Merge pull request #1 from jenkinsci/git-forensics

Add Git repository miner

Author: uhafner

.dependabot/config.yml

@@ -0,0 +1,6 @@
+version: 1
+
+update_configs:
+  - package_manager: "java:maven"
+    directory: "/"
+    update_schedule: "daily"

.github/release-drafter.yml

@@ -0,0 +1,33 @@
+_extends: .github
+tag-template: git-forensics-$NEXT_MINOR_VERSION
+name-template: Git Forensics $NEXT_PATCH_VERSION 🎁
+version-template: $MAJOR.$MINOR.$PATCH
+
+template: |
+  $CHANGES
+
+categories:
+  - title: 🚨 Removed
+    label: removed
+  - title: ⚠️ Deprecated
+    label: deprecated
+  - title: 🚀 New features and improvements
+    labels:
+      - enhancement
+      - feature
+  - title: 🐛 Bug Fixes
+    labels:
+      - bug
+      - fix
+      - bugfix
+      - regression
+  - title: 📖 Documentation updates
+    label: documentation
+  - title: 📦 Dependency updates
+    label: dependencies
+  - title: 🔧 Internal changes
+    label: internal
+  - title: 🚦 Tests
+    labels:
+      - test
+      - tests

CHANGELOG.md

@@ -1,7 +1,6 @@
-# Changelog
-All notable changes to this project will be documented in this file.
+# Changelog 
 
-The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
-and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+All notable changes of this project will be automatically logged by release drafter in 
+[GitHub releases](https://github.com/jenkinsci/git-forensics-plugin/releases). 
 
-## [Unreleased](https://github.com/uhafner/git-forensics-plugin/compare/9f25c5b9d19dccf07e97bfe03f3d565126288633...master)
+This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

CONTRIBUTING.md

@@ -22,9 +22,9 @@ Start reading the code and you'll get the hang of it. A complete description of
 coding guidelines is part of a [separate GitHub repository](https://github.com/uhafner/codingstyle), which 
 is only available in German. 
 
-For [IntelliJ IDEA](https://www.jetbrains.com/idea/) or [Eclipse](https://www.eclipse.org/) users: 
+For [IntelliJ IDEA](https://www.jetbrains.com/idea/) users: 
 the coding style is stored in configuration files within this project. If you import this project into 
-IntelliJ or Eclipse this style will used automatically. 
+IntelliJ this style will used automatically. 
 
 Moreover (since this project is about static code analysis :wink:) a configuration for the following static code
 analysis tools is defined in the POM and the `etc` and `.idea` folders:

Jenkinsfile

@@ -1,10 +1,10 @@
-node ('linux') {
-    timeout(60) {
-        stage ('Checkout') {
+node ('maven') {
+    timeout(200) {
+        stage ('Linux Checkout') {
             checkout scm
         }
 
-        stage ('Build') {
+        stage ('Linux Build') {
             String jdk = '8'
             String jdkTool = "jdk${jdk}"
             List<String> env = [
@@ -32,28 +32,30 @@ node ('linux') {
                 sh command
             }
 
+            archiveArtifacts artifacts: '**/target/*.jar', fingerprint: true
+
             junit testResults: '**/target/*-reports/TEST-*.xml'
 
-            recordIssues tool: mavenConsole(), referenceJobName: 'Plugins/git-forensics/master'
-            recordIssues tools: [java(), javaDoc()], sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
-            recordIssues tool: checkStyle(pattern: 'target/checkstyle-result.xml'), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
-            recordIssues tool: errorProne(), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
-            recordIssues tool: cpd(pattern: 'target/cpd.xml'), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
-            recordIssues tool: pmdParser(pattern: 'target/pmd.xml'), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
-            recordIssues tool: spotBugs(pattern: 'target/spotbugsXml.xml'), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
-            recordIssues tool: taskScanner(includePattern:'**/*.java', excludePattern:'target/**/*', highTags:'FIXME', normalTags:'TODO'), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
+            recordIssues enabledForFailure: true, tool: mavenConsole(), referenceJobName: 'Plugins/git-forensics/master'
+            recordIssues enabledForFailure: true, tools: [java(), javaDoc()], sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
+            recordIssues enabledForFailure: true, tool: checkStyle(pattern: 'target/checkstyle-result.xml'), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
+            recordIssues enabledForFailure: true, tool: errorProne(), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
+            recordIssues enabledForFailure: true, tool: cpd(pattern: 'target/cpd.xml'), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
+            recordIssues enabledForFailure: true, tool: pmdParser(pattern: 'target/pmd.xml'), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
+            recordIssues enabledForFailure: true, tool: spotBugs(pattern: 'target/spotbugsXml.xml'), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
+            recordIssues enabledForFailure: true, tool: taskScanner(includePattern:'**/*.java', excludePattern:'target/**/*', highTags:'FIXME', normalTags:'TODO'), sourceCodeEncoding: 'UTF-8', referenceJobName: 'Plugins/git-forensics/master'
             jacoco()
         }
     }
 }
 
 node ('windows') {
-    timeout(60) {
-        stage ('Checkout') {
+    timeout(200) {
+        stage ('Windows Checkout') {
             checkout scm
         }
 
-        stage ('Build') {
+        stage ('Windows Build') {
             String jdk = '8'
             String jdkTool = "jdk${jdk}"
             List<String> env = [

pom.xml

@@ -12,7 +12,7 @@
   <groupId>io.jenkins.plugins</groupId>
   <packaging>hpi</packaging>
   <name>Git Forensics Plugin</name>
-  <version>0.1-alpha-6-SNAPSHOT</version>
+  <version>0.2.0-SNAPSHOT</version>
   <description>Jenkins plug-in that mines and analyzes data from a Git repository.</description>
 
   <properties>
@@ -21,7 +21,7 @@
     <java.level>8</java.level>
     <jenkins-test-harness.version>2.49</jenkins-test-harness.version>
     <spotbugs.failOnError>false</spotbugs.failOnError>
-    <slf4j-nop.version>1.7.26</slf4j-nop.version>
+    <slf4j.version>1.7.26</slf4j.version>
 
     <!-- Library Dependencies Versions -->
     <error-prone.version>2.3.3</error-prone.version>
@@ -30,7 +30,7 @@
     <eclipse-collections.version>9.2.0</eclipse-collections.version>
 
     <!-- Jenkins Plugin Dependencies Versions -->
-    <forensics-api-plugin.version>0.2-alpha-1-SNAPSHOT</forensics-api-plugin.version>
+    <forensics-api-plugin.version>0.2.1</forensics-api-plugin.version>
     <git-plugin.version>3.9.1</git-plugin.version>
 
     <!-- Test Library Dependencies Versions -->
@@ -102,6 +102,11 @@
         <artifactId>scm-api</artifactId>
         <version>2.2.6</version>
       </dependency>
+      <dependency>
+        <groupId>org.slf4j</groupId>
+        <artifactId>slf4j-api</artifactId>
+        <version>${slf4j.version}</version>
+      </dependency>
     </dependencies>
   </dependencyManagement>
 
@@ -111,7 +116,7 @@
     <dependency>
       <groupId>org.slf4j</groupId>
       <artifactId>slf4j-nop</artifactId>
-      <version>${slf4j-nop.version}</version>
+      <version>${slf4j.version}</version>
     </dependency>
     <dependency>
       <groupId>com.github.spotbugs</groupId>

src/main/java/io/jenkins/plugins/git/forensics/blame/GitBlamer.java

@@ -88,7 +88,10 @@ public Blames blame(final FileLocations locations) {
             String workspacePath = getWorkspacePath();
             blames.logInfo("Job workspace = '%s'", workspacePath);
 
-            return git.withRepository(new BlameCallback(workspacePath, locations, blames, headCommit));
+            long nano = System.nanoTime();
+            Blames filledBlames = git.withRepository(new BlameCallback(workspacePath, locations, blames, headCommit));
+            filledBlames.logInfo("Blaming of authors took %d seconds", 1 + (System.nanoTime() - nano) / 1_000_000_000L);
+            return filledBlames;
         }
         catch (IOException exception) {
             blames.logException(exception, BLAME_ERROR);
@@ -131,23 +134,28 @@ static class BlameCallback implements RepositoryCallback<Blames> {
         }
 
         @Override
-        public Blames invoke(final Repository repo, final VirtualChannel channel) throws InterruptedException {
-            BlameRunner blameRunner = new BlameRunner(repo, headCommit);
+        public Blames invoke(final Repository repository, final VirtualChannel channel) throws InterruptedException {
+            try {
+                BlameRunner blameRunner = new BlameRunner(repository, headCommit);
 
-            for (String file : locations.getRelativePaths()) {
-                run(file, blameRunner);
+                for (String file : locations.getRelativePaths()) {
+                    run(file, blameRunner);
 
-                if (Thread.interrupted()) { // Cancel request by user
-                    String message = "Blaming has been interrupted while computing blame information";
-                    blames.logInfo(message);
+                    if (Thread.interrupted()) { // Cancel request by user
+                        String message = "Blaming has been interrupted while computing blame information";
+                        blames.logInfo(message);
 
-                    throw new InterruptedException(message);
+                        throw new InterruptedException(message);
+                    }
                 }
-            }
 
-            blames.logInfo("-> blamed authors of issues in %d files", blames.size());
+                blames.logInfo("-> blamed authors of issues in %d files", blames.size());
 
-            return blames;
+                return blames;
+            }
+            finally {
+                repository.close();
+            }
         }
 
         /**

src/main/java/io/jenkins/plugins/git/forensics/miner/GitRepositoryMiner.java

@@ -1,23 +1,29 @@
 package io.jenkins.plugins.git.forensics.miner;
 
 import java.io.IOException;
+import java.nio.file.LinkOption;
+import java.nio.file.Paths;
+import java.util.Collection;
 import java.util.List;
 import java.util.Set;
 import java.util.stream.Collectors;
 
 import org.apache.commons.lang3.StringUtils;
 import org.eclipse.jgit.api.Git;
 import org.eclipse.jgit.api.errors.GitAPIException;
+import org.eclipse.jgit.dircache.InvalidPathException;
 import org.eclipse.jgit.lib.Constants;
 import org.eclipse.jgit.lib.ObjectId;
 import org.eclipse.jgit.lib.PersonIdent;
 import org.eclipse.jgit.lib.Repository;
 import org.eclipse.jgit.revwalk.RevCommit;
 
 import edu.umd.cs.findbugs.annotations.Nullable;
+import edu.umd.cs.findbugs.annotations.SuppressFBWarnings;
 
 import org.jenkinsci.plugins.gitclient.GitClient;
 import org.jenkinsci.plugins.gitclient.RepositoryCallback;
+import hudson.FilePath;
 import hudson.remoting.VirtualChannel;
 
 import io.jenkins.plugins.forensics.miner.FileStatistics;
@@ -31,19 +37,31 @@
  * @see io.jenkins.plugins.forensics.miner.FileStatistics
  * @see io.jenkins.plugins.git.forensics.miner.FilesCollector
  */
+@SuppressFBWarnings(value = "SE", justification = "GitClient implementation is Serializable")
 public class GitRepositoryMiner extends RepositoryMiner {
     private static final long serialVersionUID = 1157958118716013983L;
 
     private final GitClient gitClient;
+    private final FilePath workspace;
 
     GitRepositoryMiner(final GitClient gitClient) {
+        super();
+
         this.gitClient = gitClient;
+        workspace = gitClient.getWorkTree();
     }
 
     @Override
-    public RepositoryStatistics mine() throws InterruptedException {
+    public RepositoryStatistics mine(final Collection<String> relativeFileNames) throws InterruptedException {
         try {
-            return gitClient.withRepository(new RepositoryStatisticsCallback());
+            String workspacePath = getWorkspacePath();
+
+            long nano = System.nanoTime();
+            RepositoryStatistics statistics = gitClient.withRepository(
+                    new RepositoryStatisticsCallback(workspacePath, relativeFileNames));
+            statistics.logInfo("Mining of the Git repository took %d seconds",
+                    1 + (System.nanoTime() - nano) / 1_000_000_000L);
+            return statistics;
         }
         catch (IOException exception) {
             RepositoryStatistics statistics = new RepositoryStatistics();
@@ -52,24 +70,46 @@ public RepositoryStatistics mine() throws InterruptedException {
         }
     }
 
+    private String getWorkspacePath() {
+        try {
+            return Paths.get(workspace.getRemote()).toAbsolutePath().normalize().toRealPath(LinkOption.NOFOLLOW_LINKS).toString();
+        }
+        catch (IOException | InvalidPathException exception) {
+            return workspace.getRemote();
+        }
+    }
+
     private static class RepositoryStatisticsCallback implements RepositoryCallback<RepositoryStatistics> {
         private static final long serialVersionUID = 7667073858514128136L;
+        private final String workspacePath;
+        private final Collection<String> paths;
+
+        RepositoryStatisticsCallback(final String workspacePath, final Collection<String> paths) {
+            this.workspacePath = workspacePath;
+            this.paths = paths;
+        }
 
         @Override
         public RepositoryStatistics invoke(final Repository repository, final VirtualChannel channel) {
             try {
-                ObjectId head = repository.resolve(Constants.HEAD);
-                Set<String> files = new FilesCollector(repository).findAllFor(head);
-                return analyze(repository, files);
+                if (paths.isEmpty()) { // scan whole repository
+                    ObjectId head = repository.resolve(Constants.HEAD);
+                    Set<String> files = new FilesCollector(repository).findAllFor(head);
+                    return analyze(repository, files);
+                }
+                return analyze(repository, paths);
             }
             catch (IOException exception) {
                 RepositoryStatistics statistics = new RepositoryStatistics();
                 statistics.logException(exception, "Can't obtain HEAD of repository.");
                 return statistics;
             }
+            finally {
+                repository.close();
+            }
         }
 
-        RepositoryStatistics analyze(final Repository repository, final Set<String> files) {
+        RepositoryStatistics analyze(final Repository repository, final Collection<String> files) {
             RepositoryStatistics statistics = new RepositoryStatistics();
             statistics.logInfo("Invoking Git miner to create creates statistics for all available files");
 
@@ -78,12 +118,14 @@ RepositoryStatistics analyze(final Repository repository, final Set<String> file
                     .collect(Collectors.toList());
             statistics.addAll(fileStatistics);
 
+            statistics.logInfo("-> created statistics for %d files", statistics.size());
+
             return statistics;
         }
 
         private FileStatistics analyzeHistory(final Repository repository, final String fileName,
                 final RepositoryStatistics statistics) {
-            FileStatistics fileStatistics = new FileStatistics(fileName);
+            FileStatistics fileStatistics = new FileStatistics(workspacePath + "/" + fileName);
 
             try {
                 Git git = new Git(repository);