[#944] Implement authorship analysis

build.gradle

@@ -196,7 +196,7 @@ def serveTestReportInBackground = tasks.register('serveTestReportInBackground',
     workingDir = 'build/serveTestReport'
     main = mainClassName
     classpath = sourceSets.main.runtimeClasspath
-    args = ['--config', './exampleconfig', '--since', 'd1', '--view']
+    args = ['--config', './exampleconfig', '--since', 'd1', '--view', '-A']
     String versionJvmArgs = '-Dversion=' + getRepoSenseVersion()
     jvmArgs = [ versionJvmArgs ]
     killDescendants = false // Kills descendants of started process using methods only found in Java 9 and beyond.

frontend/cypress/tests/codeView/codeView_creditBackgroundColour.cy.js

@@ -0,0 +1,42 @@
+describe('credit background colour', () => {
+  it('check if background colour match the credit information for Eugene', () => {
+    // open the code panel
+    cy.get('.icon-button.fa-code')
+      .should('exist')
+      .first()
+      .click();
+
+    // full credit - #C8E6C9
+    cy.get(':nth-child(1) > .file-content > .segment-collection > :nth-child(2) > .java > .code')
+      .should('have.css', 'background-color')
+      .and('eq', 'rgb(200, 230, 201)');
+
+    // partial credit - #E6FFED
+    cy.get(':nth-child(1) > .file-content > .segment-collection > :nth-child(4) > .java > .code')
+      .should('have.css', 'background-color')
+      .and('eq', 'rgb(230, 255, 237)');
+  });
+
+  it('check if background colour match the credit information when group is merged', () => {
+    // check merge group checkbox
+    cy.get('#summary label.merge-group > input')
+      .should('be.visible')
+      .check()
+      .should('be.checked');
+
+    // open the code panel
+    cy.get('.icon-button.fa-code')
+      .should('exist')
+      .click();
+
+    // full credit - #F0808050
+    cy.get(':nth-child(1) > .file-content > .segment-collection > :nth-child(7) > .scss > .code')
+      .should('have.css', 'background-color')
+      .and('eq', 'rgba(240, 128, 128, 0.314)');
+
+    // partial credit - #1E90FF20
+    cy.get(':nth-child(3) > .file-content > .segment-collection > :nth-child(10) > .java > .code')
+      .should('have.css', 'background-color')
+      .and('eq', 'rgba(30, 144, 255, 0.125)');
+  });
+});

frontend/src/components/c-segment.vue

@@ -1,6 +1,6 @@
 <template lang="pug">
 .segment(
-  v-bind:class="{ untouched: !segment.knownAuthor, active: isOpen }",
+  v-bind:class="{ untouched: !segment.knownAuthor, active: isOpen, isNotFullCredit: !segment.isFullCredit }",
   v-bind:style="{ 'border-left': `0.25rem solid ${authorColors[segment.knownAuthor]}` }",
   v-bind:title="`Author: ${segment.knownAuthor || \"Unknown\"}`"
 )
@@ -53,7 +53,7 @@ export default defineComponent({
     return {
       isOpen: (this.segment.knownAuthor !== null) || this.segment.lines.length < 5 as boolean,
       canOpen: (this.segment.knownAuthor === null) && this.segment.lines.length > 4 as boolean,
-      transparencyValue: '30' as string,
+      transparencyValue: (this.segment.isFullCredit ? '50' : '20') as string,
     };
   },
   computed: {
@@ -77,7 +77,7 @@ export default defineComponent({
   border-left: .25rem solid mui-color('green');
 
   .code {
-    background-color: mui-color('github', 'authored-code-background');
+    background-color: mui-color('github', 'full-authored-code-background');
     padding-left: 1rem;
   }
 
@@ -110,6 +110,12 @@ export default defineComponent({
     word-break: break-word;
   }
 
+  &.isNotFullCredit {
+    .code {
+      background-color: mui-color('github', 'partial-authored-code-background');
+    }
+  }
+
   &.untouched {
     $grey: mui-color('grey', '400');
     border-left: .25rem solid $grey;

frontend/src/styles/_colors.scss

@@ -303,7 +303,8 @@ $mui-colors: (
   'github': (
     'title-background': #FAFBFC,
     'border': #E1E4E8,
-    'authored-code-background': #E6FFED,
+    'full-authored-code-background': #C8E6C9,
+    'partial-authored-code-background': #E6FFED,
   ),
   'grey': (
     '50': #FAFAFA,

frontend/src/styles/hightlight-js-style.css

@@ -34,7 +34,7 @@
 
 .hljs-section,
 .hljs-name {
-    color: #63a35c;
+    color: #468C5A;
 }
 
 .hljs-tag {

frontend/src/types/types.ts

@@ -61,6 +61,7 @@ export interface Repo extends RepoRaw {
 
 export interface AuthorshipFileSegment {
   knownAuthor: string | null;
+  isFullCredit: boolean;
   lineNumbers: number[];
   lines: string[];
 }

frontend/src/types/zod/authorship-type.ts

@@ -4,6 +4,7 @@ const lineSchema = z.object({
   lineNumber: z.number(),
   author: z.object({ gitId: z.string() }),
   content: z.string(),
+  isFullCredit: z.boolean(),
 });
 
 const fileResult = z.object({

frontend/src/views/c-authorship.vue

@@ -411,6 +411,7 @@ export default defineComponent({
     splitSegments(lines: Array<Line>): { segments: Array<AuthorshipFileSegment>; blankLineCount: number; } {
       // split into segments separated by knownAuthor
       let lastState: string | null;
+      let lastCreditState: boolean;
       let lastId = -1;
       const segments: Array<AuthorshipFileSegment> = [];
       let blankLineCount = 0;
@@ -420,16 +421,19 @@ export default defineComponent({
           ? !this.isUnknownAuthor(line.author.gitId)
           : line.author.gitId === this.info.author;
         const knownAuthor = (line.author && isAuthorMatched) ? line.author.gitId : null;
+        const isFullCredit = line.isFullCredit;
 
-        if (knownAuthor !== lastState || lastId === -1) {
+        if (knownAuthor !== lastState || lastId === -1 || (knownAuthor && isFullCredit !== lastCreditState)) {
           segments.push({
             knownAuthor,
+            isFullCredit,
             lineNumbers: [],
             lines: [],
           });
 
           lastId += 1;
           lastState = knownAuthor;
+          lastCreditState = isFullCredit;
         }
 
         const content = line.content || ' ';

src/main/java/reposense/RepoSense.java

@@ -79,7 +79,8 @@ public static void main(String[] args) {
                     cliArguments.getSinceDate(), cliArguments.getUntilDate(),
                     cliArguments.isSinceDateProvided(), cliArguments.isUntilDateProvided(),
                     cliArguments.getNumCloningThreads(), cliArguments.getNumAnalysisThreads(),
-                    TimeUtil::getElapsedTime, cliArguments.getZoneId(), cliArguments.isFreshClonePerformed());
+                    TimeUtil::getElapsedTime, cliArguments.getZoneId(), cliArguments.isFreshClonePerformed(),
+                    cliArguments.isAuthorshipAnalyzed(), cliArguments.getOriginalityThreshold());
 
             FileUtil.zipFoldersAndFiles(reportFoldersAndFiles, cliArguments.getOutputFilePath().toAbsolutePath(),
                     ".json");

src/main/java/reposense/authorship/AuthorshipReporter.java

@@ -11,7 +11,6 @@
 import reposense.model.RepoConfiguration;
 import reposense.system.LogsManager;
 
-
 /**
  * Generates the authorship summary data for each repository.
  */
@@ -29,24 +28,27 @@ public class AuthorshipReporter {
     private final FileInfoAnalyzer fileInfoAnalyzer = new FileInfoAnalyzer();
     private final FileResultAggregator fileResultAggregator = new FileResultAggregator();
 
-
     /**
      * Generates and returns the authorship summary for each repo in {@code config}.
+     * Further analyzes the authorship of each line in the commit if {@code shouldAnalyzeAuthorship} is true, based on
+     * {code originalityThreshold}.
      */
-    public AuthorshipSummary generateAuthorshipSummary(RepoConfiguration config) {
+    public AuthorshipSummary generateAuthorshipSummary(RepoConfiguration config, boolean shouldAnalyzeAuthorship,
+            double originalityThreshold) {
         List<FileInfo> textFileInfos = fileInfoExtractor.extractTextFileInfos(config);
 
         int numFiles = textFileInfos.size();
         int totalNumLines = textFileInfos.stream()
-                .mapToInt(fileInfo -> fileInfo.getNumOfLines())
+                .mapToInt(FileInfo::getNumOfLines)
                 .sum();
 
         if (totalNumLines > HIGH_NUMBER_LINES_THRESHOLD) {
             logger.warning(String.format(HIGH_NUMBER_LINES_MESSAGE, numFiles, totalNumLines));
         }
 
         List<FileResult> fileResults = textFileInfos.stream()
-                .map(fileInfo -> fileInfoAnalyzer.analyzeTextFile(config, fileInfo))
+                .map(fileInfo -> fileInfoAnalyzer.analyzeTextFile(config, fileInfo, shouldAnalyzeAuthorship,
+                        originalityThreshold))
                 .filter(Objects::nonNull)
                 .collect(Collectors.toList());
 

src/main/java/reposense/authorship/FileInfoAnalyzer.java

@@ -12,6 +12,7 @@
 import java.util.logging.Logger;
 
 import reposense.authorship.analyzer.AnnotatorAnalyzer;
+import reposense.authorship.analyzer.AuthorshipAnalyzer;
 import reposense.authorship.model.FileInfo;
 import reposense.authorship.model.FileResult;
 import reposense.authorship.model.LineInfo;
@@ -44,10 +45,13 @@ public class FileInfoAnalyzer {
     /**
      * Analyzes the lines of the file, given in the {@code fileInfo}, that has changed in the time period provided
      * by {@code config}.
+     * Further analyzes the authorship of each line in the commit if {@code shouldAnalyzeAuthorship} is true, based on
+     * {@code originalityThreshold}.
      * Returns null if the file is missing from the local system, or none of the
      * {@link Author} specified in {@code config} contributed to the file in {@code fileInfo}.
      */
-    public FileResult analyzeTextFile(RepoConfiguration config, FileInfo fileInfo) {
+    public FileResult analyzeTextFile(RepoConfiguration config, FileInfo fileInfo, boolean shouldAnalyzeAuthorship,
+            double originalityThreshold) {
         String relativePath = fileInfo.getPath();
 
         if (Files.notExists(Paths.get(config.getRepoRoot(), relativePath))) {
@@ -59,10 +63,10 @@ public FileResult analyzeTextFile(RepoConfiguration config, FileInfo fileInfo) {
             return null;
         }
 
-        aggregateBlameAuthorModifiedAndDateInfo(config, fileInfo);
+        aggregateBlameAuthorModifiedAndDateInfo(config, fileInfo, shouldAnalyzeAuthorship, originalityThreshold);
         fileInfo.setFileType(config.getFileType(fileInfo.getPath()));
 
-        AnnotatorAnalyzer.aggregateAnnotationAuthorInfo(fileInfo, config.getAuthorConfig());
+        AnnotatorAnalyzer.aggregateAnnotationAuthorInfo(fileInfo, config.getAuthorConfig(), shouldAnalyzeAuthorship);
 
         if (!config.getAuthorList().isEmpty() && fileInfo.isAllAuthorsIgnored(config.getAuthorList())) {
             return null;
@@ -100,9 +104,8 @@ private FileResult generateTextFileResult(FileInfo fileInfo) {
             authorContributionMap.put(author, authorContributionMap.getOrDefault(author, 0) + 1);
         }
 
-        return FileResult.createTextFileResult(
-            fileInfo.getPath(), fileInfo.getFileType(), fileInfo.getLines(), authorContributionMap,
-            fileInfo.exceedsFileLimit());
+        return FileResult.createTextFileResult(fileInfo.getPath(), fileInfo.getFileType(), fileInfo.getLines(),
+                authorContributionMap, fileInfo.exceedsFileLimit());
     }
 
     /**
@@ -139,8 +142,11 @@ private FileResult generateBinaryFileResult(RepoConfiguration config, FileInfo f
      * The {@code config} is used to obtain the root directory for running git blame as well as other parameters used
      * in determining which author to assign to each line and whether to set the last modified date for a
      * {@code lineInfo}.
+     * Further analyzes the authorship of each line in the commit if {@code shouldAnalyzeAuthorship} is true, based on
+     * {@code originalityThreshold}.
      */
-    private void aggregateBlameAuthorModifiedAndDateInfo(RepoConfiguration config, FileInfo fileInfo) {
+    private void aggregateBlameAuthorModifiedAndDateInfo(RepoConfiguration config, FileInfo fileInfo,
+            boolean shouldAnalyzeAuthorship, double originalityThreshold) {
         String blameResults;
 
         if (!config.isFindingPreviousAuthorsPerformed()) {
@@ -159,14 +165,15 @@ private void aggregateBlameAuthorModifiedAndDateInfo(RepoConfiguration config, F
             String authorName = blameResultLines[lineCount + 1].substring(AUTHOR_NAME_OFFSET);
             String authorEmail = blameResultLines[lineCount + 2]
                     .substring(AUTHOR_EMAIL_OFFSET).replaceAll("<|>", "");
-            Long commitDateInMs = Long.parseLong(blameResultLines[lineCount + 3].substring(AUTHOR_TIME_OFFSET)) * 1000;
+            long commitDateInMs = Long.parseLong(blameResultLines[lineCount + 3].substring(AUTHOR_TIME_OFFSET)) * 1000;
             LocalDateTime commitDate = LocalDateTime.ofInstant(Instant.ofEpochMilli(commitDateInMs),
                     config.getZoneId());
             Author author = config.getAuthor(authorName, authorEmail);
 
-            if (!fileInfo.isFileLineTracked(lineCount / 5) || author.isIgnoringFile(filePath)
+            int lineNumber = lineCount / 5;
+            if (!fileInfo.isFileLineTracked(lineNumber) || author.isIgnoringFile(filePath)
                     || CommitHash.isInsideCommitList(commitHash, config.getIgnoreCommitList())
-                    || commitDate.compareTo(sinceDate) < 0 || commitDate.compareTo(untilDate) > 0) {
+                    || commitDate.isBefore(sinceDate) || commitDate.isAfter(untilDate)) {
                 author = Author.UNKNOWN_AUTHOR;
             }
 
@@ -176,9 +183,16 @@ private void aggregateBlameAuthorModifiedAndDateInfo(RepoConfiguration config, F
                             MESSAGE_SHALLOW_CLONING_LAST_MODIFIED_DATE_CONFLICT, config.getRepoName()));
                 }
 
-                fileInfo.setLineLastModifiedDate(lineCount / 5, commitDate);
+                fileInfo.setLineLastModifiedDate(lineNumber, commitDate);
+            }
+            fileInfo.setLineAuthor(lineNumber, author);
+
+            if (shouldAnalyzeAuthorship && !author.equals(Author.UNKNOWN_AUTHOR)) {
+                String lineContent = fileInfo.getLine(lineNumber + 1).getContent();
+                boolean isFullCredit = AuthorshipAnalyzer.analyzeAuthorship(config, fileInfo.getPath(), lineContent,
+                        commitHash, author, originalityThreshold);
+                fileInfo.setIsFullCredit(lineNumber, isFullCredit);
             }
-            fileInfo.setLineAuthor(lineCount / 5, author);
         }
     }
 

src/main/java/reposense/authorship/analyzer/AnnotatorAnalyzer.java

@@ -48,8 +48,10 @@ public class AnnotatorAnalyzer {
      *
      * @param fileInfo FileInfo to be further analyzed with author annotations.
      * @param authorConfig AuthorConfiguration for current analysis.
+     * @param shouldAnalyzeAuthorship whether credit info needs to be overwritten.
      */
-    public static void aggregateAnnotationAuthorInfo(FileInfo fileInfo, AuthorConfiguration authorConfig) {
+    public static void aggregateAnnotationAuthorInfo(FileInfo fileInfo, AuthorConfiguration authorConfig,
+            boolean shouldAnalyzeAuthorship) {
         Optional<Author> currentAnnotatedAuthor = Optional.empty();
         Path filePath = Paths.get(fileInfo.getPath());
         for (LineInfo lineInfo : fileInfo.getLines()) {
@@ -60,15 +62,15 @@ public static void aggregateAnnotationAuthorInfo(FileInfo fileInfo, AuthorConfig
                 boolean isUnknownAuthorSegment = !currentAnnotatedAuthor.isPresent() && !newAnnotatedAuthor.isPresent();
 
                 if (isEndOfAnnotatedSegment) {
-                    lineInfo.setAuthor(currentAnnotatedAuthor.get());
+                    lineInfo.updateAuthorAndCredit(currentAnnotatedAuthor.get(), shouldAnalyzeAuthorship);
                     currentAnnotatedAuthor = Optional.empty();
                 } else if (isUnknownAuthorSegment) {
                     currentAnnotatedAuthor = Optional.of(Author.UNKNOWN_AUTHOR);
                 } else {
                     currentAnnotatedAuthor = newAnnotatedAuthor.filter(author -> !author.isIgnoringFile(filePath));
                 }
             }
-            currentAnnotatedAuthor.ifPresent(lineInfo::setAuthor);
+            currentAnnotatedAuthor.ifPresent(author -> lineInfo.updateAuthorAndCredit(author, shouldAnalyzeAuthorship));
         }
     }