Development: Add SARIF parser (#9609)

src/main/java/de/tum/cit/aet/artemis/buildagent/service/BuildJobExecutionService.java

@@ -378,18 +378,18 @@ private BuildResult parseTestResults(TarArchiveInputStream testResultsTarInputSt
             }
 
             // Read the contents of the tar entry as a string.
-            String xmlString = readTarEntryContent(testResultsTarInputStream);
+            String fileString = readTarEntryContent(testResultsTarInputStream);
             // Get the file name of the tar entry.
             String fileName = getFileName(tarEntry);
 
             try {
                 // Check if the file is a static code analysis report file
                 if (StaticCodeAnalysisTool.getToolByFilePattern(fileName).isPresent()) {
-                    processStaticCodeAnalysisReportFile(fileName, xmlString, staticCodeAnalysisReports, buildJobId);
+                    processStaticCodeAnalysisReportFile(fileName, fileString, staticCodeAnalysisReports, buildJobId);
                 }
                 else {
                     // ugly workaround because in swift result files \n\t breaks the parsing
-                    var testResultFileString = xmlString.replace("\n\t", "");
+                    var testResultFileString = fileString.replace("\n\t", "");
                     if (!testResultFileString.isBlank()) {
                         processTestResultFile(testResultFileString, failedTests, successfulTests);
                     }
@@ -418,7 +418,7 @@ private boolean isValidTestResultFile(TarArchiveEntry tarArchiveEntry) {
         String result = (lastIndexOfSlash != -1 && lastIndexOfSlash + 1 < name.length()) ? name.substring(lastIndexOfSlash + 1) : name;
 
         // Java test result files are named "TEST-*.xml", Python test result files are named "*results.xml".
-        return !tarArchiveEntry.isDirectory() && result.endsWith(".xml") && !result.equals("pom.xml");
+        return !tarArchiveEntry.isDirectory() && (result.endsWith(".xml") && !result.equals("pom.xml") || result.endsWith(".sarif"));
     }
 
     /**
@@ -444,12 +444,12 @@ private String getFileName(TarArchiveEntry tarEntry) {
      * Processes a static code analysis report file and adds the report to the corresponding list.
      *
      * @param fileName                  the file name of the static code analysis report file
-     * @param xmlString                 the content of the static code analysis report file
+     * @param reportContent             the content of the static code analysis report file
      * @param staticCodeAnalysisReports the list of static code analysis reports
      */
-    private void processStaticCodeAnalysisReportFile(String fileName, String xmlString, List<StaticCodeAnalysisReportDTO> staticCodeAnalysisReports, String buildJobId) {
+    private void processStaticCodeAnalysisReportFile(String fileName, String reportContent, List<StaticCodeAnalysisReportDTO> staticCodeAnalysisReports, String buildJobId) {
         try {
-            staticCodeAnalysisReports.add(ReportParser.getReport(xmlString, fileName));
+            staticCodeAnalysisReports.add(ReportParser.getReport(reportContent, fileName));
         }
         catch (UnsupportedToolException e) {
             String msg = "Failed to parse static code analysis report for " + fileName;

src/main/java/de/tum/cit/aet/artemis/programming/domain/StaticCodeAnalysisTool.java

@@ -1,7 +1,8 @@
 package de.tum.cit.aet.artemis.programming.domain;
 
-import java.util.ArrayList;
+import java.util.EnumMap;
 import java.util.List;
+import java.util.Map;
 import java.util.Objects;
 import java.util.Optional;
 
@@ -10,28 +11,29 @@
  */
 public enum StaticCodeAnalysisTool {
 
-    SPOTBUGS(ProgrammingLanguage.JAVA, "spotbugs:spotbugs", "spotbugsXml.xml"), CHECKSTYLE(ProgrammingLanguage.JAVA, "checkstyle:checkstyle", "checkstyle-result.xml"),
-    PMD(ProgrammingLanguage.JAVA, "pmd:pmd", "pmd.xml"), PMD_CPD(ProgrammingLanguage.JAVA, "pmd:cpd", "cpd.xml"), SWIFTLINT(ProgrammingLanguage.SWIFT, "", "swiftlint-result.xml"),
-    GCC(ProgrammingLanguage.C, "", "gcc.xml");
+    // @formatter:off
+    SPOTBUGS("spotbugsXml.xml"),
+    CHECKSTYLE("checkstyle-result.xml"),
+    PMD("pmd.xml"),
+    PMD_CPD("cpd.xml"),
+    SWIFTLINT("swiftlint-result.xml"),
+    GCC("gcc.xml"),
+    OTHER(null),
+    ;
+    // @formatter:on
 
-    private final ProgrammingLanguage language;
+    // @formatter:off
+    private static final Map<ProgrammingLanguage, List<StaticCodeAnalysisTool>> TOOLS_OF_PROGRAMMING_LANGUAGE = new EnumMap<>(Map.of(
+        ProgrammingLanguage.JAVA, List.of(SPOTBUGS, CHECKSTYLE, PMD, PMD_CPD),
+        ProgrammingLanguage.SWIFT, List.of(SWIFTLINT),
+        ProgrammingLanguage.C, List.of(GCC)
+    ));
+    // @formatter:on
 
-    private final String command;
+    private final String fileName;
 
-    private final String filePattern;
-
-    StaticCodeAnalysisTool(ProgrammingLanguage language, String command, String filePattern) {
-        this.language = language;
-        this.command = command;
-        this.filePattern = filePattern;
-    }
-
-    public String getTask() {
-        return this.command;
-    }
-
-    public String getFilePattern() {
-        return this.filePattern;
+    StaticCodeAnalysisTool(String fileName) {
+        this.fileName = fileName;
     }
 
     /**
@@ -41,13 +43,7 @@ public String getFilePattern() {
      * @return List of static code analysis
      */
     public static List<StaticCodeAnalysisTool> getToolsForProgrammingLanguage(ProgrammingLanguage language) {
-        List<StaticCodeAnalysisTool> tools = new ArrayList<>();
-        for (var tool : StaticCodeAnalysisTool.values()) {
-            if (tool.language == language) {
-                tools.add(tool);
-            }
-        }
-        return tools;
+        return TOOLS_OF_PROGRAMMING_LANGUAGE.getOrDefault(language, List.of());
     }
 
     /**
@@ -58,7 +54,7 @@ public static List<StaticCodeAnalysisTool> getToolsForProgrammingLanguage(Progra
      */
     public static Optional<StaticCodeAnalysisTool> getToolByFilePattern(String fileName) {
         for (StaticCodeAnalysisTool tool : StaticCodeAnalysisTool.values()) {
-            if (Objects.equals(fileName, tool.filePattern)) {
+            if (Objects.equals(fileName, tool.fileName)) {
                 return Optional.of(tool);
             }
         }

src/main/java/de/tum/cit/aet/artemis/programming/service/localci/scaparser/ReportParser.java

@@ -1,94 +1,27 @@
 package de.tum.cit.aet.artemis.programming.service.localci.scaparser;
 
-import static de.tum.cit.aet.artemis.programming.service.localci.scaparser.utils.ReportUtils.createErrorReport;
-import static de.tum.cit.aet.artemis.programming.service.localci.scaparser.utils.ReportUtils.createFileTooLargeReport;
-
-import java.io.File;
-import java.io.IOException;
-import java.nio.file.Files;
-
-import com.fasterxml.jackson.databind.ObjectMapper;
-
 import de.tum.cit.aet.artemis.programming.dto.StaticCodeAnalysisReportDTO;
-import de.tum.cit.aet.artemis.programming.service.localci.scaparser.exception.ParserException;
 import de.tum.cit.aet.artemis.programming.service.localci.scaparser.exception.UnsupportedToolException;
 import de.tum.cit.aet.artemis.programming.service.localci.scaparser.strategy.ParserPolicy;
 import de.tum.cit.aet.artemis.programming.service.localci.scaparser.strategy.ParserStrategy;
-import de.tum.cit.aet.artemis.programming.service.localci.scaparser.utils.FileUtils;
 
 /**
  * Public API for parsing of static code analysis reports
  */
 public class ReportParser {
 
-    private final ObjectMapper mapper = new ObjectMapper();
-
-    // Reports that are bigger then the threshold will not be parsed
-    // and an issue will be generated. The unit is in megabytes.
-    private static final int STATIC_CODE_ANALYSIS_REPORT_FILESIZE_LIMIT_IN_MB = 1;
-
-    /**
-     * Transform a given static code analysis report into a JSON representation.
-     * All supported tools share the same JSON format.
-     *
-     * @param file Reference to the static code analysis report
-     * @return Static code analysis report represented as a JSON String
-     * @throws ParserException - If an exception occurs that is not already handled by the parser itself, e.g. caused by the json-parsing
-     */
-    public String transformToJSONReport(File file) throws ParserException {
-        try {
-            StaticCodeAnalysisReportDTO report = transformToReport(file);
-            return mapper.writeValueAsString(report);
-        }
-        catch (Exception e) {
-            throw new ParserException(e.getMessage(), e);
-        }
-    }
-
-    /**
-     * Transform a given static code analysis report given as a file into a plain Java object.
-     *
-     * @param file Reference to the static code analysis report
-     * @return Static code analysis report represented as a plain Java object
-     */
-    public StaticCodeAnalysisReportDTO transformToReport(File file) {
-        if (file == null) {
-            throw new IllegalArgumentException("File must not be null");
-        }
-
-        // The static code analysis parser only supports xml files.
-        if (!FileUtils.getExtension(file).equals("xml")) {
-            throw new IllegalArgumentException("File must be xml format");
-        }
-        try {
-            // Reject any file larger than the given threshold
-            if (FileUtils.isFilesizeGreaterThan(file, STATIC_CODE_ANALYSIS_REPORT_FILESIZE_LIMIT_IN_MB)) {
-                return createFileTooLargeReport(file.getName());
-            }
-
-            return getReport(file);
-        }
-        catch (Exception e) {
-            return createErrorReport(file.getName(), e);
-        }
-    }
+    private static final ParserPolicy parserPolicy = new ParserPolicy();
 
     /**
-     * Builds the document using the provided file and parses it to a Report object using ObjectMapper.
+     * Builds the document using the provided string and parses it to a Report object.
      *
-     * @param file File referencing the static code analysis report
+     * @param reportContent String containing the static code analysis report
+     * @param fileName      filename of the report used for configuring a parser
      * @return Report containing the static code analysis issues
      * @throws UnsupportedToolException if the static code analysis tool which created the report is not supported
-     * @throws IOException              if the file could not be read
      */
-    public static StaticCodeAnalysisReportDTO getReport(File file) throws IOException {
-        String xmlContent = Files.readString(file.toPath());
-        return getReport(xmlContent, file.getName());
-    }
-
-    public static StaticCodeAnalysisReportDTO getReport(String xmlContent, String fileName) {
-        ParserPolicy parserPolicy = new ParserPolicy();
+    public static StaticCodeAnalysisReportDTO getReport(String reportContent, String fileName) {
         ParserStrategy parserStrategy = parserPolicy.configure(fileName);
-        return parserStrategy.parse(xmlContent);
+        return parserStrategy.parse(reportContent);
     }
 }

src/main/java/de/tum/cit/aet/artemis/programming/service/localci/scaparser/format/sarif/ArtifactLocation.java

@@ -0,0 +1,22 @@
+package de.tum.cit.aet.artemis.programming.service.localci.scaparser.format.sarif;
+
+import java.util.Optional;
+
+import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
+
+/**
+ * Specifies the location of an artifact.
+ *
+ * @param uri A string containing a valid relative or absolute URI.
+ */
+@JsonIgnoreProperties(ignoreUnknown = true)
+public record ArtifactLocation(String uri) {
+
+    /**
+     * A string containing a valid relative or absolute URI.
+     */
+    public Optional<String> getOptionalUri() {
+        return Optional.ofNullable(uri);
+    }
+
+}

src/main/java/de/tum/cit/aet/artemis/programming/service/localci/scaparser/format/sarif/GlobalMessageStrings.java

@@ -0,0 +1,14 @@
+package de.tum.cit.aet.artemis.programming.service.localci.scaparser.format.sarif;
+
+import java.util.Map;
+
+import com.fasterxml.jackson.annotation.JsonAnySetter;
+
+/**
+ * A dictionary, each of whose keys is a resource identifier and each of whose values is a multiformatMessageString object, which holds message strings in plain text and
+ * (optionally) Markdown format. The strings can include placeholders, which can be used to construct a message in combination with an arbitrary number of additional string
+ * arguments.
+ */
+public record GlobalMessageStrings(@JsonAnySetter Map<String, MultiformatMessageString> additionalProperties) {
+
+}

src/main/java/de/tum/cit/aet/artemis/programming/service/localci/scaparser/format/sarif/Location.java

@@ -0,0 +1,23 @@
+package de.tum.cit.aet.artemis.programming.service.localci.scaparser.format.sarif;
+
+import java.util.Optional;
+
+import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
+
+/**
+ * A location within a programming artifact.
+ *
+ * @param physicalLocation A physical location relevant to a result. Specifies a reference to a programming artifact together with a range of bytes or characters within that
+ *                             artifact.
+ */
+@JsonIgnoreProperties(ignoreUnknown = true)
+public record Location(PhysicalLocation physicalLocation) {
+
+    /**
+     * A physical location relevant to a result. Specifies a reference to a programming artifact together with a range of bytes or characters within that artifact.
+     */
+    public Optional<PhysicalLocation> getOptionalPhysicalLocation() {
+        return Optional.ofNullable(physicalLocation);
+    }
+
+}

src/main/java/de/tum/cit/aet/artemis/programming/service/localci/scaparser/format/sarif/Message.java

@@ -0,0 +1,30 @@
+package de.tum.cit.aet.artemis.programming.service.localci.scaparser.format.sarif;
+
+import java.util.Optional;
+
+import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
+
+/**
+ * Encapsulates a message intended to be read by the end user.
+ *
+ * @param text A plain text message string.
+ * @param id   The identifier for this message.
+ */
+@JsonIgnoreProperties(ignoreUnknown = true)
+public record Message(String text, String id) {
+
+    /**
+     * A plain text message string.
+     */
+    public Optional<String> getOptionalText() {
+        return Optional.ofNullable(text);
+    }
+
+    /**
+     * The identifier for this message.
+     */
+    public Optional<String> getOptionalId() {
+        return Optional.ofNullable(id);
+    }
+
+}

src/main/java/de/tum/cit/aet/artemis/programming/service/localci/scaparser/format/sarif/MessageStrings.java

@@ -0,0 +1,13 @@
+package de.tum.cit.aet.artemis.programming.service.localci.scaparser.format.sarif;
+
+import java.util.Map;
+
+import com.fasterxml.jackson.annotation.JsonAnySetter;
+
+/**
+ * A set of name/value pairs with arbitrary names. Each value is a multiformatMessageString object, which holds message strings in plain text and (optionally) Markdown format. The
+ * strings can include placeholders, which can be used to construct a message in combination with an arbitrary number of additional string arguments.
+ */
+public record MessageStrings(@JsonAnySetter Map<String, MultiformatMessageString> additionalProperties) {
+
+}

src/main/java/de/tum/cit/aet/artemis/programming/service/localci/scaparser/format/sarif/MultiformatMessageString.java

@@ -0,0 +1,13 @@
+package de.tum.cit.aet.artemis.programming.service.localci.scaparser.format.sarif;
+
+import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
+
+/**
+ * A message string or message format string rendered in multiple formats.
+ *
+ * @param text A plain text message string or format string.
+ *                 (Required)
+ */
+@JsonIgnoreProperties(ignoreUnknown = true)
+public record MultiformatMessageString(String text) {
+}

src/main/java/de/tum/cit/aet/artemis/programming/service/localci/scaparser/format/sarif/PhysicalLocation.java

@@ -0,0 +1,30 @@
+package de.tum.cit.aet.artemis.programming.service.localci.scaparser.format.sarif;
+
+import java.util.Optional;
+
+import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
+
+/**
+ * A physical location relevant to a result. Specifies a reference to a programming artifact together with a range of bytes or characters within that artifact.
+ *
+ * @param artifactLocation Specifies the location of an artifact.
+ * @param region           A region within an artifact where a result was detected.
+ */
+@JsonIgnoreProperties(ignoreUnknown = true)
+public record PhysicalLocation(ArtifactLocation artifactLocation, Region region) {
+
+    /**
+     * Specifies the location of an artifact.
+     */
+    public Optional<ArtifactLocation> getOptionalArtifactLocation() {
+        return Optional.ofNullable(artifactLocation);
+    }
+
+    /**
+     * A region within an artifact where a result was detected.
+     */
+    public Optional<Region> getOptionalRegion() {
+        return Optional.ofNullable(region);
+    }
+
+}