Plagiarism check: Fix display of escaped characters

build.gradle

@@ -61,7 +61,7 @@ spotless {
     java {
         target project.fileTree(project.rootDir) {
             include "**/*.java"
-            exclude "**/src/main/java/de/tum/in/www1/artemis/service/connectors/BambooService.java", "**/src/test/resources/test-data/repository-export/EncodingISO_8559_1.java", "**/node_modules/**", "**/out/**", "**/repos/**", "**/build/**", "**/src/main/generated/**", "**/src/main/resources/templates/**"
+            exclude "**/src/main/java/de/tum/in/www1/artemis/service/connectors/BambooService.java", "**/src/test/resources/test-data/repository-export/EncodingISO_8559_1.java", "**/node_modules/**", "**/out/**", "**/repos/**", "**/repos-download/**", "**/build/**", "**/src/main/generated/**", "**/src/main/resources/templates/**"
         }
         importOrderFile "artemis-spotless.importorder"
         eclipse("4.19.0").configFile "artemis-spotless-style.xml"

src/main/java/de/tum/in/www1/artemis/domain/plagiarism/text/TextPlagiarismResult.java

@@ -2,8 +2,6 @@
 
 import javax.persistence.Entity;
 
-import org.apache.commons.lang3.ArrayUtils;
-
 import de.jplag.JPlagResult;
 import de.tum.in.www1.artemis.domain.Exercise;
 import de.tum.in.www1.artemis.domain.plagiarism.PlagiarismComparison;
@@ -31,11 +29,7 @@ public void convertJPlagResult(JPlagResult result, Exercise exercise) {
             this.comparisons.add(comparison);
         }
         this.duration = result.getDuration();
-        // NOTE: there seems to be an issue in JPlag 4.0 that the similarity distribution is reversed, either in the implementation or in the documentation.
-        // we use it like this: 0: [0% - 10%), 1: [10% - 20%), 2: [20% - 30%), ..., 9: [90% - 100%] so we reverse it
-        var similarityDistribution = result.getSimilarityDistribution();
-        ArrayUtils.reverse(similarityDistribution);
-        this.setSimilarityDistribution(similarityDistribution);
+        this.setSimilarityDistribution(result.getSimilarityDistribution());
         this.setExercise(exercise);
     }
 }

src/main/java/de/tum/in/www1/artemis/service/plagiarism/ProgrammingPlagiarismDetectionService.java

@@ -345,10 +345,11 @@ private List<Repository> downloadRepositories(ProgrammingExercise programmingExe
         // Used for sending progress notifications
         var topic = plagiarismWebsocketService.getProgrammingExercisePlagiarismCheckTopic(programmingExercise.getId());
 
+        int maxRepositories = participations.size() + 1;
         List<Repository> downloadedRepositories = new ArrayList<>();
         participations.parallelStream().forEach(participation -> {
             try {
-                var progressMessage = "Downloading repositories: " + (downloadedRepositories.size() + 1) + "/" + participations.size();
+                var progressMessage = "Downloading repositories: " + (downloadedRepositories.size() + 1) + "/" + maxRepositories;
                 plagiarismWebsocketService.notifyInstructorAboutPlagiarismState(topic, PlagiarismCheckState.RUNNING, List.of(progressMessage));
 
                 Repository repo = gitService.getOrCheckoutRepositoryForJPlag(participation, targetPath);
@@ -363,6 +364,9 @@ private List<Repository> downloadRepositories(ProgrammingExercise programmingExe
 
         // clone the template repo
         try {
+            var progressMessage = "Downloading repositories: " + maxRepositories + "/" + maxRepositories;
+            plagiarismWebsocketService.notifyInstructorAboutPlagiarismState(topic, PlagiarismCheckState.RUNNING, List.of(progressMessage));
+
             Repository templateRepo = gitService.getOrCheckoutRepository(programmingExercise.getTemplateParticipation(), targetPath);
             gitService.resetToOriginHead(templateRepo); // start with clean state
             downloadedRepositories.add(templateRepo);

src/main/webapp/app/exercises/shared/plagiarism/plagiarism-split-view/text-submission-viewer/text-submission-viewer.component.ts

@@ -176,7 +176,7 @@ export class TextSubmissionViewerComponent implements OnChanges {
                 this.repositoryService.getFile(file, domain).subscribe({
                     next: ({ fileContent }) => {
                         this.loading = false;
-                        this.fileContent = this.insertMatchTokens(escape(fileContent));
+                        this.fileContent = this.insertMatchTokens(fileContent);
                     },
                     error: () => {
                         this.loading = false;
@@ -201,47 +201,67 @@ export class TextSubmissionViewerComponent implements OnChanges {
         return this.matches.has(file);
     }
 
-    insertToken(text: string, token: string, position: number) {
-        // prevent negative values because slice does not handle them as we would wish
-        if (position < 0) {
-            position = 0;
+    insertMatchTokens(fileContent: string): string {
+        const matches = this.getMatchesForCurrentFile()
+            .filter((match) => match.from && match.to)
+            .sort((m1, m2) => {
+                const lines = m1.from.line - m2.from.line;
+                if (lines === 0) {
+                    return m1.from.column - m2.from.column;
+                }
+                return lines;
+            });
+
+        if (!matches.length) {
+            return escape(fileContent);
         }
-        return [text.slice(0, position), token, text.slice(position)].join('');
-    }
 
-    insertMatchTokens(fileContent: string) {
         const rows = fileContent.split('\n');
-        const matches = this.getMatchesForCurrentFile();
-        const offsets = new Array(rows.length).fill(0);
+        let result = '';
 
-        matches.forEach((match) => {
-            if (!match.from) {
-                captureException(new Error('"from" is not defined in insertMatchTokens'));
-                return;
-            }
-            if (!match.to) {
-                captureException(new Error('"to" is not defined in insertMatchTokens'));
-                return;
-            }
+        for (let i = 0; i < matches[0].from.line - 1; i++) {
+            result += escape(rows[i]) + '\n';
+        }
+        result += escape(rows[matches[0].from.line - 1].slice(0, matches[0].from.column - 1));
+
+        for (let i = 0; i < matches.length; i++) {
+            const match = matches[i];
 
             const idxLineFrom = match.from.line - 1;
             const idxLineTo = match.to.line - 1;
 
-            const idxColumnFrom = match.from.column - 1 + offsets[idxLineFrom];
+            const idxColumnFrom = match.from.column - 1;
+            const idxColumnTo = match.to.column + match.to.length - 1;
 
-            if (rows[idxLineFrom]) {
-                rows[idxLineFrom] = this.insertToken(rows[idxLineFrom], this.tokenStart, idxColumnFrom);
-                offsets[idxLineFrom] += this.tokenStart.length;
-            }
+            result += this.tokenStart;
 
-            const idxColumnTo = match.to.column + match.to.length - 1 + offsets[idxLineTo];
+            if (idxLineFrom === idxLineTo) {
+                result += escape(rows[idxLineFrom].slice(idxColumnFrom, idxColumnTo)) + this.tokenEnd;
+            } else {
+                result += escape(rows[idxLineFrom].slice(idxColumnFrom));
+                for (let j = idxLineFrom + 1; j < idxLineTo; j++) {
+                    result += '\n' + escape(rows[j]);
+                }
+                result += '\n' + escape(rows[idxLineTo].slice(0, idxColumnTo)) + this.tokenEnd;
+            }
 
-            if (rows[idxLineTo]) {
-                rows[idxLineTo] = this.insertToken(rows[idxLineTo], this.tokenEnd, idxColumnTo);
-                offsets[idxLineTo] += this.tokenEnd.length;
+            // escape everything up until the next match (or the end of the string if there is no more match)
+            if (i === matches.length - 1) {
+                result += escape(rows[idxLineTo].slice(idxColumnTo));
+                for (let j = idxLineTo + 1; j < rows.length; j++) {
+                    result += '\n' + escape(rows[j]);
+                }
+            } else if (matches[i + 1].from.line === match.to.line) {
+                result += escape(rows[idxLineTo].slice(idxColumnTo, matches[i + 1].from.column - 1));
+            } else {
+                result += escape(rows[idxLineTo].slice(idxColumnTo)) + '\n';
+                for (let j = idxLineTo + 1; j < matches[i + 1].from.line - 1; j++) {
+                    result += escape(rows[j]) + '\n';
+                }
+                result += escape(rows[matches[i + 1].from.line - 1].slice(0, matches[i + 1].from.column - 1));
             }
-        });
+        }
 
-        return rows.join('\n');
+        return result;
     }
 }

src/test/javascript/spec/component/plagiarism/text-submission-viewer.component.spec.ts

@@ -149,33 +149,58 @@ describe('Text Submission Viewer Component', () => {
         expect(comp.currentFile).toEqual(fileName);
     });
 
-    it('inserts a token', () => {
-        const base = 'This is a test';
-        const token = '<token>';
-        const position = 4;
-        const expectedResult = 'This<token> is a test';
+    it('should insert match tokens', () => {
+        const mockMatches = [
+            {
+                from: {
+                    column: 1,
+                    line: 1,
+                    length: 5,
+                } as TextSubmissionElement,
+                to: {
+                    column: 13,
+                    line: 1,
+                    length: 5,
+                } as TextSubmissionElement,
+            },
+            {
+                from: {
+                    column: 1,
+                    line: 2,
+                    length: 10,
+                } as TextSubmissionElement,
+                to: {
+                    column: 23,
+                    line: 2,
+                    length: 5,
+                } as TextSubmissionElement,
+            },
+        ];
+        jest.spyOn(comp, 'getMatchesForCurrentFile').mockReturnValue(mockMatches);
+
+        const fileContent = `Lorem ipsum dolor sit amet.\nConsetetur sadipscing elitr.`;
+        const expectedFileContent = `<span class="plagiarism-match">Lorem ipsum dolor</span> sit amet.\n<span class="plagiarism-match">Consetetur sadipscing elitr</span>.`;
 
-        const result = comp.insertToken(base, token, position);
+        const updatedFileContent = comp.insertMatchTokens(fileContent);
 
-        expect(result).toEqual(expectedResult);
+        expect(updatedFileContent).toEqual(expectedFileContent);
     });
 
-    it('appends a token', () => {
-        const base = 'This is a test';
-        const token = '<token>';
-        const position = 20;
-        const expectedResult = 'This is a test<token>';
+    it('should escape the text if no matches are present', () => {
+        jest.spyOn(comp, 'getMatchesForCurrentFile').mockReturnValue([]);
+        const fileContent = 'Lorem ipsum dolor sit amet.\n<test>';
+        const expectedFileContent = 'Lorem ipsum dolor sit amet.\n&lt;test&gt;';
 
-        const result = comp.insertToken(base, token, position);
+        const updatedFileContent = comp.insertMatchTokens(fileContent);
 
-        expect(result).toEqual(expectedResult);
+        expect(updatedFileContent).toEqual(expectedFileContent);
     });
 
-    it('should insert match tokens', () => {
+    it('should escape and insert tokens', () => {
         const mockMatches = [
             {
                 from: {
-                    column: 1,
+                    column: 6,
                     line: 1,
                     length: 5,
                 } as TextSubmissionElement,
@@ -199,9 +224,47 @@ describe('Text Submission Viewer Component', () => {
             },
         ];
         jest.spyOn(comp, 'getMatchesForCurrentFile').mockReturnValue(mockMatches);
+        const fileContent = 'Lorem ipsum <fake-token>dolor sit amet.\n<test> test text for inserting tokens';
+        const expectedFileContent =
+            'Lorem<span class="plagiarism-match"> ipsum &lt;fake</span>-token&gt;dolor sit amet.\n' +
+            '<span class="plagiarism-match">&lt;test&gt; test text for insert</span>ing tokens';
 
-        const fileContent = `Lorem ipsum dolor sit amet.\nConsetetur sadipscing elitr.`;
-        const expectedFileContent = `<span class="plagiarism-match">Lorem ipsum dolor</span> sit amet.\n<span class="plagiarism-match">Consetetur sadipscing elitr</span>.`;
+        const updatedFileContent = comp.insertMatchTokens(fileContent);
+
+        expect(updatedFileContent).toEqual(expectedFileContent);
+    });
+
+    it('should insert tokens for multiple matches in one line', () => {
+        const mockMatches = [
+            {
+                from: {
+                    column: 20,
+                    line: 1,
+                    length: 10,
+                } as TextSubmissionElement,
+                to: {
+                    column: 30,
+                    line: 1,
+                    length: 5,
+                } as TextSubmissionElement,
+            },
+            {
+                from: {
+                    column: 1,
+                    line: 1,
+                    length: 5,
+                } as TextSubmissionElement,
+                to: {
+                    column: 5,
+                    line: 1,
+                    length: 5,
+                } as TextSubmissionElement,
+            },
+        ];
+        jest.spyOn(comp, 'getMatchesForCurrentFile').mockReturnValue(mockMatches);
+        const fileContent = 'Lorem ipsum <fake-token>dolor sit amet.';
+        // TODO double check that, this result seems wrong
+        const expectedFileContent = '<span class="plagiarism-match">Lorem ips</span>um &lt;fake-t<span class="plagiarism-match">oken&gt;dolor sit </span>amet.';
 
         const updatedFileContent = comp.insertMatchTokens(fileContent);