#4933 - Exporting project fails if a curation CAS is missing or document state is wrong

.github/workflows/maven.yml

@@ -17,20 +17,38 @@ on:
 jobs:
   build:
     strategy:
+      fail-fast: false
       matrix:
         os: [ubuntu-latest, windows-latest]
         jdk: [17]
 
     runs-on: ${{ matrix.os }}
 
     steps:
-    - uses: actions/checkout@v4
+    - name: Checkout repository
+      uses: actions/checkout@v4
+      with:
+        ref: ${{ github.head_ref || github.ref }}
+
     - name: Set up JDK ${{ matrix.jdk }}
       uses: actions/setup-java@v4
       with:
         java-version: ${{ matrix.jdk }}
         distribution: 'temurin'
         cache: maven
+
+    - name: Set up cache date
+      run: echo "CACHE_DATE=$(date +'%Y-%m-%d')" >> $GITHUB_ENV
+
+    - name: Cache Maven repository
+      id: maven-cache
+      uses: actions/cache@v3
+      with:
+        path: ~/.m2/repository
+        key: ${{ runner.os }}-maven-${{ hashFiles('**/pom.xml') }}-${{ env.CACHE_DATE }}
+        restore-keys: |
+          ${{ runner.os }}-maven-
+
     - name: Build with Maven
       run: mvn --no-transfer-progress -B clean verify --file pom.xml
 

inception/inception-curation/src/main/java/de/tudarmstadt/ukp/inception/curation/export/CuratedDocumentsExporter.java

@@ -122,35 +122,50 @@ public void exportData(FullProjectExportRequest aRequest, ProjectExportTaskMonit
             try (var session = CasStorageSession.openNested()) {
                 // If depending on aInProgress, include only the the curation documents that are
                 // finished or also the ones that are in progress
-                if (documentService.existsCas(sourceDocument, CURATION_USER)
-                        && (aRequest.isIncludeInProgress()
-                                && CURATION_IN_PROGRESS.equals(sourceDocument.getState()))
-                        || CURATION_FINISHED.equals(sourceDocument.getState())) {
-                    // Copy CAS - this is used when importing the project again
-                    exportSerializedCas(sourceDocument, aStage);
-
-                    // Determine which format to use for export
-                    if (aRequest.getFormat() != null) {
-                        var formatId = FORMAT_AUTO.equals(aRequest.getFormat())
-                                ? sourceDocument.getFormat()
-                                : aRequest.getFormat();
-
-                        var format = importExportService.getWritableFormatById(formatId)
-                                .orElseGet(() -> {
-                                    var fallbackFormat = importExportService.getFallbackFormat();
-                                    aMonitor.addMessage(LogMessage.warn(this,
-                                            "Curation: %s No writer found for original format [%s] "
-                                                    + "- exporting as [%s] instead.",
-                                            sourceDocument, formatId, fallbackFormat.getName()));
-                                    return fallbackFormat;
-                                });
-
-                        // Copy secondary export format for convenience - not used during import
-                        exportAdditionalFormat(bulkOperationContext, sourceDocument, aStage,
-                                format);
-                    }
+                var shouldExport = (aRequest.isIncludeInProgress()
+                        && CURATION_IN_PROGRESS == sourceDocument.getState())
+                        || CURATION_FINISHED == sourceDocument.getState();
+                if (!shouldExport) {
+                    aMonitor.setProgress(
+                            initProgress + (int) ceil(((double) i) / documents.size() * 10.0));
+                    i++;
+                    continue;
+                }
+
+                if (!documentService.existsCas(sourceDocument, CURATION_USER)) {
+                    aMonitor.addMessage(LogMessage.warn(this,
+                            "Curation CAS for document %s could not be found!", sourceDocument));
+                    LOG.warn("Curation CAS for document {} could not be found!", sourceDocument);
+                    aMonitor.setProgress(
+                            initProgress + (int) ceil(((double) i) / documents.size() * 10.0));
+                    i++;
+                    continue;
+                }
+
+                // Copy CAS - this is used when importing the project again
+                exportSerializedCas(sourceDocument, aStage);
+
+                // Determine which format to use for export
+                if (aRequest.getFormat() != null) {
+                    var formatId = FORMAT_AUTO.equals(aRequest.getFormat())
+                            ? sourceDocument.getFormat()
+                            : aRequest.getFormat();
+
+                    var format = importExportService.getWritableFormatById(formatId)
+                            .orElseGet(() -> {
+                                var fallbackFormat = importExportService.getFallbackFormat();
+                                aMonitor.addMessage(LogMessage.warn(this,
+                                        "Curation: %s No writer found for original format [%s] "
+                                                + "- exporting as [%s] instead.",
+                                        sourceDocument, formatId, fallbackFormat.getName()));
+                                return fallbackFormat;
+                            });
+
+                    // Copy secondary export format for convenience - not used during import
+                    exportAdditionalFormat(bulkOperationContext, sourceDocument, aStage, format);
                 }
             }
+
             aMonitor.setProgress(initProgress + (int) ceil(((double) i) / documents.size() * 10.0));
             i++;
         }