Implemented validating input streams in addition to files.

validator/pom.xml

@@ -29,9 +29,9 @@
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <maven.deploy.skip>false
         </maven.deploy.skip><!-- do deploy to maven central, parent project does not and inherits -->
-        <maven.compiler.compilerVersion>8</maven.compiler.compilerVersion>
+        <maven.compiler.compilerVersion>21</maven.compiler.compilerVersion>
-        <maven.compiler.source>8</maven.compiler.source>
+        <maven.compiler.source>21</maven.compiler.source>
-        <maven.compiler.target>8</maven.compiler.target>
+        <maven.compiler.target>21</maven.compiler.target>
 
     </properties>
     <dependencies>
@@ -190,8 +190,8 @@
                     <!-- http://stackoverflow.com/questions/574594/how-can-i-create-an-executable-jar-with-dependencies-using-maven
                              mvn clean compile assembly:single -->
                     <!-- or whatever version you use -->
-                    <source>8</source>
+                    <source>9</source>
-                    <target>8</target>
+                    <target>9</target>
                 </configuration>
             </plugin>
             <!-- /ZUV -->

validator/src/main/java/org/mustangproject/validator/ByteArraySearcher.java

@@ -0,0 +1,28 @@
+package org.mustangproject.validator;
+
+public final class ByteArraySearcher {
+
+	private ByteArraySearcher() {
+	}
+
+	public static boolean contains(byte[] haystack, byte[] needle) {
+		if (needle.length > haystack.length) {
+			return false;
+		}
+
+		for (int i = 0; i <= haystack.length - needle.length; i++) {
+			boolean found = true;
+			for (int j = 0; j < needle.length; j++) {
+				if (haystack[i + j] != needle[j]) {
+					found = false;
+					break;
+				}
+			}
+			if (found) {
+				return true;
+			}
+		}
+
+		return false;
+	}
+}

validator/src/main/java/org/mustangproject/validator/PDFValidator.java

@@ -1,8 +1,10 @@
 package org.mustangproject.validator;
 
+import java.io.ByteArrayInputStream;
 import java.io.ByteArrayOutputStream;
 import java.io.File;
 import java.io.IOException;
+import java.io.InputStream;
 import java.io.PrintWriter;
 import java.io.StringReader;
 import java.io.StringWriter;
@@ -37,10 +39,12 @@ import org.verapdf.pdfa.validation.validators.ValidatorConfig;
 import org.verapdf.pdfa.validation.validators.ValidatorFactory;
 import org.verapdf.processor.BatchProcessor;
 import org.verapdf.processor.FormatOption;
+import org.verapdf.processor.ItemProcessor;
 import org.verapdf.processor.ProcessorConfig;
 import org.verapdf.processor.ProcessorFactory;
 import org.verapdf.processor.TaskType;
 import org.verapdf.processor.plugins.PluginsCollectionConfig;
+import org.verapdf.processor.reports.ItemDetails;
 import org.w3c.dom.Document;
 import org.w3c.dom.NodeList;
 import org.xml.sax.InputSource;
@@ -50,14 +54,14 @@ public class PDFValidator extends Validator {
 
 	public PDFValidator(ValidationContext ctx) {
 		super(ctx);
-		// TODO Auto-generated constructor stub
 	}
 
 	private static final Logger LOGGER = LoggerFactory.getLogger(PDFValidator.class.getCanonicalName()); // log output
-																											// is
 
 	private String pdfFilename;
 
+	private byte[] fileContents;
+
 	private String pdfReport;
 
 	private String Signature;
@@ -72,12 +76,8 @@ public class PDFValidator extends Validator {
 	public void validate() throws IrrecoverableValidationError {
 
 		zfXML = null;
-		final File file = new File(pdfFilename);
 		// file existence must have been checked before
-		final BigFileSearcher searcher = new BigFileSearcher();
+		if (!ByteArraySearcher.contains(fileContents, new byte[]{'%', 'P', 'D', 'F'})) {
-
-		final byte[] pdfSignature = { '%', 'P', 'D', 'F' };
-		if (searcher.indexOf(file, pdfSignature) != 0) {
 			context.addResultItem(
 				new ValidationResultItem(ESeverity.fatal, "Not a PDF file " + pdfFilename).setSection(20).setPart(EPart.pdf));
 
@@ -103,33 +103,29 @@ public class PDFValidator extends Validator {
 		// tasks.add(TaskType.FIX_METADATA);
 		// Creating processor config
 		final ProcessorConfig processorConfig = ProcessorFactory.fromValues(validatorConfig, featureConfig, pluginsConfig,
-				fixerConfig, tasks);
+			fixerConfig, tasks
+		);
 		// Creating processor and output stream.
 		final ByteArrayOutputStream reportStream = new ByteArrayOutputStream();
-		try (BatchProcessor processor = ProcessorFactory.fileBatchProcessor(processorConfig)) {
+		final InputStream inputStream = new ByteArrayInputStream(fileContents);
+		try (ItemProcessor processor = ProcessorFactory.createProcessor(processorConfig)) {
 			// Generating list of files for processing
-			final List<File> files = new ArrayList<>();
-			files.add(new File(pdfFilename));
 			// starting the processor
-                        processor.process(files, ProcessorFactory.getHandler(FormatOption.MRR, true, reportStream,
+			ItemDetails itemDetails = ItemDetails.fromValues(pdfFilename);
-                                                        processorConfig.getValidatorConfig().isRecordPasses()));                        
+			inputStream.mark(Integer.MAX_VALUE);
-			pdfReport = reportStream.toString("utf-8").replaceAll("<\\?xml version=\"1\\.0\" encoding=\"utf-8\"\\?>",
+			processor.process(itemDetails, inputStream);
-					"");
+			pdfReport = reportStream.toString("utf-8").replaceAll(
-		} catch (final VeraPDFException e) {
+				"<\\?xml version=\"1\\.0\" encoding=\"utf-8\"\\?>",
-			final ValidationResultItem vri = new ValidationResultItem(ESeverity.exception, e.getMessage()).setSection(6)
+				""
-					.setPart(EPart.pdf);
+			);
-			final StringWriter sw = new StringWriter();
+			inputStream.reset();
-			final PrintWriter pw = new PrintWriter(sw);
+		} catch (final Exception excep) {
-			e.printStackTrace(pw);
-			vri.setStacktrace(sw.toString());
-			context.addResultItem(vri);
-		} catch (final IOException excep) {
 			context.addResultItem(new ValidationResultItem(ESeverity.exception, excep.getMessage()).setSection(7)
 				.setPart(EPart.pdf).setStacktrace(excep.getStackTrace().toString()));
 		}
 
 		// step 2 validate XMP
-		final ZUGFeRDImporter zi = new ZUGFeRDImporter(pdfFilename);
+		final ZUGFeRDImporter zi = new ZUGFeRDImporter(inputStream);
 		final String xmp = zi.getXMP();
 
 		final DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
@@ -178,8 +174,10 @@ public class PDFValidator extends Validator {
 				}
 			}
 			if (!conformanceLevelValid) {
-				context.addResultItem(new ValidationResultItem(ESeverity.error,
+				context.addResultItem(new ValidationResultItem(
-						"XMP Metadata: ConformanceLevel contains invalid value").setSection(12).setPart(EPart.pdf));
+					ESeverity.error,
+					"XMP Metadata: ConformanceLevel contains invalid value"
+				).setSection(12).setPart(EPart.pdf));
 
 			}
 			xpr = xpath.compile("//*[local-name()=\"DocumentType\"]|//*[local-name()=\"Description\"]/@DocumentType");
@@ -192,7 +190,9 @@ public class PDFValidator extends Validator {
 
 			boolean documentTypeValid = false;
 			for (int i = 0; i < nodes.getLength(); i++) {
-				if (nodes.item(i).getTextContent().equals("INVOICE")||nodes.item(i).getTextContent().equals("ORDER")||nodes.item(i).getTextContent().equals("ORDER_RESPONSE")||nodes.item(i).getTextContent().equals("ORDER_CHANGE")) {
+				if (nodes.item(i).getTextContent().equals("INVOICE") || nodes.item(i).getTextContent().equals("ORDER")
+					|| nodes.item(i).getTextContent().equals("ORDER_RESPONSE") || nodes.item(i).getTextContent()
+					.equals("ORDER_CHANGE")) {
 					documentTypeValid = true;
 				}
 			}
@@ -222,8 +222,10 @@ public class PDFValidator extends Validator {
 			}
 			if (!documentFilenameValid) {
 
-				context.addResultItem(new ValidationResultItem(ESeverity.error,
+				context.addResultItem(new ValidationResultItem(
-						"XMP Metadata: DocumentFileName contains invalid value").setSection(19).setPart(EPart.pdf));
+					ESeverity.error,
+					"XMP Metadata: DocumentFileName contains invalid value"
+				).setSection(19).setPart(EPart.pdf));
 			}
 			xpr = xpath.compile("//*[local-name()=\"Version\"]|//*[local-name()=\"Description\"]/@Version");
 			nodes = (NodeList) xpr.evaluate(docXMP, XPathConstants.NODESET);
@@ -272,19 +274,19 @@ public class PDFValidator extends Validator {
 			final byte[] pdfMachineSignature = "pdfMachine from Broadgun Software".getBytes("UTF-8");
 			final byte[] ghostscriptSignature = "%%Invocation:".getBytes("UTF-8");
 
-			if (searcher.indexOf(file, symtraxSignature) != -1) {
+			if (ByteArraySearcher.contains(fileContents, symtraxSignature)) {
 				Signature = "Symtrax";
-			} else if (searcher.indexOf(file, mustangSignature) != -1) {
+			} else if (ByteArraySearcher.contains(fileContents, mustangSignature)) {
 				Signature = "Mustang";
-			} else if (searcher.indexOf(file, facturxpythonSignature) != -1) {
+			} else if (ByteArraySearcher.contains(fileContents, facturxpythonSignature)) {
 				Signature = "Factur/X Python";
-			} else if (searcher.indexOf(file, intarsysSignature) != -1) {
+			} else if (ByteArraySearcher.contains(fileContents, intarsysSignature)) {
 				Signature = "Intarsys";
-			} else if (searcher.indexOf(file, konikSignature) != -1) {
+			} else if (ByteArraySearcher.contains(fileContents, konikSignature)) {
 				Signature = "Konik";
-			} else if (searcher.indexOf(file, pdfMachineSignature) != -1) {
+			} else if (ByteArraySearcher.contains(fileContents, pdfMachineSignature)) {
 				Signature = "pdfMachine";
-			} else if (searcher.indexOf(file, ghostscriptSignature) != -1) {
+			} else if (ByteArraySearcher.contains(fileContents, ghostscriptSignature)) {
 				Signature = "Ghostscript";
 			}
 
@@ -327,6 +329,10 @@ public class PDFValidator extends Validator {
 
 	}
 
+	public void setFileContents(byte[] fileContents) {
+		this.fileContents = fileContents;
+	}
+
 	public String getRawXML() {
 		return zfXML;
 

validator/src/main/java/org/mustangproject/validator/ZUGFeRDValidator.java

@@ -91,6 +91,7 @@ public class ZUGFeRDValidator {
 			.append("<validation filename='" + context.getFilename() + "' datetime='" + isoDF.format(date) + "'>");
 
 		boolean isPDF = false;
+		byte[] content = null;
 		try {
 
 			if (filename == null) {
@@ -105,11 +106,12 @@ public class ZUGFeRDValidator {
 				context.addResultItem(
 					new ValidationResultItem(ESeverity.fatal, "File not found").setSection(1).setPart(EPart.pdf));
 			} else if (file.length() < 32) {
-				// with less then 32 bytes it can not even be a proper XML file
+				// with less than 32 bytes it can not even be a proper XML file
 				context.addResultItem(
 					new ValidationResultItem(ESeverity.fatal, "File too small").setSection(5).setPart(EPart.pdf));
 			} else {
 				BigFileSearcher searcher = new BigFileSearcher();
+				content = Files.readAllBytes(file.toPath());
 				XMLValidator xv = new XMLValidator(context);
 				if (disableNotices) {
 					xv.disableNotices();
@@ -118,6 +120,7 @@ public class ZUGFeRDValidator {
 				isPDF = searcher.indexOf(file, pdfSignature) == 0;
 				if (isPDF) {
 					pdfv.setFilename(filename);
+					pdfv.setFileContents(content);
 
 					optionsRecognized = true;
 					try {
@@ -135,24 +138,12 @@ public class ZUGFeRDValidator {
 					try {
 						pdfv.validate();
 
-						sha1Checksum = calcSHA1(file);
+						sha1Checksum = calcSHA1(new FileInputStream(file));
 
 						// Validate PDF
 
-						finalStringResult.append(pdfv.getXMLResult());
+						getPdfValidationResults(finalStringResult, pdfv, xv);
-						pdfValidity = context.isValid();
+					} catch (IrrecoverableValidationError | FileNotFoundException irx) {
-
-						Signature = context.getSignature();
-						context.clear();// clear sets valid to true again
-						if (pdfv.getRawXML() != null) {
-							xv.setStringContent(pdfv.getRawXML());
-							displayXMLValidationOutput = true;
-						} else {
-							context.addResultItem(
-									new ValidationResultItem(ESeverity.exception, "XML could not be extracted")
-											.setSection(17));
-						}
-					} catch (IrrecoverableValidationError irx) {
 						// @todo log
 					}
 
@@ -162,11 +153,9 @@ public class ZUGFeRDValidator {
 				} else {
 					boolean isXML = false;
 					try {
-
 						DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
 						DocumentBuilder db = dbf.newDocumentBuilder();
 
-						byte[] content=Files.readAllBytes(file.toPath());
 						content = XMLTools.removeBOM(content);
 						String s = new String(content, StandardCharsets.UTF_8);
 						InputSource is = new InputSource(new StringReader(s));
@@ -175,8 +164,7 @@ public class ZUGFeRDValidator {
 						Element root = doc.getDocumentElement();
 						isXML = true;//no exception so far
 
-					}
+					} catch (Exception ex) {
-					catch (Exception ex) {
 						// probably no xml file, sth like SAXParseException content not allowed in prolog
 						// ignore isXML is already false
 						// in the tests, this may error-out anyway
@@ -188,7 +176,7 @@ public class ZUGFeRDValidator {
 						optionsRecognized = true;
 						xv.setFilename(filename);
 						if (file.exists()) {
-							sha1Checksum = calcSHA1(file);
+							sha1Checksum = calcSHA1(Files.newInputStream(file.toPath()));
 						}
 
 						displayXMLValidationOutput = true;
@@ -217,9 +205,7 @@ public class ZUGFeRDValidator {
 				}
 
 			}
-		}
+		} catch (IrrecoverableValidationError | IOException irx) {
-
-		catch (IrrecoverableValidationError irx) {
 			// @todo log
 		} finally {
 			finalStringResult.append(context.getXMLResult());
@@ -227,6 +213,141 @@ public class ZUGFeRDValidator {
 
 		}
 
+		return formatOutput(finalStringResult, isPDF);
+	}
+
+	public String validate(InputStream inputStream, String fileNameOfInputStream) {
+		boolean xmlValidity;
+		context.clear();
+		StringBuffer finalStringResult = new StringBuffer();
+		SimpleDateFormat isoDF = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
+		Date date = new Date();
+		startTime = Calendar.getInstance().getTimeInMillis();
+		context.setFilename(fileNameOfInputStream);// set filename without path
+		finalStringResult.append("<validation filename='").append(context.getFilename()).append("' datetime='").append(isoDF.format(date)).append("'>");
+
+		boolean isPDF = false;
+		byte[] content = new byte[0];
+		try {
+
+			if (fileNameOfInputStream == null) {
+				optionsRecognized = false;
+				context.addResultItem(new ValidationResultItem(ESeverity.fatal, "Filename not specified").setSection(10)
+					.setPart(EPart.pdf));
+			}
+
+			PDFValidator pdfv = new PDFValidator(context);
+			if (inputStream == null) {
+				context.addResultItem(
+					new ValidationResultItem(ESeverity.fatal, "File not found").setSection(1).setPart(EPart.pdf));
+			} else if (inputStream.available() < 32) {
+				// with less then 32 bytes it can not even be a proper XML file
+				context.addResultItem(
+					new ValidationResultItem(ESeverity.fatal, "File too small").setSection(5).setPart(EPart.pdf));
+			} else {
+				content = inputStream.readAllBytes();
+				isPDF = ByteArraySearcher.contains(content, new byte[]{'%', 'P', 'D', 'F'});
+				XMLValidator xv = new XMLValidator(context);
+				if (isPDF) {
+					pdfv.setFilename(fileNameOfInputStream);
+					pdfv.setFileContents(content);
+
+					optionsRecognized = true;
+					finalStringResult.append("<pdf>");
+					try {
+						pdfv.validate();
+
+						sha1Checksum = calcSHA1(inputStream);
+
+						// Validate PDF
+
+						getPdfValidationResults(finalStringResult, pdfv, xv);
+					} catch (IrrecoverableValidationError irx) {
+						LOGGER.info(irx.getMessage());
+					}
+
+					finalStringResult.append("</pdf>\n");
+
+					context.clearCustomXML();
+				} else {
+					boolean isXML = false;
+					try {
+						DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
+						DocumentBuilder db = dbf.newDocumentBuilder();
+
+						content = XMLTools.removeBOM(content);
+						String s = new String(content, StandardCharsets.UTF_8);
+						InputSource is = new InputSource(new StringReader(s));
+						Document doc = db.parse(is);
+
+						Element root = doc.getDocumentElement();
+						isXML = true;//no exception so far
+					} catch (Exception ex) {
+						LOGGER.info("No XML part provided");
+					}
+					if (isXML) {
+						pdfValidity = true;
+						optionsRecognized = true;
+						xv.setFilename(fileNameOfInputStream);
+						sha1Checksum = calcSHA1(inputStream);
+
+						displayXMLValidationOutput = true;
+
+					} else {
+						optionsRecognized = false;
+						context.addResultItem(new ValidationResultItem(
+							ESeverity.exception,
+							"File does not look like PDF nor XML (contains neither %PDF nor <?xml)"
+						).setSection(8));
+
+					}
+				}
+				if ((optionsRecognized) && (displayXMLValidationOutput)) {
+					finalStringResult.append("<xml>");
+					try {
+						xv.validate();
+					} catch (IrrecoverableValidationError irx) {
+						LOGGER.info("The hell");
+					}
+					finalStringResult.append(xv.getXMLResult());
+					finalStringResult.append("</xml>");
+					context.clearCustomXML();
+				}
+
+				if ((isPDF) && (!pdfValidity)) {
+					context.setInvalid();
+				}
+
+			}
+		} catch (IrrecoverableValidationError | IOException irx) {
+			LOGGER.info(irx.getMessage());
+		} finally {
+			finalStringResult.append(context.getXMLResult());
+			finalStringResult.append("</validation>");
+
+		}
+
+		return formatOutput(finalStringResult, isPDF);
+	}
+
+	private void getPdfValidationResults(StringBuffer finalStringResult, PDFValidator pdfv, XMLValidator xv) throws IrrecoverableValidationError {
+		finalStringResult.append(pdfv.getXMLResult());
+		pdfValidity = context.isValid();
+
+		Signature = context.getSignature();
+		context.clear();// clear sets valid to true again
+		if (pdfv.getRawXML() != null) {
+			xv.setStringContent(pdfv.getRawXML());
+			displayXMLValidationOutput = true;
+		} else {
+			context.addResultItem(
+				new ValidationResultItem(ESeverity.exception, "XML could not be extracted")
+					.setSection(17));
+		}
+	}
+
+	private String formatOutput(StringBuffer finalStringResult, boolean isPDF) {
+		boolean xmlValidity;
 		OutputFormat format = OutputFormat.createPrettyPrint();
 		StringWriter sw = new StringWriter();
 		org.dom4j.Document document = null;
@@ -261,7 +382,8 @@ public class ZUGFeRDValidator {
 
 		LOGGER.info("Parsed PDF:" + pdfResult + " XML:" + (xmlValidity ? "valid" : "invalid")
 			+ " Signature:" + Signature + " Checksum:" + sha1Checksum + " Profile:" + context.getProfile()
-				+ " Version:" + context.getGeneration() + " Took:" + duration + "ms Errors:["+context.getCSVResult()+"] "+toBeAppended);
+			+ " Version:" + context.getGeneration() + " Took:" + duration + "ms Errors:[" + context.getCSVResult()
+			+ "] " + toBeAppended);
 		wasCompletelyValid = ((pdfValidity) && (xmlValidity));
 		return sw.toString();
 	}
@@ -272,10 +394,11 @@ public class ZUGFeRDValidator {
 	public void disableNotices() {
 		disableNotices = true;
 	}
+
 	/**
 	 * Read the file and calculate the SHA-1 checksum
 	 *
-	 * @param file the file to read
+	 * @param inputStream the InputStream to read
 	 * @return the hex representation of the SHA-1 using uppercase chars
 	 * @throws FileNotFoundException    if the file does not exist, is a directory
 	 *                                  rather than a regular file, or for some
@@ -283,25 +406,20 @@ public class ZUGFeRDValidator {
 	 * @throws IOException              if an I/O error occurs
 	 * @throws NoSuchAlgorithmException should never happen
 	 */
-	private static String calcSHA1(File file) {
+	private static String calcSHA1(InputStream inputStream) {
 		MessageDigest sha1 = null;
 		try {
 
 			sha1 = MessageDigest.getInstance("SHA-1");
-			InputStream input = new FileInputStream(file);
 			byte[] buffer = new byte[8192];
-			int len = input.read(buffer);
+			int len = inputStream.read(buffer);
 
 			while (len != -1) {
 				sha1.update(buffer, 0, len);
-				len = input.read(buffer);
+				len = inputStream.read(buffer);
 			}
-			input.close();
+			inputStream.close();
-		} catch (FileNotFoundException e) {
+		} catch (IOException | NoSuchAlgorithmException e) {
-			LOGGER.error(e.getMessage(), e);
-		} catch (IOException e) {
-			LOGGER.error(e.getMessage(), e);
-		} catch (NoSuchAlgorithmException e) {
 			LOGGER.error(e.getMessage(), e);
 		}
 		if (sha1 == null) {