feat: refine normalizations

Author: jpedroh

src/main/injectors/GenericMergeModule.groovy

@@ -7,10 +7,9 @@ import interfaces.DataCollector
 import interfaces.OutputProcessor
 import interfaces.ProjectProcessor
 import services.commitFilters.MutuallyModifiedFilesCommitFilter
-import services.dataCollectors.mergeToolExecutors.JDimeMergeToolExecutorDataCollector
-import services.dataCollectors.mergeToolExecutors.LastMergeMergeToolExecutorDataCollector
-import services.dataCollectors.mergeToolExecutors.MergirafMergeToolExecutorDataCollector
-import services.dataCollectors.mergeToolExecutors.SporkMergeToolExecutorDataCollector
+import services.dataCollectors.common.RunDataCollectorsInParallel
+import services.dataCollectors.fileSyntacticNormalization.JDimeFileSyntacticNormalizationDataCollector
+import services.dataCollectors.fileSyntacticNormalization.SporkFileSyntacticNormalizationDataCollector
 import services.outputProcessors.EmptyOutputProcessor
 import services.projectProcessors.DummyProjectProcessor
 
@@ -22,11 +21,20 @@ class GenericMergeModule extends AbstractModule {
 
         Multibinder<DataCollector> dataCollectorBinder = Multibinder.newSetBinder(binder(), DataCollector.class)
 
-        // Run the merge tools on the scenarios
-        dataCollectorBinder.addBinding().to(JDimeMergeToolExecutorDataCollector.class)
-        dataCollectorBinder.addBinding().to(LastMergeMergeToolExecutorDataCollector.class)
-        dataCollectorBinder.addBinding().to(SporkMergeToolExecutorDataCollector.class)
-        dataCollectorBinder.addBinding().to(MergirafMergeToolExecutorDataCollector.class)
+//        // Run the merge tools on the scenarios
+//        dataCollectorBinder.addBinding().to(JDimeMergeToolExecutorDataCollector.class)
+//        dataCollectorBinder.addBinding().to(LastMergeMergeToolExecutorDataCollector.class)
+//        dataCollectorBinder.addBinding().to(SporkMergeToolExecutorDataCollector.class)
+//        dataCollectorBinder.addBinding().to(MergirafMergeToolExecutorDataCollector.class)
+
+        // Run, in parallel, normalizations on resulting files
+        dataCollectorBinder.addBinding().toInstance(new RunDataCollectorsInParallel([
+                new JDimeFileSyntacticNormalizationDataCollector("merge.java", "merge.jdime_normalized.java"),
+                new JDimeFileSyntacticNormalizationDataCollector("merge.last_merge.java", "merge.last_merge.jdime_normalized.java"),
+                new SporkFileSyntacticNormalizationDataCollector("merge.java", "merge.spork_normalized.java"),
+                new SporkFileSyntacticNormalizationDataCollector("merge.spork.java", "merge.spork.spork_normalized.java"),
+                new SporkFileSyntacticNormalizationDataCollector("merge.mergiraf.java", "merge.mergiraf.spork_normalized.java"),
+        ]))
 
         Multibinder<OutputProcessor> outputProcessorBinder = Multibinder.newSetBinder(binder(), OutputProcessor.class)
         outputProcessorBinder.addBinding().to(EmptyOutputProcessor.class)

src/main/services/dataCollectors/fileSyntacticNormalization/BaseFileSyntacticNormalizationDataCollector.groovy

@@ -12,7 +12,7 @@ import java.nio.file.Path
 import java.nio.file.StandardCopyOption
 
 abstract class BaseFileSyntacticNormalizationDataCollector implements DataCollector {
-    private static Logger LOG = LogManager.getLogger(BaseFileSyntacticNormalizationDataCollector.class)
+    protected static Logger LOG = LogManager.getLogger(BaseFileSyntacticNormalizationDataCollector.class)
 
     protected String inputFile
     protected String outputFile

src/main/services/dataCollectors/fileSyntacticNormalization/JDimeFileSyntacticNormalizationDataCollector.groovy

@@ -4,6 +4,7 @@ package services.dataCollectors.fileSyntacticNormalization
 import util.ProcessRunner
 
 import java.nio.file.Path
+import java.util.concurrent.TimeUnit
 
 class JDimeFileSyntacticNormalizationDataCollector extends BaseFileSyntacticNormalizationDataCollector {
     private static final String JDIME_BINARY_PATH = "${System.getProperty("user.dir")}/dependencies/jdime/install/JDime/bin"
@@ -23,7 +24,8 @@ class JDimeFileSyntacticNormalizationDataCollector extends BaseFileSyntacticNorm
                 inputFile.toAbsolutePath().toString(),
                 inputFile.toAbsolutePath().toString())
 
-        def exitCode = ProcessRunner.startProcess(processBuilder).waitFor()
-        return exitCode != 0
+        def output = ProcessRunner.startProcess(processBuilder)
+        def hasCompleted = output.waitFor(1, TimeUnit.HOURS)
+        return hasCompleted && output.exitValue() != 0
     }
 }

src/main/services/dataCollectors/fileSyntacticNormalization/SporkFileSyntacticNormalizationDataCollector.groovy

@@ -1,11 +1,12 @@
 package services.dataCollectors.fileSyntacticNormalization
 
-
 import org.apache.logging.log4j.LogManager
 import org.apache.logging.log4j.Logger
 import util.ProcessRunner
 
+import java.nio.file.Files
 import java.nio.file.Path
+import java.util.concurrent.TimeUnit
 
 class SporkFileSyntacticNormalizationDataCollector extends BaseFileSyntacticNormalizationDataCollector {
     private static Logger LOG = LogManager.getLogger(SporkFileSyntacticNormalizationDataCollector.class)
@@ -25,7 +26,8 @@ class SporkFileSyntacticNormalizationDataCollector extends BaseFileSyntacticNorm
         def process = ProcessRunner.startProcess(processBuilder)
         process.getInputStream().eachLine(LOG::trace)
         process.getErrorStream().eachLine(LOG::warn)
-        return true
+        def hasCompleted = process.waitFor(1, TimeUnit.HOURS)
+        return hasCompleted && Files.exists(outputFile)
     }
 
     private static List<String> getBuildParameters(Path inputFile, Path outputFile) {