louisdevie/mustangproject
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Added toecount to main tree, closed #44, added pdf 1.4 and a3 sample files

Browse Source
This commit is contained in:
Jochen Stärk
2017-09-01 10:17:54 +02:00
parent 127435cf04
commit 5d3ad6f920
12 changed files with 891 additions and 219 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
History.md
View File

@@ -1,3 +1,10 @@
1.4.1
=====
Now using factory. Export now also possible on OutputStream.
Further dev improvements: no more need to call PDFattachZugferdFile(null);
toecount now has options to combine documents and upgrade xml file from ZF1 to ZF2
More unit tests, e.g. for custom xml export.
1.4.0
=====
2017-05-11
@@ -12,23 +19,30 @@ Thanks to AlexanderSchmidt and yankee42.
1.3.0
=====
2016-03-15
Additional checks in the new version facilitate correct usage within your own applications. For example, input data (PDF/A-1) and the sequence of the calls are checked for accuracy.
A community patch (thanks to Alexander Schmidt) improves the internal functioning and removes the last known bugs.
1.2.0
=====
2015-10-15
Compliance to GEFEG and ZUGFeRD Checker.
1.1.2
=====
2015-06-15
The ZUGFeRD-Metadata now conforms to more validators like the Konik Validation Service. As a new feature it is now also possible to create test invoices.
1.1.1
=====
2015-03-31
Maven and custom xml
1.1.0
=====
2014-12-07
ZUGFeRD 1.0
1.0.0
=====
2014-05-22
ZUGFeRD 1.0RC Comfort

30
dependency-reduced-pom.xml
View File

@@ -46,6 +46,36 @@
</scm>
<build>
<plugins>
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<configuration>
<archive>
<manifest>
<mainClass>org.mustangproject.toecount.Toecount</mainClass>
</manifest>
</archive>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
</plugin>
<plugin>
<artifactId>maven-compiler-plugin</artifactId>
<version>2.3.2</version>
<configuration>
<archive>
<manifest>
<addClasspath>true</addClasspath>
<mainClass>org.mustangproject.toecount.Toecount</mainClass>
</manifest>
</archive>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
<source>1.7</source>
<target>1.7</target>
</configuration>
</plugin>
<plugin>
<artifactId>maven-deploy-plugin</artifactId>
<version>2.8.2</version>

44
pom.xml
View File

@@ -58,9 +58,53 @@
<version>4.3.1</version>
<scope>test</scope>
</dependency>
<!-- For Toecount -->
<dependency>
<groupId>com.sanityinc</groupId>
<artifactId>jargs</artifactId>
<version>2.0-SNAPSHOT</version>
</dependency>
</dependencies>
<build>
<plugins>
<!-- toecount -->
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<configuration>
<archive>
<manifest>
<mainClass>org.mustangproject.toecount.Toecount</mainClass>
</manifest>
</archive>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>2.3.2</version>
<configuration>
<archive>
<manifest>
<addClasspath>true</addClasspath>
<mainClass>org.mustangproject.toecount.Toecount</mainClass>
</manifest>
</archive>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
<!-- 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>1.7</source>
<target>1.7</target>
</configuration>
</plugin>
<!-- /toecount -->
<plugin>
<artifactId>maven-deploy-plugin</artifactId>
<version>2.8.2</version>

54
src/main/java/org/mustangproject/ZUGFeRD/XMPSchemaPDFAExtensions.java
View File

@@ -1,4 +1,5 @@
package org.mustangproject.ZUGFeRD;
/**
* Mustangproject's ZUGFeRD implementation
* ZUGFeRD exporter helper class
@@ -20,16 +21,17 @@ import org.apache.xmpbox.type.PDFASchemaType;
import org.apache.xmpbox.type.StructuredType;
import org.apache.xmpbox.type.TextType;
/**
* Additionally to adding a RDF namespace with a indication which file attachment if Zugferd, this namespace has to be described in a PDFA Extension Schema. I
* know there is a PDFAExtensionSchema in the context of PDFBox' XMPBOX but I have been using PDFBox' JempBOX so far because I could not find out how to write
* XMPBOX XMPMetadata to a PDF file. So this is my version of PDFAExtensionSchema for PDFBox' jempbox XMPMetadata
* Additionally to adding a RDF namespace with a indication which file
* attachment if Zugferd, this namespace has to be described in a PDFA Extension
* Schema. I know there is a PDFAExtensionSchema in the context of PDFBox'
* XMPBOX but I have been using PDFBox' JempBOX so far because I could not find
* out how to write XMPBOX XMPMetadata to a PDF file. So this is my version of
* PDFAExtensionSchema for PDFBox' jempbox XMPMetadata
*
* @author jstaerk
*/
@StructuredType(preferedPrefix = "pdfaExtension", namespace = "http://www.aiim.org/pdfa/ns/extension/")
public class XMPSchemaPDFAExtensions extends PDFAExtensionSchema {
@@ -38,13 +40,16 @@ import org.apache.xmpbox.type.TextType;
public final String xmlns_pdfaProperty = "http://www.aiim.org/pdfa/ns/property#";
public final String prefix_pdfaProperty = "pdfaProperty";
private DefinedStructuredType addProperty(ArrayProperty parent, String name, String type, String category, String description) {
private DefinedStructuredType addProperty(ArrayProperty parent, String name, String type, String category,
String description) {
XMPMetadata metadata = getMetadata();
DefinedStructuredType li = new DefinedStructuredType(metadata, getNamespace(), getPrefix(), XmpConstants.LIST_NAME);
DefinedStructuredType li = new DefinedStructuredType(metadata, getNamespace(), getPrefix(),
XmpConstants.LIST_NAME);
li.setAttribute(new Attribute(getNamespace(), XmpConstants.PARSE_TYPE, XmpConstants.RESOURCE_NAME));
ChoiceType pdfa2 = new ChoiceType(metadata, xmlns_pdfaProperty, prefix_pdfaProperty, PDFAPropertyType.NAME, name);
ChoiceType pdfa2 = new ChoiceType(metadata, xmlns_pdfaProperty, prefix_pdfaProperty, PDFAPropertyType.NAME,
name);
li.addProperty(pdfa2);
pdfa2 = new ChoiceType(metadata, xmlns_pdfaProperty, prefix_pdfaProperty, PDFAPropertyType.VALUETYPE, type);
@@ -53,7 +58,8 @@ import org.apache.xmpbox.type.TextType;
pdfa2 = new ChoiceType(metadata, xmlns_pdfaProperty, prefix_pdfaProperty, PDFAPropertyType.CATEGORY, category);
li.addProperty(pdfa2);
pdfa2 = new ChoiceType(metadata, xmlns_pdfaProperty, prefix_pdfaProperty, PDFAPropertyType.DESCRIPTION, description);
pdfa2 = new ChoiceType(metadata, xmlns_pdfaProperty, prefix_pdfaProperty, PDFAPropertyType.DESCRIPTION,
description);
li.addProperty(pdfa2);
parent.addProperty(li);
@@ -64,31 +70,49 @@ import org.apache.xmpbox.type.TextType;
public XMPSchemaPDFAExtensions(XMPMetadata metadata) {
super(metadata);
attachExtensions(metadata, true);
}
public XMPSchemaPDFAExtensions(XMPMetadata metadata, boolean withZF) {
super(metadata);
attachExtensions(metadata, withZF);
}
public void attachExtensions(XMPMetadata metadata, boolean withZF) {
addNamespace(xmlns_pdfaSchema, prefix_pdfaSchema);
addNamespace(xmlns_pdfaProperty, prefix_pdfaProperty);
ArrayProperty newBag = createArrayProperty(SCHEMAS, Cardinality.Bag);
DefinedStructuredType li = new DefinedStructuredType(metadata, getNamespace(), getPrefix(), XmpConstants.LIST_NAME);
DefinedStructuredType li = new DefinedStructuredType(metadata, getNamespace(), getPrefix(),
XmpConstants.LIST_NAME);
li.setAttribute(new Attribute(getNamespace(), XmpConstants.PARSE_TYPE, XmpConstants.RESOURCE_NAME));
newBag.addProperty(li);
addProperty(newBag);
TextType pdfa1 = new TextType(metadata, xmlns_pdfaSchema, prefix_pdfaSchema, PDFASchemaType.SCHEMA, "ZUGFeRD PDFA Extension Schema");
if (withZF) {
TextType pdfa1 = new TextType(metadata, xmlns_pdfaSchema, prefix_pdfaSchema, PDFASchemaType.SCHEMA,
"ZUGFeRD PDFA Extension Schema");
li.addProperty(pdfa1);
pdfa1 = new TextType(metadata, xmlns_pdfaSchema, prefix_pdfaSchema, PDFASchemaType.NAMESPACE_URI, "urn:ferd:pdfa:CrossIndustryDocument:invoice:1p0#");
pdfa1 = new TextType(metadata, xmlns_pdfaSchema, prefix_pdfaSchema, PDFASchemaType.NAMESPACE_URI,
"urn:ferd:pdfa:CrossIndustryDocument:invoice:1p0#");
li.addProperty(pdfa1);
pdfa1 = new TextType(metadata, xmlns_pdfaSchema, prefix_pdfaSchema, PDFASchemaType.PREFIX, "zf");
li.addProperty(pdfa1);
ArrayProperty newSeq = new ArrayProperty(metadata, xmlns_pdfaSchema, prefix_pdfaSchema, PDFASchemaType.PROPERTY, Cardinality.Seq);
ArrayProperty newSeq = new ArrayProperty(metadata, xmlns_pdfaSchema, prefix_pdfaSchema,
PDFASchemaType.PROPERTY, Cardinality.Seq);
li.addProperty(newSeq);
addProperty(newSeq, "DocumentFileName", "Text", "external", "name of the embedded XML invoice file");
addProperty(newSeq, "DocumentType", "Text", "external", "INVOICE");
addProperty(newSeq, "Version", "Text", "external", "The actual version of the ZUGFeRD XML schema");
addProperty(newSeq, "ConformanceLevel", "Text", "external", "The conformance level of the embedded ZUGFeRD data");
addProperty(newSeq, "ConformanceLevel", "Text", "external",
"The conformance level of the embedded ZUGFeRD data");
}
}
}

104
src/main/java/org/mustangproject/ZUGFeRD/ZUGFeRDExporterFromA1Factory.java
View File

@@ -26,6 +26,7 @@ import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import java.util.GregorianCalendar;
public class ZUGFeRDExporterFromA1Factory {
@@ -35,12 +36,13 @@ public class ZUGFeRDExporterFromA1Factory {
private String producer = "mustangproject";
private String creator = "mustangproject";
private boolean attachZugferdHeaders = true;
private static boolean includeXMPinOptionalXPacket=true;
/**
* Makes A PDF/A3a-compliant document from a PDF-A1 compliant document (on
* the metadata level, this will not e.g. convert graphics to JPG-2000)
* Makes A PDF/A3a-compliant document from a PDF-A1 compliant document (on the
* metadata level, this will not e.g. convert graphics to JPG-2000)
*
* @param pdfFilename filename of an PDF/A1 compliant document
* @param pdfFilename
* filename of an PDF/A1 compliant document
*/
public ZUGFeRDExporter loadFromPDFA1(String pdfFilename) throws IOException {
ensurePDFIsValidA1(new FileDataSource(pdfFilename));
@@ -50,10 +52,11 @@ public class ZUGFeRDExporterFromA1Factory {
}
/**
* Makes A PDF/A3a-compliant document from a PDF-A1 compliant document (on
* the metadata level, this will not e.g. convert graphics to JPG-2000)
* Makes A PDF/A3a-compliant document from a PDF-A1 compliant document (on the
* metadata level, this will not e.g. convert graphics to JPG-2000)
*
* @param pdfBinary binary of a PDF/A1 compliant document
* @param pdfBinary
* binary of a PDF/A1 compliant document
*/
public ZUGFeRDExporter loadFromPDFA1(byte[] pdfBinary) throws IOException {
ensurePDFIsValidA1(new ByteArrayDataSource(new ByteArrayInputStream(pdfBinary)));
@@ -66,10 +69,11 @@ public class ZUGFeRDExporterFromA1Factory {
}
/**
* Makes A PDF/A3a-compliant document from a PDF-A1 compliant document (on
* the metadata level, this will not e.g. convert graphics to JPG-2000)
* Makes A PDF/A3a-compliant document from a PDF-A1 compliant document (on the
* metadata level, this will not e.g. convert graphics to JPG-2000)
*
* @param pdfSource source to read a PDF/A1 compliant document from
* @param pdfSource
* source to read a PDF/A1 compliant document from
*/
public ZUGFeRDExporter loadFromPDFA1(InputStream pdfSource) throws IOException {
return loadFromPDFA1(readAllBytes(pdfSource));
@@ -93,8 +97,8 @@ public class ZUGFeRDExporterFromA1Factory {
PDDocumentCatalog cat = doc.getDocumentCatalog();
PDMetadata metadata = new PDMetadata(doc);
cat.setMetadata(metadata);
XMPMetadata xmp = XMPMetadata.createXMPMetadata();
XMPMetadata xmp = XMPMetadata.createXMPMetadata();
PDFAIdentificationSchema pdfaid = new PDFAIdentificationSchema(xmp);
@@ -118,21 +122,21 @@ public class ZUGFeRDExporterFromA1Factory {
pdf.setProducer(fullProducer);
/*
* // Mandatory: PDF/A3-a is tagged PDF which has to be expressed using
* a // MarkInfo dictionary (PDF A/3 Standard sec. 6.7.2.2) PDMarkInfo
* markinfo = new PDMarkInfo(); markinfo.setMarked(true);
* // Mandatory: PDF/A3-a is tagged PDF which has to be expressed using a //
* MarkInfo dictionary (PDF A/3 Standard sec. 6.7.2.2) PDMarkInfo markinfo = new
* PDMarkInfo(); markinfo.setMarked(true);
* doc.getDocumentCatalog().setMarkInfo(markinfo);
*/
/*
*
* To be on the safe side, we use level B without Markinfo because we
* can not guarantee that the user correctly tagged the templates for
* the PDF.
* To be on the safe side, we use level B without Markinfo because we can not
* guarantee that the user correctly tagged the templates for the PDF.
*/
try {
pdfaid.setConformance(conformanceLevel.getLetter());// $NON-NLS-1$ //$NON-NLS-1$
} catch (BadFieldValueException ex) {
// This should be impossible, because it would occur only if an illegal conformance level is supplied,
// This should be impossible, because it would occur only if an illegal
// conformance level is supplied,
// however the enum enforces that the conformance level is valid.
throw new Error(ex);
}
@@ -140,18 +144,16 @@ public class ZUGFeRDExporterFromA1Factory {
pdfaid.setPart(3);
if (attachZugferdHeaders) {
addZugferdXMP(xmp); /*
* this is the only line where we do something
* Zugferd-specific, i.e. add PDF metadata
* specifically for Zugferd, not generically for
* a embedded file
addXMP(xmp); /*
* this is the only line where we do something Zugferd-specific, i.e. add PDF
* metadata specifically for Zugferd, not generically for a embedded file
*/
}
try {
metadata.importXMPMetadata(serializeXmpMetadata(xmp));
} catch (TransformerException e) {
throw new ZUGFeRDExportException("Could not export XmpMetadata", e);
}
@@ -160,7 +162,25 @@ public class ZUGFeRDExporterFromA1Factory {
private static byte[] serializeXmpMetadata(XMPMetadata xmpMetadata) throws TransformerException {
XmpSerializer serializer = new XmpSerializer();
ByteArrayOutputStream buffer = new ByteArrayOutputStream();
String prefix="";
String suffix="";
if (includeXMPinOptionalXPacket) {
prefix="<?xpacket begin=\"\uFEFF\" id=\"W5M0MpCehiHzreSzNTczkc9d\"?>";
suffix="<?xpacket end=\"w\"?>";
}
try {
buffer.write(prefix.getBytes("UTF-8"));
serializer.serialize(xmpMetadata, buffer, false);
buffer.write(suffix.getBytes("UTF-8"));
} catch (UnsupportedEncodingException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return buffer.toByteArray();
}
@@ -169,19 +189,21 @@ public class ZUGFeRDExporterFromA1Factory {
}
/**
* This will add both the RDF-indication which embedded file is Zugferd
* and the neccessary PDF/A schema extension description to be able to add
* this information to RDF
* This will add both the RDF-indication which embedded file is Zugferd and the
* neccessary PDF/A schema extension description to be able to add this
* information to RDF
*
* @param metadata
*/
private void addZugferdXMP(XMPMetadata metadata) {
private void addXMP(XMPMetadata metadata) {
if (attachZugferdHeaders) {
XMPSchemaZugferd zf = new XMPSchemaZugferd(metadata, zugferdConformanceLevel);
metadata.addSchema(zf);
}
XMPSchemaPDFAExtensions pdfaex = new XMPSchemaPDFAExtensions(metadata);
XMPSchemaPDFAExtensions pdfaex = new XMPSchemaPDFAExtensions(metadata, attachZugferdHeaders);
metadata.addSchema(pdfaex);
@@ -201,18 +223,16 @@ public class ZUGFeRDExporterFromA1Factory {
private static boolean getA1ParserValidationResult(PreflightParser parser) throws IOException {
/*
* Parse the PDF file with PreflightParser that inherits from the
* NonSequentialParser. Some additional controls are present to
* check a set of PDF/A requirements. (Stream length consistency,
* EOL after some Keyword...)
* NonSequentialParser. Some additional controls are present to check a set of
* PDF/A requirements. (Stream length consistency, EOL after some Keyword...)
*/
parser.parse();
try (PreflightDocument document = parser.getPreflightDocument()) {
/*
* Once the syntax validation is done, the parser can provide a
* PreflightDocument (that inherits from PDDocument) This document
* process the end of PDF/A validation.
* PreflightDocument (that inherits from PDDocument) This document process the
* end of PDF/A validation.
*/
document.validate();
@@ -221,9 +241,9 @@ public class ZUGFeRDExporterFromA1Factory {
return document.getResult().isValid();
} catch (ValidationException e) {
/*
* the parse method can throw a SyntaxValidationException if the PDF
* file can't be parsed. In this case, the exception contains an
* instance of ValidationResult
* the parse method can throw a SyntaxValidationException if the PDF file can't
* be parsed. In this case, the exception contains an instance of
* ValidationResult
*/
return false;
}
@@ -234,10 +254,10 @@ public class ZUGFeRDExporterFromA1Factory {
*
* PDF/A-3 has three coformance levels, called "A", "U" and "B".
*
* PDF/A-3-B where B means only visually preservable, U -standard for
* Mustang- means visually and unicode preservable and A means full
* compliance, i.e. visually, unicode and structurally preservable and
* tagged PDF, i.e. useful metainformation for blind people.
* PDF/A-3-B where B means only visually preservable, U -standard for Mustang-
* means visually and unicode preservable and A means full compliance, i.e.
* visually, unicode and structurally preservable and tagged PDF, i.e. useful
* metainformation for blind people.
*
* Feel free to pass "A" as new level if you know what you are doing :-)
*

73
src/main/java/org/mustangproject/toecount/FileChecker.java Executable file
View File

@@ -0,0 +1,73 @@
package org.mustangproject.toecount;
import org.mustangproject.ZUGFeRD.ZUGFeRDImporter;
public class FileChecker {
String filename;
StatRun thisRun;
boolean isPDF=false;
public FileChecker(String filename, StatRun statistics) {
this.filename=filename;
thisRun=statistics;
thisRun.incFileCount();
String extension = "";
if (!thisRun.shallIgnoreFileExt()) {
int extIndex = filename.lastIndexOf(".");
if (extIndex >= 0) {
extension = filename.substring(extIndex).toLowerCase();
isPDF=extension.equals(".pdf");// alternative check for PDF: File starts with %PDF-
thisRun.incPDFCount();
}
} else {
thisRun.incPDFCount();
}
}
public boolean checkForZUGFeRD() {
if ((!isPDF)&&(!thisRun.shallIgnoreFileExt())) {
return false;
}
ZUGFeRDImporter zi=new ZUGFeRDImporter();
try {
zi.extract(filename);
if (zi.canParse()) {
thisRun.incZUGFeRDCount();
return true;
} else {
return false;
}
} catch (NullPointerException e) {
// something really rare happened -- corrupted ZF?
/***
* e.g. Exception in thread "main" java.lang.NullPointerException
at org.mustangproject.ZUGFeRD.ZUGFeRDImporter.extractLowLevel(ZUGFeRDImporter.java:90)
at org.mustangproject.ZUGFeRD.ZUGFeRDImporter.extract(ZUGFeRDImporter.java:64)
at toecount.FileChecker.checkForZUGFeRD(FileChecker.java:33)
at toecount.Toecount.main(Toecount.java:111)
*
*/
// Ignore nevertheless, most likely we're batch processing
return false;
} catch (Exception e2) {
/**
* probably thrown up from
AM org.apache.pdfbox.pdfparser.PDFParser parse, most likely
INFORMATION: Document is encrypted
but also other internal PDF errors possible like
..Okt 23, 2015 11:17:53 AM org.apache.pdfbox.pdfparser.XrefTrailerResolver setStartxref
*/
return false;
}
}
public boolean isPDF() {
return isPDF;
}
public String getOutputLine() {
return thisRun.getOutputLine();
}
}

56
src/main/java/org/mustangproject/toecount/FileTraverser.java Executable file
View File

@@ -0,0 +1,56 @@
package org.mustangproject.toecount;
import static java.nio.file.FileVisitResult.CONTINUE;
import java.io.IOException;
import java.nio.file.FileVisitResult;
import java.nio.file.Path;
import java.nio.file.SimpleFileVisitor;
import java.nio.file.attribute.BasicFileAttributes;
public class FileTraverser extends SimpleFileVisitor<Path> {
private StatRun thisRun;
public FileTraverser(StatRun statistics) {
this.thisRun=statistics;
}
/***
* check each file
*/
@Override
public FileVisitResult visitFile(Path file, BasicFileAttributes attr) {
if (attr.isSymbolicLink()) {
// Not yet handled
} else if (attr.isRegularFile()) {
String filename = file.toString();
FileChecker fc = new FileChecker(filename, thisRun);
fc.checkForZUGFeRD();
System.out.print(fc.getOutputLine());
}
return CONTINUE;
}
/***
* for each directory
*/
@Override
public FileVisitResult postVisitDirectory(Path dir, IOException exc) {
// System.out.format("Directory: %s%n", dir);
thisRun.incDirCount();
return CONTINUE;
}
/***
* show errors like file permission stacktraces
*/
@Override
public FileVisitResult visitFileFailed(Path file, IOException exc) {
System.err.println(exc);
return CONTINUE;
}
}

69
src/main/java/org/mustangproject/toecount/StatRun.java Executable file
View File

@@ -0,0 +1,69 @@
package org.mustangproject.toecount;
public class StatRun {
private int pdfCount = 0;
private int horseCount = 0;
private int fileCount = 0;
private int dirCount = 0;
private boolean checkFileExt=true;
public void ignoreFileExtension() {
checkFileExt=false;
}
public boolean shallIgnoreFileExt() {
return !checkFileExt;
}
public void incFileCount(){
fileCount++;
}
public void incPDFCount(){
pdfCount++;
}
public void incZUGFeRDCount(){
horseCount++;
}
public void incDirCount(){
dirCount++;
}
public int getFileCount(){
return fileCount;
}
public int getPDFCount(){
return pdfCount;
}
public int getZUGFeRDCount(){
return horseCount;
}
public int getDirCount(){
return dirCount;
}
/***
* returns final statistics
* @return
*/
public String getSummaryLine() {
return "\r\n===================================================================\r\n"+String.format(
"Files:\t%d\tDirs:\t%d\tPDF:\t%d\tZUGFeRD:\t%d\r\n",
getFileCount(), getDirCount(), getPDFCount(), getZUGFeRDCount());
}
/***
* show that something is happening
* @return String
*/
public String getOutputLine() {
return ".";
}
}

306
src/main/java/org/mustangproject/toecount/Toecount.java Executable file
View File

@@ -0,0 +1,306 @@
package org.mustangproject.toecount;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.regex.Pattern;
import javax.xml.bind.JAXBException;
import javax.xml.transform.TransformerException;
import org.mustangproject.ZUGFeRD.ZUGFeRDExporter;
import org.mustangproject.ZUGFeRD.ZUGFeRDExporterFromA1Factory;
import org.mustangproject.ZUGFeRD.ZUGFeRDImporter;
import com.sanityinc.jargs.CmdLineParser;
import com.sanityinc.jargs.CmdLineParser.Option;
public class Toecount {
// build with: /opt/local/bin/mvn clean compile assembly:single
private static void printUsage() {
System.err.println(getUsage());
}
private static String getUsage() {
return "Usage: Toecount [-d,--directory] [-l,--listfromstdin] [-i,--ignorefileextension] | [-c,--combine] | [-e,--extract] | [-u,--upgrade] | [-a,--a3only] | [-h,--help]\r\n";
}
private static void printHelp() {
System.out.println("Mustangproject.org's Toecount 0.2.0 \r\n"
+ "A Apache Public License command line tool for statistics on PDF invoices with\r\n"
+ "ZUGFeRD Metadata (http://www.zugferd.org)\r\n" + "\r\n" + getUsage() + "Count operations"
+ "\t--directory= count ZUGFeRD files in directory to be scanned\r\n"
+ "\t\tIf it is a directory, it will recurse.\r\n"
+ "\t--listfromstdin=count ZUGFeRD files from a list of linefeed separated files on runtime.\r\n"
+ "\t\tIt will start once a blank line has been entered.\r\n"
+ "\t--ignorefileextension=if PDF files are counted check *.* instead of *.pdf files"
+ "Merge operations"
+ "\t--combine= combine ZUGFeRD-invoice.xml and invoice.pdf to invoice.zugferd.pdf\r\n"
+ "\t--extract= extract invoice.zugferd.pdf to ZUGFeRD-invoice.xml\r\n"
+ "\t--upgrade= upgrade ZUGFeRD-invoice.pdf to ZUGFeRD-2-invoice.xml\r\n"
+ "\t--a3only= upgrade from PDF/A1 to A3 only \r\n"
);
}
// /opt/local/bin/mvn clean compile assembly:single
public static void main(String[] args) {
CmdLineParser parser = new CmdLineParser();
Option<String> dirnameOption = parser.addStringOption('d', "directory");
Option<Boolean> filesFromStdInOption = parser.addBooleanOption('l', "listfromstdin");
Option<Boolean> ignoreFileExtOption = parser.addBooleanOption('i', "ignorefileextension");
Option<Boolean> combineOption = parser.addBooleanOption('c', "combine");
Option<Boolean> extractOption = parser.addBooleanOption('e', "extract");
Option<Boolean> helpOption = parser.addBooleanOption('h', "help");
Option<Boolean> upgradeOption = parser.addBooleanOption('u', "upgrade");
Option<Boolean> a3onlyOption = parser.addBooleanOption('a', "a3only");
if (args.length == 0) {
printUsage();
System.exit(2);
}
try {
parser.parse(args);
} catch (CmdLineParser.OptionException e) {
System.err.println(e.getMessage());
printUsage();
System.exit(2);
}
String directoryName = parser.getOptionValue(dirnameOption);
Boolean filesFromStdIn = parser.getOptionValue(filesFromStdInOption, Boolean.FALSE);
Boolean combineRequested = parser.getOptionValue(combineOption, Boolean.FALSE);
Boolean extractRequested = parser.getOptionValue(extractOption, Boolean.FALSE);
Boolean helpRequested = parser.getOptionValue(helpOption, Boolean.FALSE);
Boolean upgradeRequested = parser.getOptionValue(upgradeOption, Boolean.FALSE);
Boolean ignoreFileExt = parser.getOptionValue(ignoreFileExtOption, Boolean.FALSE);
Boolean a3only = parser.getOptionValue(a3onlyOption, Boolean.FALSE);
if (helpRequested) {
printHelp();
}
if (((directoryName != null) && (directoryName.length() > 0)) || filesFromStdIn.booleanValue()) {
StatRun sr = new StatRun();
if (ignoreFileExt) {
sr.ignoreFileExtension();
}
if (directoryName != null) {
Path startingDir = Paths.get(directoryName);
if (Files.isRegularFile(startingDir)) {
String filename = startingDir.toString();
FileChecker fc = new FileChecker(filename, sr);
fc.checkForZUGFeRD();
System.out.print(fc.getOutputLine());
} else if (Files.isDirectory(startingDir)) {
FileTraverser pf = new FileTraverser(sr);
try {
Files.walkFileTree(startingDir, pf);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
if (filesFromStdIn) {
BufferedReader in = new BufferedReader(new InputStreamReader(System.in));
String s;
try {
while ((s = in.readLine()) != null && s.length() != 0) {
FileChecker fc = new FileChecker(s, sr);
fc.checkForZUGFeRD();
System.out.print(fc.getOutputLine());
}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
System.out.println(sr.getSummaryLine());
} else if (combineRequested) {
/*
* ZUGFeRDExporter ze= new ZUGFeRDExporterFromA1Factory()
* .setProducer("toecount") .setCreator(System.getProperty("user.name"))
* .loadFromPDFA1("invoice.pdf");
*/
try {
ZUGFeRDExporter ze = new ZUGFeRDExporter();
ze.PDFmakeA3compliant("./invoice.pdf", "Toecount", System.getProperty("user.name"), true);
ze.setZUGFeRDXMLData(Files.readAllBytes(Paths.get("./ZUGFeRD-invoice.xml")));
ze.PDFattachZugferdFile(null);
ze.export("invoice.ZUGFeRD.pdf");
} catch (IOException e) {
e.printStackTrace();
// } catch (JAXBException e) {
// e.printStackTrace();
} catch (TransformerException e) {
e.printStackTrace();
}
System.out.println("Written to invoice.ZUGFeRD.pdf");
} else if (extractRequested) {
ZUGFeRDImporter zi = new ZUGFeRDImporter();
zi.extract("invoice.zugferd.pdf");
try {
Files.write(Paths.get("./ZUGFeRD-invoice.xml"), zi.getRawXML());
} catch (IOException e) {
e.printStackTrace();
}
System.out.println("Written to ZUGFeRD-invoice.xml");
} else if (a3only) {
/*
* ZUGFeRDExporter ze= new ZUGFeRDExporterFromA1Factory()
* .setProducer("toecount") .setCreator(System.getProperty("user.name"))
* .loadFromPDFA1("invoice.pdf");
*/
try {
ZUGFeRDExporter ze = new ZUGFeRDExporterFromA1Factory().setAttachZugferdHeaders(false).loadFromPDFA1("./invoice.pdf");
ze.export("invoice.a3.pdf");
} catch (IOException e) {
e.printStackTrace();
}
System.out.println("Written to invoice.a3.pdf");
} else if (upgradeRequested) {
try {
String xml = new String(Files.readAllBytes(Paths.get("./ZUGFeRD-invoice.xml")), StandardCharsets.UTF_8);
// todo: attributes may also be in single quotes, this one hardcodedly expects
// double ones
xml = xml.replace("\"urn:ferd:CrossIndustryDocument:invoice:1p0",
"\"urn:un:unece:uncefact:data:standard:CrossIndustryInvoice:13");
xml = xml.replace("urn:un:unece:uncefact:data:standard:ReusableAggregateBusinessInformationEntity:12",
"urn:un:unece:uncefact:data:standard:ReusableAggregateBusinessInformationEntity:20");
xml = xml.replace("urn:un:unece:uncefact:data:standard:UnqualifiedDataType:15",
"urn:un:unece:uncefact:data:standard:UnqualifiedDataType:20");
xml = xml.replace("rsm:CrossIndustryDocument", "rsm:CrossIndustryInvoice");
xml = xml.replace("rsm:SpecifiedExchangedDocumentContext", "rsm:CIExchangedDocumentContext");
xml = xml.replace("rsm:HeaderExchangedDocument", "rsm:CIIHExchangedDocument");
xml = xml.replace("SpecifiedSupplyChainTradeTransaction", "CIIHSupplyChainTradeTransaction");
xml = xml.replace("ram:GuidelineSpecifiedDocumentContextParameter",
"ram:GuidelineSpecifiedCIDocumentContextParameter");
xml = xml.replace("ram:IncludedNote", "ram:IncludedCINote");
xml = xml.replace("ram:ApplicableSupplyChainTradeAgreement",
"ram:ApplicableCIIHSupplyChainTradeAgreement");
xml = xml.replace("ram:SellerTradeParty", "ram:SellerCITradeParty");
xml = xml.replace("ram:BuyerTradeParty", "ram:BuyerCITradeParty");
xml = xml.replace("ram:ApplicableSupplyChainTradeDelivery",
"ram:ApplicableCIIHSupplyChainTradeDelivery");
xml = xml.replace("ram:ApplicableSupplyChainTradeSettlement",
"ram:ApplicableCIIHSupplyChainTradeSettlement");
xml = xml.replace("ram:IncludedSupplyChainTradeLineItem", "ram:IncludedCIILSupplyChainTradeLineItem");
xml = xml.replace("ram:AssociatedDocumentLineDocument", "ram:AssociatedCIILDocumentLineDocument");
xml = xml.replace("ram:SpecifiedSupplyChainTradeDelivery", "ram:SpecifiedCIILSupplyChainTradeDelivery");
xml = xml.replace("ram:SpecifiedSupplyChainTradeSettlement",
"ram:SpecifiedCIILSupplyChainTradeSettlement");
xml = xml.replace("ram:SpecifiedTradeProduct", "ram:SpecifiedCITradeProduct");
xml = xml.replace("ram:ActualDeliverySupplyChainEvent", "ram:ActualDeliveryCISupplyChainEvent");
xml = xml.replace("ram:SpecifiedTradeSettlementPaymentMeans",
"ram:SpecifiedCITradeSettlementPaymentMeans");
xml = xml.replace("ram:PayeePartyCreditorFinancialAccount", "ram:PayeePartyCICreditorFinancialAccount");
xml = xml.replace("ram:PayeeSpecifiedCreditorFinancialInstitution",
"ram:PayeeSpecifiedCICreditorFinancialInstitution");
xml = xml.replace("ram:ApplicableTradeTax", "ram:ApplicableCITradeTax");
xml = xml.replace("ram:ApplicablePercent", "ram:RateApplicablePercent");
xml = xml.replace("ram:PostalTradeAddress", "ram:PostalCITradeAddress");
xml = xml.replace("ram:ApplicableTradePaymentDiscountTerms",
"ram:ApplicableCITradePaymentDiscountTerms");
xml = xml.replace("ram:ApplicableProductCharacteristic", "ram:ApplicableCIProductCharacteristic");
xml = xml.replace("ram:ShipToTradeParty", "ram:ShipToCITradeParty");
xml = xml.replace("ram:ShipFromTradeParty", "ram:ShipFromCITradeParty");
xml = xml.replace("ram:ReceivableSpecifiedTradeAccountingAccount",
"ram:ReceivableSpecifiedCITradeAccountingAccount");
xml = xml.replace("ram:ContractReferencedDocument", "ram:ContractReferencedCIReferencedDocument");
// "ram:SpecifiedTradeAccountingAccount ram:SalesSpecifiedTradeAccountingAccount
// oder ReceivablesSpecifiedTradeAccountingAccount oder
// PurchaseSpecifiedTradeAccountingAccount
xml = xml.replace("ram:AdditionalReferencedDocument", "ram:AdditionalReferencedCIReferencedDocument");
xml = xml.replace("ram:TelephoneUniversalCommunication", "ram:TelephoneCIUniversalCommunication");
xml = xml.replace("ram:EmailURIUniversalCommunication", "ram:EmailURICIUniversalCommunication");
xml = xml.replace("ram:AdditionalReferencedDocument", "ram:AdditionalReferencedCIReferencedDocument");
xml = xml.replace("ram:IncludedReferencedProduct", "ram:IncludedReferencedProduct");
xml = xml.replace("ram:DefinedTradeContact", "ram:DefinedCITradeContact");
xml = xml.replace("ram:BillingSpecifiedPeriod", "ram:BillingCISpecifiedPeriod");
xml = xml.replace("ram:BuyerOrderReferencedDocument", "ram:BuyerOrderReferencedCIReferencedDocument");
xml = xml.replace("ram:DeliveryNoteReferencedDocument",
"ram:DeliveryNoteReferencedCIReferencedDocument");
xml = xml.replace("ram:SpecifiedTradeAllowanceCharge", "ram:SpecifiedCITradeAllowanceCharge");
xml = xml.replace("ram:SpecifiedLogisticsServiceCharge", "ram:SpecifiedCILogisticsServiceCharge");
xml = xml.replace("ram:AppliedTradeAllowanceCharge", "ram:AppliedCITradeAllowanceCharge");
xml = xml.replace("ram:InvoiceeTradeParty", "ram:InvoiceeCITradeParty");
xml = xml.replace("ram:CategoryTradeTax", "ram:CategoryCITradeTax");
xml = xml.replace("ram:SpecifiedTaxRegistration", "ram:SpecifiedCITaxRegistration");
xml = xml.replace("ram:PostalTradeAddress", "ram:PostalCITradeAddress");
xml = xml.replace("ram:SpecifiedTradePaymentTerms", "ram:SpecifiedCITradePaymentTerms");
xml = xml.replace("ram:SpecifiedSupplyChainTradeAgreement",
"ram:SpecifiedCIILSupplyChainTradeAgreement");
xml = xml.replace("ram:GrossPriceProductTradePrice", "ram:GrossPriceProductCITradePrice");
xml = xml.replace("ram:NetPriceProductTradePrice", "ram:NetPriceProductCITradePrice");
xml = xml.replaceAll("(?s)\\<ram:TestIndicator.*\\/ram:TestIndicator>", "");
// remove manually for the time being:
// xml=xml.replaceAll("ram:TestIndicator>(.*?)/ram:TestIndicator>", "");
// one ram:SpecifiedCIILTradeSettlementMonetarySummation will have to be
// ram:SpecifiedCIIHTradeSettlementMonetarySummation afterwards
String summationClose = "</ram:SpecifiedTradeSettlementMonetarySummation>";
int posFirstSummation = xml.indexOf(summationClose) + summationClose.length();
// if ram:SpecifiedTradeSettlementMonetarySummation were not found indexOf would
// return -1, therefore,
// to check if it
if (posFirstSummation > summationClose.length()) {
String xmlAfterFirstSummation = xml.substring(posFirstSummation);
String xmlBeforeIncludingFirstSummation = xml.substring(0, posFirstSummation);
// replace only once the header
xmlBeforeIncludingFirstSummation = xmlBeforeIncludingFirstSummation.replace(
"ram:SpecifiedTradeSettlementMonetarySummation",
"ram:SpecifiedCIIHTradeSettlementMonetarySummation");
// reconstruct the document now with a replaced first
// ram:SpecifiedTradeSettlementMonetarySummation to SpecifiedCIIH...
xml = xmlBeforeIncludingFirstSummation + xmlAfterFirstSummation;
}
// replace the rest of the ram:SpecifiedTradeSettlementMonetarySummation with
// the line value SpecifiedCIIL...
xml = xml.replace("ram:SpecifiedTradeSettlementMonetarySummation",
"ram:SpecifiedCIILTradeSettlementMonetarySummation");
// the rest of the ram:SpecifiedTradeSettlementMonetarySummation should be in
// ram:ApplicableSupplyChainTradeSettlement
// xml=xml.replaceAll(Pattern.quote("ram:SpecifiedTradeSettlementMonetarySummation"),
// "ram:SpecifiedCIILTradeSettlementMonetarySummation");
Files.write(Paths.get("./ZUGFeRD-2-invoice.xml"), xml.getBytes());
} catch (IOException e) {
e.printStackTrace();
}
System.out.println("Written to ZUGFeRD-2-invoice.xml");
}
}
}

40
src/test/java/org/mustangproject/ZUGFeRD/MustangReaderWriterTest.java
View File

@@ -1,5 +1,6 @@
package org.mustangproject.ZUGFeRD;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.math.BigDecimal;
@@ -409,12 +410,16 @@ public class MustangReaderWriterTest extends TestCase implements IZUGFeRDExporta
this.getClass().getResourceAsStream("/MustangGnuaccountingBeispielRE-20170509_505blanko.pdf");
ZUGFeRDExporter ze = new ZUGFeRDExporterFromA1Factory()
.setProducer("My Application")
.setCreator(System.getProperty("user.name"))
.loadFromPDFA1(SOURCE_PDF)) {
ze.PDFattachZugferdFile(this);
ze.export(TARGET_PDF);
ByteArrayOutputStream baos=new ByteArrayOutputStream();
ze.export(baos);
String pdfContent=baos.toString("UTF-8");
assertFalse(pdfContent.indexOf("(via mustangproject.org")==-1);
}
// now check the contents (like MustangReaderTest)
@@ -446,4 +451,35 @@ public class MustangReaderWriterTest extends TestCase implements IZUGFeRDExporta
}
/**
* @Test(expected = IndexOutOfBoundsException.class)
* @throws Exception
*/
public void testExceptionOnPDF14() throws Exception
{
final String TARGET_PDF = "./target/testout-MustangGnuaccountingBeispielRE-20170509_505new.pdf";
boolean exceptionThrown=false;
// the writing part
try(InputStream SOURCE_PDF =
this.getClass().getResourceAsStream("/MustangGnuaccountingBeispielRE-20170509_505PDF14.pdf");
ZUGFeRDExporter ze = new ZUGFeRDExporterFromA1Factory()
.loadFromPDFA1(SOURCE_PDF)) {
ze.PDFattachZugferdFile(this);
ze.export(TARGET_PDF);
ByteArrayOutputStream baos=new ByteArrayOutputStream();
ze.export(baos);
} catch (IOException ex) {
// should throw a java.io.IOException: File is not a valid PDF/A-1 input file
exceptionThrown=true;
}
assertTrue(exceptionThrown);
}
}

BIN
src/test/resources/MustangGnuaccountingBeispielRE-20170509_505PDF14.pdf Normal file
View File

Binary file not shown.

BIN
src/test/resources/MustangGnuaccountingBeispielRE-20170509_505PDFA3.pdf Normal file
View File

Binary file not shown.