REL 1.26 - Merge release to master branch

.github/workflows/test-pr.yml

@@ -7,16 +7,19 @@ on:
 jobs:
   build:
     name: Checkout and Build
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-latest
+
+    continue-on-error: true
 
     strategy:
+      fail-fast: false
       matrix:
-        java-version: [8, 11, 16, 17]
+        java-version: [8, 11, 16, 17, 21]
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: JDK setup
-        uses: actions/setup-java@v2
+        uses: actions/setup-java@v4
         with:
           java-version: ${{ matrix.java-version }}
           distribution: 'temurin'
@@ -44,11 +47,11 @@ jobs:
 
   coverage:
     name: Quality Assurance
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-latest
     needs: [ build ]
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Download metadata coverage report
         uses: actions/download-artifact@master
         with:

.github/workflows/update-jakarta-workflow.yml

@@ -9,18 +9,21 @@ jobs:
   checkout-and-build:
     runs-on: ubuntu-latest
 
+    continue-on-error: true
+
     strategy:
+      fail-fast: false
       matrix:
-        java-version: [11, 16, 17]
+        java-version: [11, 16, 17, 21]
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
           ref: integration
       - name: JDK setup
-        uses: actions/setup-java@v3
+        uses: actions/setup-java@v4
         with:
           java-version: ${{ matrix.java-version }}
           distribution: 'temurin'
@@ -44,7 +47,7 @@ jobs:
     needs: checkout-and-build
     steps:
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
           ref: integration

README.md

@@ -2,7 +2,7 @@ veraPDF-pdfbox-validation
 =========================
 *PDF Box based PDF/A and PDF/UA validation, feature extraction and metadata repair developed for veraPDF*
 
-[![Build Status](https://jenkins.openpreservation.org/job/veraPDF/job/1.24/job/pdfbox-validation/badge/icon)](https://jenkins.openpreservation.org/job/veraPDF/job/1.24/job/pdfbox-validation/ "OPF Jenkins")
+[![Build Status](https://jenkins.openpreservation.org/job/veraPDF/job/1.26/job/pdfbox-validation/badge/icon)](https://jenkins.openpreservation.org/job/veraPDF/job/1.26/job/pdfbox-validation/ "OPF Jenkins")
 [![Maven Central](https://img.shields.io/maven-central/v/org.verapdf/pdfbox-validation-model.svg)](https://repo1.maven.org/maven2/org/verapdf/pdfbox-validation-model/ "Maven central")
 [![CodeCov Coverage](https://img.shields.io/codecov/c/github/veraPDF/veraPDF-pdfbox-validation.svg)](https://codecov.io/gh/veraPDF/veraPDF-pdfbox-validation/ "CodeCov coverage")
 [![Codacy Badge](https://app.codacy.com/project/badge/Grade/216fae32f94541e694228d96527aee5c)](https://app.codacy.com/gh/veraPDF/veraPDF-pdfbox-validation/dashboard?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_grade "Codacy coverage")
@@ -29,7 +29,7 @@ Quick Start
 
 In order to build the parser you'll need:
 
- * Java 9 - 17, which can be downloaded [from Oracle](https://www.oracle.com/technetwork/java/javase/downloads/index.html), or for Linux users [OpenJDK](https://openjdk.java.net/install/index.html).
+ * Java 9 - 21, which can be downloaded [from Oracle](https://www.oracle.com/technetwork/java/javase/downloads/index.html), or for Linux users [OpenJDK](https://openjdk.java.net/install/index.html).
  * [Maven v3+](https://maven.apache.org/)
 
 ### Building the veraPDF PDF Box Validation Model

pdfbox-feature-reporting/pom.xml

@@ -26,7 +26,7 @@
   <parent>
     <artifactId>verapdf-pdfbox-validation</artifactId>
     <groupId>org.verapdf</groupId>
-    <version>1.24.0</version>
+    <version>1.26.0</version>
   </parent>
   <modelVersion>4.0.0</modelVersion>
 

pdfbox-metadata-fixer/pom.xml

@@ -28,7 +28,7 @@
   <parent>
     <artifactId>verapdf-pdfbox-validation</artifactId>
     <groupId>org.verapdf</groupId>
-    <version>1.24.0</version>
+    <version>1.26.0</version>
   </parent>
 
   <artifactId>pdfbox-metadata-fixer</artifactId>

pdfbox-metadata-fixer/src/main/java/org/verapdf/metadata/fixer/impl/pb/model/InfoDictionaryImpl.java

@@ -66,6 +66,11 @@ public String getAuthor() {
 		return this.info.getAuthor();
 	}
 
+	@Override
+	public int getAuthorSize() {
+		return this.info.getAuthor() != null ? 1 : 0;
+	}
+
 	@Override
 	public void setAuthor(String author) {
 		this.info.setAuthor(author);

pdfbox-metadata-fixer/src/main/java/org/verapdf/metadata/fixer/impl/pb/model/MetadataImpl.java

@@ -113,15 +113,15 @@ public void removePDFIdentificationSchema(
         try {
             if (isValidIdentification()) {
                 int part = flavour.getPart().getPartNumber();
-                Integer schemaPart = this.metadata.getIdentificationPart();
+                Integer schemaPart = this.metadata.getPDFAIdentificationPart();
 
                 if (schemaPart != null &&
                         schemaPart.intValue() != part) {
                     return;
                 }
             }
 
-            boolean isDeleted = this.metadata.deleteIdentificationSchema();
+            boolean isDeleted = this.metadata.deletePDFAIdentificationSchema();
             if (isDeleted) {
                 this.setNeedToBeUpdated(true);
                 resultBuilder.addFix("Identification schema removed");
@@ -141,8 +141,8 @@ public void addPDFIdentificationSchema(
 
         try {
             if (isValidIdentification()) {
-                Integer schemaPart = this.metadata.getIdentificationPart();
-                String schemaConformance = this.metadata.getIdentificationConformance();
+                Integer schemaPart = this.metadata.getPDFAIdentificationPart();
+                String schemaConformance = this.metadata.getPDFAIdentificationConformance();
 
                 if (schemaPart != null &&
                         schemaConformance != null &&
@@ -152,8 +152,8 @@ public void addPDFIdentificationSchema(
                 }
             }
 
-            this.metadata.setIdentificationPart(Integer.valueOf(part));
-            this.metadata.setIdentificationConformance(conformance);
+            this.metadata.setPDFAIdentificationPart(Integer.valueOf(part));
+            this.metadata.setPDFAIdentificationConformance(conformance);
             this.setNeedToBeUpdated(true);
             resultBuilder.addFix("Identification schema added");
 
@@ -184,16 +184,15 @@ private static int confToInt(String conf) {
 
     private boolean isValidIdentification() {
         try {
-            Integer identificationPart = this.metadata.getIdentificationPart();
+            Integer identificationPart = this.metadata.getPDFAIdentificationPart();
             if (identificationPart == null) {
                 return false;
 			}
-                String identificationConformance = this.metadata.getIdentificationConformance();
+                String identificationConformance = this.metadata.getPDFAIdentificationConformance();
                 if (identificationPart.intValue() == 1) {
                     return "A".equals(identificationConformance) || "B".equals(identificationConformance);
                 } else if (identificationPart.intValue() == 2 || identificationPart.intValue() == 3) {
-                    return "A".equals(this.metadata.getIdentificationConformance()) ||
-                            "U".equals(identificationConformance) ||
+                    return "A".equals(identificationConformance) || "U".equals(identificationConformance) ||
                             "B".equals(identificationConformance);
                 } else {
                     return false;

pdfbox-metadata-fixer/src/main/java/org/verapdf/metadata/fixer/impl/pb/schemas/DublinCoreSchemaImpl.java

@@ -105,6 +105,18 @@ public String getAuthor() {
 		}
 	}
 
+	@Override
+	public int getAuthorSize() {
+		try {
+			List<String> creators = this.meta.getCreator();
+			if (creators != null) {
+				return creators.size();
+			}
+		} catch (XMPException ignored) {
+		}
+		return 0;
+	}
+
 	@Override
 	public void setAuthor(String creator) {
 		try {

pdfbox-metadata-fixer/src/test/java/org/verapdf/metadata/fixer/impl/pb/model/MetadataImplTest.java

@@ -76,8 +76,8 @@ public void addPDFIdentificationSchemaTest() throws IOException, XMPException {
                 MetadataFixerResultImpl.Builder builder = new MetadataFixerResultImpl.Builder();
                 impl.addPDFIdentificationSchema(builder, PDFAFlavour.PDFA_1_B);
 
-                assertEquals(filePart, xmp.getIdentificationPart());
-                assertEquals(fileConformance, xmp.getIdentificationConformance());
+                assertEquals(filePart, xmp.getPDFAIdentificationPart());
+                assertEquals(fileConformance, xmp.getPDFAIdentificationConformance());
             }
         }
     }

pdfbox-validation-model/pom.xml

@@ -28,7 +28,7 @@
   <parent>
     <artifactId>verapdf-pdfbox-validation</artifactId>
     <groupId>org.verapdf</groupId>
-    <version>1.24.0</version>
+    <version>1.26.0</version>
   </parent>
 
   <artifactId>pdfbox-validation-model</artifactId>

pdfbox-validation-model/src/main/java/org/verapdf/model/ModelParser.java

@@ -21,6 +21,7 @@
 package org.verapdf.model;
 
 import org.verapdf.xmp.XMPException;
+import org.verapdf.xmp.containers.StaticXmpCoreContainers;
 import org.verapdf.xmp.impl.VeraPDFMeta;
 import java.util.logging.Logger;
 import org.apache.pdfbox.pdmodel.PDDocument;
@@ -56,7 +57,7 @@
  */
 public final class ModelParser implements PDFAParser {
 	private static final ReleaseDetails pdfBoxReleaseDetails = ReleaseDetails.addDetailsFromResource(
-			ReleaseDetails.APPLICATION_PROPERTIES_ROOT + "pdfbox-parser." + ReleaseDetails.PROPERTIES_EXT);
+			ReleaseDetails.APPLICATION_PROPERTIES_ROOT + "pdfbox-validation." + ReleaseDetails.PROPERTIES_EXT);
 	private static final URI id = URI.create("http://pdfa.verapdf.org/parser#pdfbox");
 	private static final ComponentDetails details = Components.veraDetails(id, "PDFBox Parser",
 			pdfBoxReleaseDetails.getVersion(), "veraPDF PDFBox based model parser.");
@@ -131,11 +132,11 @@ private static PDFAFlavour obtainFlavour(PDDocument document, PDFAFlavour defaul
 		}
 		try (InputStream is = metadata.exportXMPMetadata()) {
 			VeraPDFMeta veraPDFMeta = VeraPDFMeta.parse(is);
-			Integer identificationPart = veraPDFMeta.getIdentificationPart();
-			String identificationConformance = veraPDFMeta.getIdentificationConformance();
+			Integer identificationPart = veraPDFMeta.getPDFAIdentificationPart();
+			String identificationConformance = veraPDFMeta.getPDFAIdentificationConformance();
 			String prefix = "";
 			if (identificationPart == null && identificationConformance == null) {
-				identificationPart = veraPDFMeta.getUAIdentificationPart();
+				identificationPart = veraPDFMeta.getPDFUAIdentificationPart();
 				if (identificationPart != null) {
 					prefix = PDFUA_PREFIX;
 				}
@@ -157,6 +158,7 @@ private static PDFAFlavour obtainFlavour(PDDocument document, PDFAFlavour defaul
 
 	private static void cleanUp() {
 		StaticContainers.clearAllContainers();
+		StaticXmpCoreContainers.clearAllContainers();
 	}
 
 	@Override

pdfbox-validation-model/src/main/java/org/verapdf/model/impl/pb/cos/PBCosActualText.java

@@ -20,7 +20,6 @@
  */
 package org.verapdf.model.impl.pb.cos;
 
-import org.verapdf.model.impl.pb.operator.textshow.PUAHelper;
 import org.verapdf.model.coslayer.CosActualText;
 import org.apache.pdfbox.cos.COSString;
 
@@ -34,9 +33,4 @@ public class PBCosActualText extends PBCosString implements CosActualText {
     public PBCosActualText(COSString cosString) {
         super(cosString, COS_ACTUAL_TEXT_TYPE);
     }
-
-    @Override
-    public Boolean getcontainsPUA() {
-        return PUAHelper.containPUA(((COSString)baseObject).getString());
-    }
 }

pdfbox-validation-model/src/main/java/org/verapdf/model/impl/pb/cos/PBCosDocument.java

@@ -76,7 +76,6 @@ public class PBCosDocument extends PBCosObject implements CosDocument {
 	private final boolean isOptionalContentPresent;
 	private final boolean isLinearised;
 	private final int postEOFDataSize;
-	private final Boolean doesInfoMatchXMP;
 	private final String firstPageID;
 	private final String lastID;
 	private final boolean needsRendering;
@@ -131,7 +130,6 @@ public PBCosDocument(COSDocument cosDocument, PDFAFlavour flavour) {
 			this.firstPageID = null;
 		}
 		this.isLinearised = cosDocument.getTrailer() != cosDocument.getLastTrailer() && cosDocument.isLinearized();
-		this.doesInfoMatchXMP = XMPChecker.doesInfoMatchXMP(cosDocument);
 		this.needsRendering = this.getNeedsRenderingValue();
 	}
 
@@ -255,14 +253,6 @@ public Boolean getisLinearized() {
 		return Boolean.valueOf(this.isLinearised);
 	}
 
-	/**
-	 * @return true if XMP content matches Info dictionary content
-	 */
-	@Override
-	public Boolean getdoesInfoMatchXMP() {
-		return this.doesInfoMatchXMP;
-	}
-
 	@Override
 	public Boolean getMarked() {
 		if (this.catalog != null) {

pdfbox-validation-model/src/main/java/org/verapdf/model/impl/pb/cos/PBCosFileSpecification.java

@@ -86,12 +86,22 @@ public Boolean getisAssociatedFile() {
 				&& StaticContainers.getFileSpecificationKeys().contains(this.baseObject.getKey()));
 	}
 
+	@Override
+	public Boolean getpresentInEmbeddedFiles() {
+		return null;
+	}
+
 	@Override
 	public Boolean getcontainsEF() {
 		return this.baseObject != null && this.baseObject instanceof COSDictionary &&
 				((COSDictionary) this.baseObject).containsKey(COSName.EF);
 	}
 
+	@Override
+	public Boolean getcontainsDesc() {
+		return null;
+	}
+
 	@Override
 	public List<? extends Object> getLinkedObjects(String link) {
 		if (EF.equals(link)) {

pdfbox-validation-model/src/main/java/org/verapdf/model/impl/pb/cos/PBCosString.java

@@ -22,6 +22,7 @@
 
 import org.apache.pdfbox.cos.COSString;
 import org.verapdf.model.coslayer.CosString;
+import org.verapdf.model.impl.pb.operator.textshow.PUAHelper;
 
 /**
  * Current class is representation of CosString interface of abstract model.
@@ -85,4 +86,9 @@ public Boolean getcontainsOnlyHex() {
     public Long gethexCount() {
         return this.hexCount;
     }
+
+    @Override
+    public Boolean getcontainsPUA() {
+        return PUAHelper.containPUA(((COSString)baseObject).getString());
+    }
 }

pdfbox-validation-model/src/main/java/org/verapdf/model/impl/pb/cos/PBCosTrailer.java

@@ -23,10 +23,8 @@
 import org.apache.pdfbox.cos.COSBase;
 import org.apache.pdfbox.cos.COSDictionary;
 import org.apache.pdfbox.cos.COSName;
-import org.apache.pdfbox.cos.COSObject;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.verapdf.model.baselayer.Object;
-import org.verapdf.model.coslayer.CosIndirect;
 import org.verapdf.model.coslayer.CosInfo;
 import org.verapdf.model.coslayer.CosTrailer;
 import org.verapdf.model.impl.pb.pd.PBoxPDEncryption;
@@ -73,8 +71,6 @@ public Boolean getisEncrypted() {
     @Override
     public List<? extends Object> getLinkedObjects(String link) {
         switch (link) {
-            case CATALOG:
-                return this.getCatalog();
             case ENCRYPT:
                 return this.getEncrypt();
             case INFO:
@@ -84,13 +80,6 @@ public List<? extends Object> getLinkedObjects(String link) {
         }
     }
 
-    private List<CosIndirect> getCatalog() {
-        List<CosIndirect> catalog = new ArrayList<>(MAX_NUMBER_OF_ELEMENTS);
-        COSBase base = ((COSDictionary) this.baseObject).getItem(COSName.ROOT);
-        catalog.add(new PBCosIndirect((COSObject) base, this.document, this.flavour));
-        return Collections.unmodifiableList(catalog);
-    }
-
     private List<PDEncryption> getEncrypt() {
         COSBase base = ((COSDictionary)this.baseObject).getDictionaryObject(COSName.ENCRYPT);
         if (base != null && base instanceof COSDictionary) {