-        for (String language : languagesToProcess) {
+        for (String language : runInputData.runDataPerLanguage.keySet()) {
             CpdRunInputData.LanguageSpecificRunData languageSpecificRunData = runInputData.runDataPerLanguage.get(language);
             List<Path> pathsToScan = languageSpecificRunData.filesToScan.stream().map(Paths::get).collect(Collectors.toList());
             CpdLanguageRunResults languageRunResults = runLanguage(
@@ -49,6 +50,9 @@ public Map<String, CpdLanguageRunResults> run(CpdRunInputData runInputData) thro
     }
 
     private CpdLanguageRunResults runLanguage(String language, List<Path> pathsToScan, int minimumTokens, boolean skipDuplicateFiles) throws IOException {
+        System.out.println("Running CPD for language '" + language + "' with " + pathsToScan.size() +
+                " file(s) to scan using minimumTokens=" + minimumTokens + " and skipDuplicateFiles=" + skipDuplicateFiles + ".");
+
         // 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

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

@@ -24,11 +24,12 @@ public class PmdRunner {
     PmdRunResults run(PmdRunInputData inputData) {
         validateRunInputData(inputData);
 
-        List<String> languagesToProcess = new ArrayList<>(inputData.runDataPerLanguage.keySet());
-        progressReporter.initialize(languagesToProcess);
+        Map<String, Integer> languageFileCounts = inputData.runDataPerLanguage.entrySet().stream()
+                .collect(Collectors.toMap(Map.Entry::getKey, entry -> entry.getValue().filesToScan.size()));
+        progressReporter.initialize(languageFileCounts);
 
         PmdRunResults runResults = new PmdRunResults();
-        for (String language: languagesToProcess) {
+        for (String language: inputData.runDataPerLanguage.keySet()) {
             runLanguage(language, inputData, runResults);
         }
         return runResults;
@@ -37,6 +38,8 @@ PmdRunResults run(PmdRunInputData inputData) {
     private void runLanguage(String language, PmdRunInputData inputData, PmdRunResults runResults) {
         PmdRunInputData.LanguageSpecificRunData languageSpecificRunData = inputData.runDataPerLanguage.get(language);
 
+        System.out.println("Running PMD rules for language '" + language + "' with " + languageSpecificRunData.filesToScan.size() + " file(s) to scan.");
+
         PMDConfiguration config = new PMDConfiguration();
         config.addRuleSet(inputData.ruleSetInputFile);
         List<Path> inputPathList = languageSpecificRunData.filesToScan.stream().map(Paths::get).collect(Collectors.toList());

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

@@ -6,12 +6,21 @@
 
 // This class helps us track the overall progress of all language runs
 public class ProgressReporter {
+    private Map<String, Float> languageWeight = new HashMap<>();
     private Map<String, Float> progressPerLanguage = new HashMap<>();
     private float lastReportedProgress = 0.0f;
 
-    public void initialize(List<String> languages) {
+    public void initialize(Map<String, Integer> languageFileCounts) {
         progressPerLanguage = new HashMap<>();
-        languages.forEach(l -> this.updateProgressForLanguage(l, 0.0f));
+        languageWeight = new HashMap<>();
+        int totalNumFilesToScan = languageFileCounts.values().stream().mapToInt(Integer::intValue).sum();
+        for (Map.Entry<String,Integer> entry : languageFileCounts.entrySet()) {
+            String language = entry.getKey();
+            Integer numFiles = entry.getValue();
+            languageWeight.put(language, (float) numFiles / totalNumFilesToScan);
+            this.updateProgressForLanguage(language, 0.0f);
+
+        }
     }
 
     public void updateProgressForLanguage(String language, float percComplete) {
@@ -28,10 +37,10 @@ public void reportOverallProgress() {
     }
 
     private float calculateOverallPercentage() {
-        float sum = 0.0f;
-        for (float progress : progressPerLanguage.values()) {
-            sum += progress;
+        float overallPerc = 0.0f;
+        for (String language : progressPerLanguage.keySet()) {
+            overallPerc += (progressPerLanguage.get(language) * languageWeight.get(language));
         }
-        return sum / progressPerLanguage.size();
+        return overallPerc;
     }
 }

packages/code-analyzer-pmd-engine/src/cpd-wrapper.ts

@@ -73,8 +73,9 @@ export class CpdWrapperInvoker {
             if (stdOutMsg.startsWith(STDOUT_PROGRESS_MARKER)) {
                 const cpdWrapperProgress: number = parseFloat(stdOutMsg.slice(STDOUT_PROGRESS_MARKER.length));
                 emitProgress(10 + 80*(cpdWrapperProgress/100)); // 10 to 90%
+            } else {
+                this.emitLogEvent(LogLevel.Fine, `[JAVA StdOut]: ${stdOutMsg}`);
             }
-            this.emitLogEvent(LogLevel.Fine, `[JAVA StdOut]: ${stdOutMsg}`);
         });
 
         try {

packages/code-analyzer-pmd-engine/src/pmd-engine.ts

@@ -188,7 +188,8 @@ function toSeverityLevel(pmdRulePriority: string): SeverityLevel {
 
 function toViolation(pmdViolation: PmdViolation): Violation {
     return {
-        ruleName: toUniqueRuleName(pmdViolation.rule, extensionToLanguageId[path.extname(pmdViolation.codeLocation.file)]),
+        ruleName: toUniqueRuleName(pmdViolation.rule,
+            extensionToLanguageId[path.extname(pmdViolation.codeLocation.file).toLowerCase()]),
         message: pmdViolation.message,
         codeLocations: [{
             file: pmdViolation.codeLocation.file,

packages/code-analyzer-pmd-engine/src/pmd-wrapper.ts

@@ -126,7 +126,7 @@ export class PmdWrapperInvoker {
         await this.javaCommandExecutor.exec(javaCmdArgs, javaClassPaths, (stdOutMsg: string) => {
             if (stdOutMsg.startsWith(STDOUT_PROGRESS_MARKER)) {
                 const pmdWrapperProgress: number = parseFloat(stdOutMsg.slice(STDOUT_PROGRESS_MARKER.length));
-                emitProgress(10 + (80 * pmdWrapperProgress / 100)); // 10 to 90%
+                emitProgress(10 + 80*(pmdWrapperProgress/100)); // 10 to 90%
             } else {
                 this.emitLogEvent(LogLevel.Fine, `[JAVA StdOut]: ${stdOutMsg}`);
             }

packages/code-analyzer-pmd-engine/test/pmd-engine.test.ts

@@ -448,7 +448,7 @@ describe('Tests for the runRules method of PmdEngine', () => {
 
         // Also check that we have all the correct progress events
         expect(progressEvents.map(e => e.percentComplete)).toEqual(
-            [2, 2.3, 4.4, 4.7, 5, 6.86, 10.58, 14.3, 23.6, 32.9, 42.2, 51.5, 70.1, 88.7, 93.35, 98, 100]);
+            [2, 2.3, 4.4, 4.7, 5, 6.86, 10.58, 14.3, 26.7, 39.1, 51.5, 63.9, 76.3, 88.7, 93.35, 98, 100]);
     });
 
     it('When a single rule is selected, then return only violations for that rule', async () => {