Skip to content

Commit

Permalink
Merge pull request #379 from Sarenor/implement-input-stream-validation
Browse files Browse the repository at this point in the history 
Implement input stream validation
  • Loading branch information
@jstaerk
jstaerk authored May 6, 2024
2 parents ed97bb9 + 37fb01c commit 3d73e9c
Show file tree
Hide file tree
Showing 5 changed files with 344 additions and 173 deletions.
28 changes: 28 additions & 0 deletions validator/src/main/java/org/mustangproject/validator/ByteArraySearcher.java
View file
Original file line number Diff line number Diff line change
@@ -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;
}
}
168 changes: 86 additions & 82 deletions validator/src/main/java/org/mustangproject/validator/PDFValidator.java
View file
Original file line number Diff line number Diff line change
@@ -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;
Expand Down Expand Up @@ -33,14 +35,18 @@
import org.verapdf.metadata.fixer.FixerFactory;
import org.verapdf.metadata.fixer.MetadataFixerConfig;
import org.verapdf.gf.foundry.VeraGreenfieldFoundryProvider;
import org.verapdf.pdfa.flavours.PDFAFlavour;
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.ProcessorResult;
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;
Expand All @@ -50,15 +56,17 @@ 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 static final PDFAFlavour[] PDF_A_3_FLAVOURS = {PDFAFlavour.PDFA_3_A, PDFAFlavour.PDFA_3_A, PDFAFlavour.PDFA_3_A};

private String pdfFilename;

private byte[] fileContents;

private String pdfReport;
private ProcessorResult processorResult = null;

private String Signature;

Expand All @@ -69,17 +77,13 @@ protected static boolean stringArrayContains(String[] arr, String targetValue) {
}

@Override
public void validate() throws IrrecoverableValidationError {
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();

final byte[] pdfSignature = { '%', 'P', 'D', 'F' };
if (searcher.indexOf(file, pdfSignature) != 0) {
if (!ByteArraySearcher.contains(fileContents, new byte[]{'%', 'P', 'D', 'F'})) {
context.addResultItem(
new ValidationResultItem(ESeverity.fatal, "Not a PDF file "+pdfFilename).setSection(20).setPart(EPart.pdf));
new ValidationResultItem(ESeverity.fatal, "Not a PDF file " + pdfFilename).setSection(20).setPart(EPart.pdf));

}

Expand All @@ -103,41 +107,37 @@ public void validate() throws IrrecoverableValidationError {
// 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,
processorConfig.getValidatorConfig().isRecordPasses()));
pdfReport = reportStream.toString("utf-8").replaceAll("<\\?xml version=\"1\\.0\" encoding=\"utf-8\"\\?>",
"");
} catch (final VeraPDFException e) {
final ValidationResultItem vri = new ValidationResultItem(ESeverity.exception, e.getMessage()).setSection(6)
.setPart(EPart.pdf);
final StringWriter sw = new StringWriter();
final PrintWriter pw = new PrintWriter(sw);
e.printStackTrace(pw);
vri.setStacktrace(sw.toString());
context.addResultItem(vri);
} catch (final IOException excep) {
ItemDetails itemDetails = ItemDetails.fromValues(pdfFilename);
inputStream.mark(Integer.MAX_VALUE);
processorResult = processor.process(itemDetails, inputStream);
pdfReport = processorResult.getValidationResult().toString().replaceAll(
"<\\?xml version=\"1\\.0\" encoding=\"utf-8\"\\?>",
""
);
inputStream.reset();
} catch (final Exception excep) {
context.addResultItem(new ValidationResultItem(ESeverity.exception, excep.getMessage()).setSection(7)
.setPart(EPart.pdf).setStacktrace(excep.getStackTrace().toString()));
.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();
final Document docXMP;

if (xmp.length() == 0) {
context.addResultItem(new ValidationResultItem(ESeverity.error, "Invalid XMP Metadata not found")
.setSection(17).setPart(EPart.pdf));
.setSection(17).setPart(EPart.pdf));
}
/*
* checking for sth like <zf:ConformanceLevel>EXTENDED</zf:ConformanceLevel>
Expand All @@ -160,70 +160,76 @@ public void validate() throws IrrecoverableValidationError {

// get the first element
XPathExpression xpr = xpath.compile(
"//*[local-name()=\"ConformanceLevel\"]|//*[local-name()=\"Description\"]/@ConformanceLevel");
"//*[local-name()=\"ConformanceLevel\"]|//*[local-name()=\"Description\"]/@ConformanceLevel");
NodeList nodes = (NodeList) xpr.evaluate(docXMP, XPathConstants.NODESET);

if (nodes.getLength() == 0) {
context.addResultItem(
new ValidationResultItem(ESeverity.error, "XMP Metadata: ConformanceLevel not found")
.setSection(11).setPart(EPart.pdf));
new ValidationResultItem(ESeverity.error, "XMP Metadata: ConformanceLevel not found")
.setSection(11).setPart(EPart.pdf));
}
boolean conformanceLevelValid=false;

boolean conformanceLevelValid = false;
for (int i = 0; i < nodes.getLength(); i++) {

final String[] valueArray = { "BASIC WL", "BASIC", "MINIMUM", "EN 16931", "COMFORT", "CIUS", "EXTENDED", "XRECHNUNG" };
final String[] valueArray = {"BASIC WL", "BASIC", "MINIMUM", "EN 16931", "COMFORT", "CIUS", "EXTENDED", "XRECHNUNG"};
if (stringArrayContains(valueArray, nodes.item(i).getTextContent())) {
conformanceLevelValid=true;
conformanceLevelValid = true;
}
}
if (!conformanceLevelValid) {
context.addResultItem(new ValidationResultItem(ESeverity.error,
"XMP Metadata: ConformanceLevel contains invalid value").setSection(12).setPart(EPart.pdf));
context.addResultItem(new ValidationResultItem(
ESeverity.error,
"XMP Metadata: ConformanceLevel contains invalid value"
).setSection(12).setPart(EPart.pdf));

}
xpr = xpath.compile("//*[local-name()=\"DocumentType\"]|//*[local-name()=\"Description\"]/@DocumentType");
nodes = (NodeList) xpr.evaluate(docXMP, XPathConstants.NODESET);

if (nodes.getLength() == 0) {
context.addResultItem(new ValidationResultItem(ESeverity.error, "XMP Metadata: DocumentType not found")
.setSection(13).setPart(EPart.pdf));
.setSection(13).setPart(EPart.pdf));
}

boolean documentTypeValid=false;
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")) {
documentTypeValid=true;
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;
}
}
if (!documentTypeValid) {
context.addResultItem(
new ValidationResultItem(ESeverity.error, "XMP Metadata: DocumentType invalid")
.setSection(14).setPart(EPart.pdf));
new ValidationResultItem(ESeverity.error, "XMP Metadata: DocumentType invalid")
.setSection(14).setPart(EPart.pdf));

}
xpr = xpath.compile(
"//*[local-name()=\"DocumentFileName\"]|//*[local-name()=\"Description\"]/@DocumentFileName");
"//*[local-name()=\"DocumentFileName\"]|//*[local-name()=\"Description\"]/@DocumentFileName");
nodes = (NodeList) xpr.evaluate(docXMP, XPathConstants.NODESET);

if (nodes.getLength() == 0) {
context.addResultItem(
new ValidationResultItem(ESeverity.error, "XMP Metadata: DocumentFileName not found")
.setSection(21).setPart(EPart.pdf));
new ValidationResultItem(ESeverity.error, "XMP Metadata: DocumentFileName not found")
.setSection(21).setPart(EPart.pdf));
}
boolean documentFilenameValid=false;
boolean documentFilenameValid = false;
for (int i = 0; i < nodes.getLength(); i++) {
final String[] valueArray = { "factur-x.xml", "ZUGFeRD-invoice.xml", "zugferd-invoice.xml", "xrechnung.xml" , "order-x.xml" };
final String[] valueArray = {"factur-x.xml", "ZUGFeRD-invoice.xml", "zugferd-invoice.xml", "xrechnung.xml", "order-x.xml"};
if (stringArrayContains(valueArray, nodes.item(i).getTextContent())) {
documentFilenameValid=true;
documentFilenameValid = true;
}

// e.g. ZUGFeRD-invoice.xml
}
if (!documentFilenameValid) {

context.addResultItem(new ValidationResultItem(ESeverity.error,
"XMP Metadata: DocumentFileName contains invalid value").setSection(19).setPart(EPart.pdf));
context.addResultItem(new ValidationResultItem(
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);
Expand All @@ -234,30 +240,23 @@ public void validate() throws IrrecoverableValidationError {
// print the text content of each child
if (nodes.getLength() == 0) {
context.addResultItem(new ValidationResultItem(ESeverity.error, "XMP Metadata: Version not found")
.setSection(15).setPart(EPart.pdf));
.setSection(15).setPart(EPart.pdf));
}

boolean versionValid=false;
boolean versionValid = false;
for (int i = 0; i < nodes.getLength(); i++) {
final String[] valueArray = { "1.0", "2p0", "1.2", "2.0" , "2.1" }; //1.2, 2.0 and 2.1 are for xrechnung 1.2, 2p0 can be ZF 2.0, 2.1, 2.1.1
final String[] valueArray = {"1.0", "2p0", "1.2", "2.0", "2.1"}; //1.2, 2.0 and 2.1 are for xrechnung 1.2, 2p0 can be ZF 2.0, 2.1, 2.1.1
if (stringArrayContains(valueArray, nodes.item(i).getTextContent())) {
versionValid=true;
versionValid = true;
} // e.g. 1.0
}
if (!versionValid) {
context.addResultItem(
new ValidationResultItem(ESeverity.error, "XMP Metadata: Version contains invalid value")
.setSection(16).setPart(EPart.pdf));
new ValidationResultItem(ESeverity.error, "XMP Metadata: Version contains invalid value")
.setSection(16).setPart(EPart.pdf));

}

} catch (final SAXException e) {
LOGGER.error(e.getMessage(), e);
} catch (final IOException e) {
LOGGER.error(e.getMessage(), e);
} catch (final ParserConfigurationException e) {
LOGGER.error(e.getMessage(), e);
} catch (final XPathExpressionException e) {
} catch (final SAXException | IOException | ParserConfigurationException | XPathExpressionException e) {
LOGGER.error(e.getMessage(), e);
}
zfXML = zi.getUTF8();
Expand All @@ -272,19 +271,19 @@ public void validate() throws IrrecoverableValidationError {
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";
}

Expand All @@ -295,38 +294,43 @@ public void validate() throws IrrecoverableValidationError {
}

// step 4:validate additional data
final HashMap<String, byte[]> additionalData=zi.getAdditionalData();
final HashMap<String, byte[]> additionalData = zi.getAdditionalData();
for (final String filename : additionalData.keySet()) {
// validating xml in byte[] additionalData.get(filename)
LOGGER.info("validating additionalData " + filename);
validateSchema(additionalData.get(filename), "ad/basic/additional_data_base_schema.xsd", 2, EPart.pdf);
}


//end

final long endTime = Calendar.getInstance().getTimeInMillis();
if (!pdfReport.contains("validationReports compliant=\"1\"")) {
if (!processorResult.getValidationResult().isCompliant()) {
context.setInvalid();
}
if (!pdfReport.contains("PDF/A-3")) {
if (Arrays.stream(PDF_A_3_FLAVOURS)
.anyMatch(pdfaFlavour -> processorResult.getValidationResult().getPDFAFlavour().equals(pdfaFlavour))) {
context.addResultItem(
new ValidationResultItem(ESeverity.error, "Not a PDF/A-3").setSection(23).setPart(EPart.pdf));
new ValidationResultItem(ESeverity.error, "Not a PDF/A-3").setSection(23).setPart(EPart.pdf));

}
context.addCustomXML(pdfReport + "<info><signature>"
+ ((context.getSignature() != null) ? context.getSignature() : "unknown")
+ "</signature><duration unit=\"ms\">" + (endTime - startPDFTime) + "</duration></info>");
+ ((context.getSignature() != null) ? context.getSignature() : "unknown")
+ "</signature><duration unit=\"ms\">" + (endTime - startPDFTime) + "</duration></info>");

}


@Override
public void setFilename(String filename) throws IrrecoverableValidationError {
this.pdfFilename = filename;

}

public void setFileContents(byte[] fileContents) {
this.fileContents = fileContents;
}

public String getRawXML() {
return zfXML;

Expand Down
Loading

0 comments on commit 3d73e9c

Please sign in to comment.