Merge branch 'integration' into issue887-javax.json_to_jakarta.json

jhove-apps/pom.xml

@@ -60,11 +60,6 @@
       <artifactId>jhove-core</artifactId>
       <version>${project.version}</version>
     </dependency>
-
-    <dependency>
-      <groupId>junit</groupId>
-      <artifactId>junit</artifactId>
-    </dependency>
   </dependencies>
 
   <profiles>

jhove-apps/src/main/java/edu/harvard/hul/ois/jhove/viewer/RepTreeRoot.java

@@ -889,7 +889,7 @@ private DefaultMutableTreeNode nisoToNode(NisoImageMetadata niso) {
 				"NisoImageMetadata", true);
 		String s = niso.getMimeType();
 		if (s != null) {
-			val.add(new DefaultMutableTreeNode("MIMEType: " + s, false));
+			val.add(new DefaultMutableTreeNode("FormatName: " + s, false));
 		}
 		s = niso.getByteOrder();
 		if (s != null) {
@@ -1274,6 +1274,10 @@ private DefaultMutableTreeNode nisoToNode(NisoImageMetadata niso) {
 			for (int i = 0; i < iarray.length; i++) {
 				nod.add(new DefaultMutableTreeNode(Integer.toString(iarray[i]),
 						false));
+				//BitsPerSampleUnit Integer is assumed, because of BitsPerSample
+				// According to the specification, it can also be float.
+				// This is currently not supported by jHove
+				nod.add(new DefaultMutableTreeNode("Integer"));
 			}
 		}
 		if ((n = niso.getSamplesPerPixel()) != NisoImageMetadata.NULL) {

jhove-bbt/scripts/bbt-jhove.sh

@@ -127,7 +127,7 @@ showHelp() {
 checkParams "$@"
 candidate="${paramOutputLoc:?}/${MAJOR_MINOR_VER}"
 tempInstallLoc="/tmp/to-test"
-sed -i 's/^java.*/java -javaagent:${HOME}\/\.m2\/repository\/org\/jacoco\/org\.jacoco\.agent\/0.8.10\/org\.jacoco.agent-0\.8\.10-runtime\.jar=destfile=jhove-apps\/target\/jacoco\.exec -Xss2048k  -classpath "$CP" edu.harvard.hul.ois.jhove.Jhove -c "${CONFIG}" "${@}"/g' "${tempInstallLoc}/jhove"
+sed -i 's/^java.*/java -javaagent:${HOME}\/\.m2\/repository\/org\/jacoco\/org\.jacoco\.agent\/0.8.11\/org\.jacoco.agent-0\.8\.11-runtime\.jar=destfile=jhove-apps\/target\/jacoco\.exec -Xss2048k  -classpath "$CP" edu.harvard.hul.ois.jhove.Jhove -c "${CONFIG}" "${@}"/g' "${tempInstallLoc}/jhove"
 bash "$SCRIPT_DIR/baseline-jhove.sh" -j "${tempInstallLoc}" -c "${paramCorpusLoc}" -o "${candidate}"
 
 if [[ -f "${SCRIPT_DIR}/create-${MAJOR_MINOR_VER}-target.sh" ]]

jhove-bbt/scripts/create-1.29-target.sh

@@ -55,3 +55,6 @@ echo "TEST BASELINE: Creating baseline"
 # Simply copy baseline for now we're not making any changes
 echo " - copying ${baselineRoot} baseline to ${targetRoot}"
 cp -R "${baselineRoot}" "${targetRoot}"
+
+# Update release details for ePub module
+find "${targetRoot}" -type f -name "audit.jhove.xml" -exec sed -i 's/^   <module release="1.2">EPUB-ptc<\/module>$/   <module release="1.3">EPUB-ptc<\/module>/' {} \;

jhove-core/pom.xml

@@ -37,13 +37,17 @@
       <scope>runtime</scope>
     </dependency>
     <dependency>
-      <groupId>junit</groupId>
-      <artifactId>junit</artifactId>
+      <groupId>org.junit.jupiter</groupId>
+      <artifactId>junit-jupiter-engine</artifactId>
+    </dependency>
+    <dependency>
+        <groupId>org.junit.vintage</groupId>
+        <artifactId>junit-vintage-engine</artifactId>
     </dependency>
     <dependency>
       <groupId>nl.jqno.equalsverifier</groupId>
       <artifactId>equalsverifier</artifactId>
-      <version>3.14</version>
+      <version>3.15.8</version>
       <scope>test</scope>
     </dependency>
   </dependencies>

jhove-ext-modules/pom.xml

@@ -13,7 +13,7 @@
 
   <properties>
     <jwat.version>1.0.3</jwat.version>
-    <epubcheck.version>4.2.6</epubcheck.version>
+    <epubcheck.version>5.1.0</epubcheck.version>
   </properties>
 
   <build>
@@ -58,8 +58,8 @@
       <version>${project.version}</version>
     </dependency>
     <dependency>
-      <groupId>junit</groupId>
-      <artifactId>junit</artifactId>
+      <groupId>org.junit.vintage</groupId>
+      <artifactId>junit-vintage-engine</artifactId>
     </dependency>
     <!-- JWAT for WARC, ARC and GZIP -->
     <dependency>

jhove-ext-modules/src/main/java/org/ithaka/portico/jhove/module/EpubModule.java

@@ -82,9 +82,9 @@ public class EpubModule extends ModuleBase {
     private static final String FORMATNAME = "EPUB";
 
     private static final String NAME = "EPUB-ptc";
-    private static final String RELEASE = "1.2";
-    private static final int[] DATE = { 2023, 03, 16 };
-    private static final String RIGHTS_YEAR = "2019";
+    private static final String RELEASE = "1.3";
+    private static final int[] DATE = { 2023, 06, 12 };
+    private static final String RIGHTS_YEAR = "2023";
     private static final String[] FORMAT = { FORMATNAME };
     private static final String COVERAGE = FORMATNAME;
     private static final String[] MIMETYPE = { EPUB_MEDIATYPE };
@@ -94,18 +94,18 @@ public class EpubModule extends ModuleBase {
     private static final String NOTE = "This module uses EPUBCheck for testing of EPUB files.";
 
     // EPUB agent information
-    private static final String EPUB_AGENTNAME = "International Digital Publishing Forum";
+    private static final String EPUB_AGENTNAME = "International Digital Publishing Forum and World Wide Web Consortium";
     private static final AgentType EPUB_AGENTTYPE = AgentType.STANDARD;
-    private static final String EPUB_AGENTADDRESS = "International Digital Publishing Forum (IDPF), "
-            + "113 Cherry Street, Suite 70-719, Seattle, WA 98104";
-    private static final String EPUB_AGENTWEBSITE = "http://idpf.org";
-    private static final String EPUB_AGENTEMAIL = "membership@idpf.org";
-    private static final String EPUB_AGENTPHONE = "+1-206-451-7250";
+    private static final String EPUB_AGENTADDRESS = "W3C Inc, "
+            + "401 Edgewater Place, Suite 600, Wakefield, MA 01880, USA";
+    private static final String EPUB_AGENTWEBSITE = "https://www.w3.org/";
+    private static final String EPUB_AGENTEMAIL = "membership@w3.org";
+    private static final String EPUB_AGENTPHONE = "+1-339-273-2711";
 
     // EPUB format doc information
     private static final String EPUB_FORMATDOCTITLE = FORMATNAME;
-    private static final String EPUB_FORMATDOCDATE = "2019-05-15";
-    private static final String EPUB_FORMATDOCURL = "http://www.idpf.org/epub/dir/";
+    private static final String EPUB_FORMATDOCDATE = "2023-05-25";
+    private static final String EPUB_FORMATDOCURL = "https://www.w3.org/TR/epub/";
 
     // Signatures
     private static final String EPUB_EXTENSION = ".epub";

jhove-ext-modules/src/main/java/org/ithaka/portico/jhove/module/epub/JhoveRepInfoReport.java

@@ -72,6 +72,8 @@ public class JhoveRepInfoReport extends MasterReport {
     protected static final String ISO_DATE_PATTERN = "yyyy-MM-dd'T'HH:mm:ss'Z'";
     protected static final String FALLBACK_FORMAT = "application/octet-stream";
 
+    protected static final String FRAGMENT_START = "#";
+
     public JhoveRepInfoReport(String ePubName) {
         this.setEpubFileName(PathUtil.removeWorkingDirectory(ePubName));
 
@@ -146,7 +148,8 @@ public void info(String resource, FeatureEnum feature, String value) {
             this.references.add(value);
             break;
         case RESOURCE:
-            this.resources.add(value);
+            String no_fragment = value.split(FRAGMENT_START)[0];
+            this.resources.add(no_fragment);
             break;
         case DC_LANGUAGE:
             this.language = value;

jhove-ext-modules/src/test/java/org/ithaka/portico/jhove/module/EpubModuleTest.java

@@ -74,7 +74,7 @@ public class EpubModuleTest {
     private static final String EPUB3_TITLE_ENCODING = "src/test/resources/epub/epub3-multiple-renditions.epub";
 
     private static final String EXPECTED_MEDIATYPE = "application/epub+zip";
-    private static final String EXPECTED_VERSION_3_2 = "3.2";
+    private static final String EXPECTED_VERSION_3_3 = "3.3";
     private static final String PNG_MIMETYPE = "image/png";
     private static final String XHTML_MIMETYPE = "application/xhtml+xml";
     private static final String NCX_MIMETYPE = "application/x-dtbncx+xml";
@@ -99,9 +99,11 @@ public void parseValidEpub3PropertiesTest() throws Exception {
         assertEquals(0, info.getMessage().size()); // no errors
         assertEquals("EPUB", info.getFormat());
         assertEquals(EXPECTED_MEDIATYPE, info.getMimeType());
-        assertEquals(EXPECTED_VERSION_3_2, info.getVersion());
+        assertEquals(EXPECTED_VERSION_3_3, info.getVersion());
         // these may change, so just check they aren't null
-        assertNotNull(info.getCreated());
+        // note: this property is missing in 5.1.0 of epubcheck but 
+        // due for fix in next maintence release, uncomment when fixed.
+        //assertNotNull(info.getCreated());
         assertNotNull(info.getLastModified());
 
         Property metadata = info.getProperty(EPUBMETADATA_KEY);
@@ -248,7 +250,9 @@ public void parseValidEpub2PropertiesTest() throws Exception {
         assertEquals(EXPECTED_MEDIATYPE, info.getMimeType());
         assertEquals("2.0.1", info.getVersion());
         // may change, so just check it isn't null
-        assertNotNull(info.getCreated());
+        // note: this property is missing in 5.1.0 of epubcheck but 
+        // due for fix in next maintence release, uncomment when fixed.
+        //assertNotNull(info.getCreated());
 
         Property metadata = info.getProperty(EPUBMETADATA_KEY);
         Map<String, Object> props = toMap(metadata);
@@ -397,7 +401,7 @@ public void parseImproperlyCompressedEpubTest() throws Exception {
         File epubFile = new File(ZIPPED_EPUB_FILEPATH);
         RepInfo info = parseAndCheckValidity(epubFile, RepInfo.FALSE, RepInfo.FALSE);
         assertEquals(EXPECTED_MEDIATYPE, info.getMimeType());
-        assertEquals(EXPECTED_VERSION_3_2, info.getVersion());
+        assertEquals(EXPECTED_VERSION_3_3, info.getVersion());
         assertEquals(1, info.getMessage().size());
         assertEquals("PKG-006", info.getMessage().get(0).getId());
     }
@@ -425,7 +429,7 @@ public void parseNonEpubTest() throws Exception {
         File epubFile = new File(WRONG_EXT_NOT_AN_EPUB_FILEPATH);
         RepInfo info = parseAndCheckValidity(epubFile, RepInfo.FALSE, RepInfo.FALSE);
         List<Message> msgs = info.getMessage();
-        final int expectedNumMessages = 3;
+        final int expectedNumMessages = 2;
         assertEquals(expectedNumMessages, msgs.size());
     }
 
@@ -451,7 +455,7 @@ public void parseNonEpubWithEpubExtensionTest() throws Exception {
         RepInfo info = parseAndCheckValidity(epubFile, RepInfo.FALSE, RepInfo.FALSE);
         assertEquals(OCTET_MIMETYPE, info.getMimeType());
         List<Message> msgs = info.getMessage();
-        final int expectedNumMessages = 3;
+        final int expectedNumMessages = 2;
         assertEquals(expectedNumMessages, msgs.size());
     }
 
@@ -508,7 +512,7 @@ public void parseEpubWithMissingFontsTest() throws Exception {
         Map<String, Object> fontinfo = new HashMap<String, Object>();
         font.forEach(f -> fontinfo.put(f.getName(), f.getValue()));
 
-        // only one font in this file, listed but missing.
+        // a single font file is listed - it is supposed to be embedded but is missing.
         assertEquals("Courier", fontinfo.get(PROPNAME_FONTNAME));
         assertEquals(true, fontinfo.get(PROPNAME_FONTFILE));
 
@@ -579,18 +583,12 @@ public void parseEpubMissingOpfTest() throws Exception {
         File epubFile = new File(EPUB2_MISSING_OPF_FILEPATH);
         RepInfo info = parseAndCheckValidity(epubFile, RepInfo.FALSE, RepInfo.FALSE);
 
-        assertEquals(OCTET_MIMETYPE, info.getMimeType());
-
         Set<String> msgCodes = new HashSet<String>();
-        assertEquals(2, info.getMessage().size());
-        Message msg1 = info.getMessage().get(0);
-        Message msg2 = info.getMessage().get(1);
-        assertTrue(msg1 instanceof ErrorMessage);
-        msgCodes.add(msg1.getId());
-        assertTrue(msg2 instanceof ErrorMessage);
-        msgCodes.add(msg2.getId());
+        assertEquals(1, info.getMessage().size());
+        Message msg = info.getMessage().get(0);
+        assertTrue(msg instanceof ErrorMessage);
+        msgCodes.add(msg.getId());
         assertTrue(msgCodes.contains("OPF-002"));
-        assertTrue(msgCodes.contains("RSC-001"));
     }
 
     /**
@@ -665,8 +663,8 @@ public void checkSignaturesEpub2WithEncryptionTest() throws Exception {
     public void parseEpub3TitleEncodingTest() throws Exception {
         File epubFile = new File(EPUB3_TITLE_ENCODING);
         String expectedTitle = "महाभारत";
-        // well formed and valid
-        RepInfo info = parseAndCheckValidity(epubFile, RepInfo.TRUE, RepInfo.TRUE);
+        // well formed but not valid (this is inconsequential to the test, we're just checking title)
+        RepInfo info = parseAndCheckValidity(epubFile, RepInfo.TRUE, RepInfo.FALSE);
 
         Property metadata = info.getProperty(PROPNAME_EPUB_METADATA);
         Map<String, Object> props = toMap(metadata);

jhove-ext-modules/src/test/java/org/ithaka/portico/jhove/module/epub/JhoveRepInfoReportTest.java

@@ -4,6 +4,7 @@
 import static org.junit.Assert.assertEquals;
 import static org.junit.Assert.assertTrue;
 
+import java.io.File;
 import java.text.SimpleDateFormat;
 import java.util.Arrays;
 import java.util.Date;
@@ -45,9 +46,10 @@ public class JhoveRepInfoReportTest {
     private static final MessageId WARN_MSG_ID = MessageId.CHK_001;
     private static final String WARN_MSG = "Consider yourself warned";
     private static final String WARN_MSG_SUGGEST = "Don't do it again!";
-
-    private EPUBLocation messageLoc = EPUBLocation.create("epub.opf");
-    private EPUBLocation messageLoc2 = EPUBLocation.create("content.xhtml");
+
+    private EPUBLocation messageLoc = EPUBLocation.of(new File("epub.opf"));
+    private EPUBLocation messageLoc2 = EPUBLocation.of(new File("content.xhtml"));
+
     private String messageArg = "fakearg";
 
 

jhove-installer/pom.xml

@@ -14,7 +14,7 @@
 
   <properties>
     <installer.output.filename>jhove-xplt-installer-${project.version}.jar</installer.output.filename>
-    <izpack.version>5.1.3</izpack.version>
+    <izpack.version>5.2.0</izpack.version>
     <izpack.staging>${project.build.directory}/staging</izpack.staging>
     <izpack.target>${project.build.directory}</izpack.target>
     <izpack.scripts>${project.build.scriptSourceDirectory}</izpack.scripts>

jhove-modules/ascii-hul/src/main/resources/edu/harvard/hul/ois/jhove/module/ascii/ErrorMessages_de.properties

@@ -1,4 +1,4 @@
 ASCII-HUL-1 = Ungültiges Zeichen
 ASCII-HUL-1-SUB = "Zeichen = %c (0x%2X)";
 ASCII-HUL-2 = Leere Datei
-ASCII-HUL-3 = Nicht druckbare Zeichen
+ASCII-HUL-3 = Nicht druckbare Zeichen

jhove-modules/jpeg-hul/src/main/resources/edu/harvard/hul/ois/jhove/module/jpeg/ErrorMessages_de.properties

@@ -0,0 +1,17 @@
+JPEG-HUL-1 = DDT Segment ohne vorhergehendes DTI
+JPEG-HUL-2 = Unerwartetes Dateiende
+JPEG-HUL-3 = I/O Ausnahme bei der Bearbeitung von Exif Metadaten:
+JPEG-HUL-4 = Ungültiger JPEG Header
+JPEG-HUL-5 = JFIF APP0 Marker nicht am Anfang der Datei
+JPEG-HUL-6 = Marker nicht valide in diesem Kontext 
+JPEG-HUL-7 = Erwartetes Marker-Byte 255
+JPEG-HUL-7-SUB = Lese Marker-Byte Wert %d
+JPEG-HUL-8 = SPIFF Marker nicht am Anfang der Datei
+JPEG-HUL-9 = Datei beginnt nicht mit SPIFF, Exif oder JFIF Segment
+JPEG-HUL-10 = Nichterkannte Kacheldaten 
+JPEG-HUL-11 = Nicht zulässiges ICCProfil in APP2 Segment; Meldung
+JPEG-HUL-12 = Adobe Marker Segment, unzulässiger transformFlag Wert %d
+JPEG-HUL-13 = Unbekannter Farbraum mit Komponentenanzahl: %d
+JPEG-HUL-14 = TIFF-HUL module benötigt, um Exif-Daten auszuwerten
+
+JHOVE-SYS-1 = Fehler beim Erstellen einer temporären Datei. Kontrolliere die Konfiguration:

jhove-modules/jpeg-hul/src/main/resources/edu/harvard/hul/ois/jhove/module/jpeg/ErrorMessages_en.properties

@@ -10,8 +10,8 @@ JPEG-HUL-8 = SPIFF marker not at beginning of file
 JPEG-HUL-9 = File does not begin with SPIFF, Exif or JFIF segment
 JPEG-HUL-10 = Unrecognized tiling data
 JPEG-HUL-11 = Invalid ICCProfile in APP2 segment; message 
-JPEG-HUL-12=Adobe marker segment, bad transformFlag value %d
-JPEG-HUL-13=Unknown colorspace with number of components of %d
+JPEG-HUL-12 = Adobe marker segment, bad transformFlag value %d
+JPEG-HUL-13 = Unknown colorspace with number of components of %d
 JPEG-HUL-14 = TIFF-HUL module required to report Exif data
 
-JHOVE-1 = Error creating temporary file. Check your configuration: 
+JHOVE-SYS-1 = Error creating temporary file. Check your configuration:

jhove-modules/pdf-hul/src/main/java/edu/harvard/hul/ois/jhove/module/PdfModule.java

@@ -1531,7 +1531,10 @@ protected boolean readXRefTables(RepInfo info) throws IOException {
 						// (Most likely we've hit the keyword "trailer".
 						break;
 					}
-					_objCount = ((Numeric) _parser.getNext()).getIntegerValue();
+					token = _parser.getNext();
+					if (token instanceof Numeric) {
+						_objCount = ((Numeric) token).getIntegerValue();
+					}
 					if (_xref == null) {
 						_xref = new long[_objCount];
 					}
@@ -2367,13 +2370,20 @@ protected void findImages(RepInfo info) throws IOException {
 											.get(DICT_KEY_WIDTH);
 									PdfSimpleObject widObj = (PdfSimpleObject) resolveIndirectObject(
 											widthBase);
-									niso.setImageWidth(widObj.getIntValue());
 									PdfObject heightBase = xobdict
 											.get(DICT_KEY_HEIGHT);
 									PdfSimpleObject htObj = (PdfSimpleObject) resolveIndirectObject(
 											heightBase);
-									niso.setImageLength(htObj.getIntValue());
-
+									if(widObj != null || htObj != null ) {		
+											niso.setImageWidth(widObj.getIntValue());
+											niso.setImageLength(htObj.getIntValue());
+									} else {
+										info.setWellFormed(false);
+										JhoveMessage message = JhoveMessages.getMessageInstance(
+												MessageConstants.PDF_HUL_159.getId(), 
+												MessageConstants.PDF_HUL_159.getMessage());
+										info.setMessage(new ErrorMessage(message)); // PDF-HUL-159
+									}
 									// Check for filters to add to the filter
 									// list
 									Filter[] filters = ((PdfStream) xob)

jhove-modules/pdf-hul/src/main/java/edu/harvard/hul/ois/jhove/module/pdf/MessageConstants.java

@@ -197,6 +197,7 @@ public enum MessageConstants {
 	public static final JhoveMessage PDF_HUL_156 = messageFactory.getMessage("PDF-HUL-156");
     public static final JhoveMessage PDF_HUL_157 = messageFactory.getMessage("PDF-HUL-157");
     public static final JhoveMessage PDF_HUL_158 = messageFactory.getMessage("PDF-HUL-158");
+	public static final JhoveMessage PDF_HUL_159 = messageFactory.getMessage("PDF-HUL-159");
 
 	/**
 	 * Logger Messages

jhove-modules/pdf-hul/src/main/resources/edu/harvard/hul/ois/jhove/module/pdf/ErrorMessages.properties

@@ -160,3 +160,4 @@ PDF-HUL-155 = Error parsing mandatory version number from PDF header.
 PDF-HUL-156 = Extension can't be defined as an indirect reference
 PDF-HUL-157 = Unexpected exception {0}
 PDF-HUL-158 = Unexpected exception {0}
+PDF-HUL-159 = Image height and width are manditory properties

jhove-modules/pom.xml

@@ -21,8 +21,8 @@
       <version>1.29.0-SNAPSHOT</version>
     </dependency>
     <dependency>
-      <groupId>junit</groupId>
-      <artifactId>junit</artifactId>
+      <groupId>org.junit.vintage</groupId>
+      <artifactId>junit-vintage-engine</artifactId>
     </dependency>
     <dependency>
       <groupId>javax.xml.bind</groupId>