Package org.apache.xmpbox.xml

Class DomXmpParser

java.lang.Object

org.apache.xmpbox.xml.DomXmpParser

public class DomXmpParser
extends Object

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
protected static class	DomXmpParser.NamespaceFinder

Field Summary

Fields

Modifier and Type	Field	Description
private DocumentBuilder	dBuilder
private DomXmpParser.NamespaceFinder	nsFinder
private boolean	strictParsing

Constructor Summary

Constructors

Constructor	Description
DomXmpParser()

Method Summary

Modifier and Type	Method	Description
private PropertyType	checkPropertyDefinition(TypeMapping tm, QName qName, String parentTypeName)
private void	createProperty(XMPMetadata xmp, Element property, PropertyType type, ComplexPropertyContainer container)
private void	expectNaming(Element element, String ns, String prefix, String ln)
private Element	findDescriptionsParent(Element root)
private AbstractStructuredType	instanciateStructured(TypeMapping tm, Types type, String name, String structuredNamespace)
private boolean	isSchemaExtensionProperty(Element element)
boolean	isStrictParsing()	Tell if strict parsing mode is enabled.
private void	loadAttributes(AbstractField sp, Element element)
private void	manageArray(XMPMetadata xmp, Element property, PropertyType type, ComplexPropertyContainer container)
private void	manageDefinedType(XMPMetadata xmp, Element property, String prefix, ComplexPropertyContainer container)
private void	manageLangAlt(XMPMetadata xmp, Element property, ComplexPropertyContainer container)
private void	manageSimpleType(XMPMetadata xmp, Element property, Types type, ComplexPropertyContainer container)
private void	manageStructuredType(XMPMetadata xmp, Element property, String prefix, ComplexPropertyContainer container)
private void	maybeAddNonStandardNamespace(XMPMetadata xmp, Attr attr)
XMPMetadata	parse(byte[] xmp)
XMPMetadata	parse(InputStream input)
private void	parseChildrenAsProperties(XMPMetadata xmp, List<Element> properties, TypeMapping tm, Element description)
private void	parseDescriptionInner(XMPMetadata xmp, Element description, ComplexPropertyContainer parentContainer)
private void	parseDescriptionRoot(XMPMetadata xmp, Element description)
private void	parseDescriptionRootAttr(XMPMetadata xmp, Element description, Attr attr, TypeMapping tm)
private void	parseEndPacket(XMPMetadata metadata, ProcessingInstruction pi)
private XMPMetadata	parseInitialXpacket(ProcessingInstruction pi)
private AbstractStructuredType	parseLiDescription(XMPMetadata xmp, QName parentQName, Element liDescriptionElement)
private AbstractField	parseLiElement(XMPMetadata xmp, QName descriptor, Element liElement, Types type)
private void	parseSchemaExtensions(XMPMetadata xmp, Element description)
private void	removeCommentsAndBlanks(Node root)	Remove all the comments and blank nodes in the parent element of the parameter
void	setStrictParsing(boolean strictParsing)	Enable or disable strict parsing mode.
private AbstractStructuredType	tryParseAttributesAsProperties(TypeMapping tm, Element liElement, AbstractStructuredType ast, PropertiesDescription pm, QName qName)	This attempts to run the same logic as in parseLiDescription() but with simple attributes that will be treated like children.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Details

dBuilder

private DocumentBuilder dBuilder

nsFinder

private DomXmpParser.NamespaceFinder nsFinder

strictParsing

private boolean strictParsing

Constructor Details

DomXmpParser

public DomXmpParser()
             throws XmpParsingException

Throws:

XmpParsingException

Method Details

isStrictParsing

public boolean isStrictParsing()

Tell if strict parsing mode is enabled.

Returns:

Whether strict parsing mode is enabled or not.

setStrictParsing

public void setStrictParsing(boolean strictParsing)

Enable or disable strict parsing mode.

Parameters:

strictParsing - Whether to be strict or lenient when parsing XMP. True (the default) means that malformed XMP will result in an exception, false (lenient) means that if malformed content is encountered, the parser will continue its work if possible. Use strict mode if you want to work with PDF/A files. Use lenient mode if you care more about getting metadata.

parse

public XMPMetadata parse(byte[] xmp)
                  throws XmpParsingException

Throws:

XmpParsingException

parse

public XMPMetadata parse(InputStream input)
                  throws XmpParsingException

Throws:

XmpParsingException

maybeAddNonStandardNamespace

private void maybeAddNonStandardNamespace(XMPMetadata xmp,
 Attr attr)

isSchemaExtensionProperty

private boolean isSchemaExtensionProperty(Element element)

parseSchemaExtensions

private void parseSchemaExtensions(XMPMetadata xmp,
 Element description)
                            throws XmpParsingException

Throws:

XmpParsingException

parseDescriptionRoot

private void parseDescriptionRoot(XMPMetadata xmp,
 Element description)
                           throws XmpParsingException

Throws:

XmpParsingException

parseDescriptionRootAttr

private void parseDescriptionRootAttr(XMPMetadata xmp,
 Element description,
 Attr attr,
 TypeMapping tm)
                               throws XmpSchemaException,
XmpParsingException

Throws:

XmpSchemaException

XmpParsingException

parseChildrenAsProperties

private void parseChildrenAsProperties(XMPMetadata xmp,
 List<Element> properties,
 TypeMapping tm,
 Element description)
                                throws XmpParsingException,
XmpSchemaException

Throws:

XmpParsingException

XmpSchemaException

createProperty

private void createProperty(XMPMetadata xmp,
 Element property,
 PropertyType type,
 ComplexPropertyContainer container)
                     throws XmpParsingException

Throws:

XmpParsingException

manageDefinedType

private void manageDefinedType(XMPMetadata xmp,
 Element property,
 String prefix,
 ComplexPropertyContainer container)
                        throws XmpParsingException

Throws:

XmpParsingException

manageStructuredType

private void manageStructuredType(XMPMetadata xmp,
 Element property,
 String prefix,
 ComplexPropertyContainer container)
                           throws XmpParsingException

Throws:

XmpParsingException

manageSimpleType

private void manageSimpleType(XMPMetadata xmp,
 Element property,
 Types type,
 ComplexPropertyContainer container)

manageArray

private void manageArray(XMPMetadata xmp,
 Element property,
 PropertyType type,
 ComplexPropertyContainer container)
                  throws XmpParsingException

Throws:

XmpParsingException

manageLangAlt

private void manageLangAlt(XMPMetadata xmp,
 Element property,
 ComplexPropertyContainer container)
                    throws XmpParsingException

Throws:

XmpParsingException

parseDescriptionInner

private void parseDescriptionInner(XMPMetadata xmp,
 Element description,
 ComplexPropertyContainer parentContainer)
                            throws XmpParsingException

Throws:

XmpParsingException

parseLiElement

private AbstractField parseLiElement(XMPMetadata xmp,
 QName descriptor,
 Element liElement,
 Types type)
                              throws XmpParsingException

Throws:

XmpParsingException

loadAttributes

private void loadAttributes(AbstractField sp,
 Element element)

parseLiDescription

private AbstractStructuredType parseLiDescription(XMPMetadata xmp,
 QName parentQName,
 Element liDescriptionElement)
                                           throws XmpParsingException

Throws:

XmpParsingException

parseInitialXpacket

private XMPMetadata parseInitialXpacket(ProcessingInstruction pi)
                                 throws XmpParsingException

Throws:

XmpParsingException

parseEndPacket

private void parseEndPacket(XMPMetadata metadata,
 ProcessingInstruction pi)
                     throws XmpParsingException

Throws:

XmpParsingException

findDescriptionsParent

private Element findDescriptionsParent(Element root)
                                throws XmpParsingException

Throws:

XmpParsingException

expectNaming

private void expectNaming(Element element,
 String ns,
 String prefix,
 String ln)
                   throws XmpParsingException

Throws:

XmpParsingException

removeCommentsAndBlanks

private void removeCommentsAndBlanks(Node root)

Remove all the comments and blank nodes in the parent element of the parameter

Parameters:

root - the first node of an element or document to clear

instanciateStructured

private AbstractStructuredType instanciateStructured(TypeMapping tm,
 Types type,
 String name,
 String structuredNamespace)
                                              throws XmpParsingException

Throws:

XmpParsingException

checkPropertyDefinition

private PropertyType checkPropertyDefinition(TypeMapping tm,
 QName qName,
 String parentTypeName)
                                      throws XmpParsingException

Throws:

XmpParsingException

tryParseAttributesAsProperties

private AbstractStructuredType tryParseAttributesAsProperties(TypeMapping tm,
 Element liElement,
 AbstractStructuredType ast,
 PropertiesDescription pm,
 QName qName)
                                                       throws XmpParsingException

This attempts to run the same logic as in parseLiDescription() but with simple attributes that will be treated like children. This is inspired by loadAttributes() and parseDescriptionRootAttr(). This solves the problem in PDFBOX-3882 where properties appear as attributes in places lower than the descriptor root.

Parameters:

tm -

liElement -

ast - An AbstractStructuredType object, can be null.

pm - A PropertiesDescription object, must be set if ast is not null.

qName - QName of the parent, will be used if instantiating an AbstractStructuredType object, must be set if ast is not null.

Returns:

An AbstractStructuredType, possibly created here if it was null as parameter.

Throws:

XmpParsingException