September 21, 2024
May 13, 2022
DocumentBuilderFactory (Java SE 22 & JDK 22) with Examples.
You will find code examples on most DocumentBuilderFactory methods.
Summary
Defines a factory API that enables applications to obtain a parser that produces DOM object trees from XML documents.
final var xml = """
<root>
<child-a>AAA</child-a>
<child-b>BBB</child-b>
</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var childA = document.getElementsByTagName("child-a").item(0);
System.out.println(childA); // [child-a: null]
System.out.println(childA.getTextContent()); // AAA
final var childB = document.getElementsByTagName("child-b").item(0);
System.out.println(childB); // [child-b: null]
System.out.println(childB.getTextContent()); // BBB
Please see also the link below.
XML processing can expose applications to certain vulnerabilities. Among the most prominent and well-known attacks are the XML External Entity (XXE) injection attack and the exponential entity expansion attack, also know as the XML bomb or billion laughs attack.
Constructors
DocumentBuilderFactory ()
Protected constructor to prevent instantiation.
protected. I think it's rare to create a subclass of this class. Therefore, the code example is omitted.
Methods
abstract Object getAttribute (String name)
Allows the user to retrieve specific attributes on the underlying implementation.
final var dtdFile = Path.of("R:", "java-work", "sample.dtd");
System.out.println(dtdFile); // R:\java-work\sample.dtd
Files.writeString(dtdFile, """
<!ENTITY aaa "bbb">
""");
final var xml = """
<!DOCTYPE root SYSTEM "file:///R:/java-work/sample.dtd">
<root>&aaa;</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
factory.setAttribute(XMLConstants.ACCESS_EXTERNAL_DTD, "all");
final var ret = factory.getAttribute(XMLConstants.ACCESS_EXTERNAL_DTD);
System.out.println(ret); // "all"
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
System.out.println(root.getTextContent()); // bbb
}
{
factory.setAttribute(XMLConstants.ACCESS_EXTERNAL_DTD, "");
final var ret = factory.getAttribute(XMLConstants.ACCESS_EXTERNAL_DTD);
System.out.println(ret); // ""
final var builder = factory.newDocumentBuilder();
try {
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
} catch (SAXException e) {
System.out.println(e);
}
// Result
// ↓
//org.xml.sax.SAXParseException; lineNumber: 1; columnNumber: 57; External DTD:
// Failed to read external DTD 'sample.dtd', because 'file' access is not allowed due to
// restriction set by the accessExternalDTD property.
}
abstract boolean getFeature (String name)
Get the state of the named feature.
// An example of the exponential entity expansion attack.
final var xml = """
<!DOCTYPE root[
<!ENTITY x100 "X">
<!ENTITY x99 "&x100;&x100;">
<!ENTITY x98 "&x99;&x99;">
...
(omitted)
...
<!ENTITY x3 "&x4;&x4;">
<!ENTITY x2 "&x3;&x3;">
<!ENTITY x1 "&x2;&x2;">
]>
<root>&x1;</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.getFeature(XMLConstants.FEATURE_SECURE_PROCESSING);
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
try {
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
} catch (SAXException e) {
System.out.println(e);
}
// Result
// ↓
//org.xml.sax.SAXParseException; lineNumber: 1; columnNumber: 1; JAXP00010001:
// The parser has encountered more than "64000" entity expansions in this document;
// this is the limit imposed by the JDK.
}
factory.setFeature(XMLConstants.FEATURE_SECURE_PROCESSING, false);
{
final var ret = factory.getFeature(XMLConstants.FEATURE_SECURE_PROCESSING);
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
// Warning! Entities are growing exponentially, so parsing it takes a very long time.
//final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
}
Schema getSchema ()
Gets the Schema object specified through the setSchema(Schema schema) method.
final var xsd = """
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:element name="root" type="xsd:string"/>
</xsd:schema>
""";
final var schemaFactory = SchemaFactory.newDefaultInstance();
final var schema = schemaFactory.newSchema(
new StreamSource(new ByteArrayInputStream(xsd.getBytes())));
final var factory = DocumentBuilderFactory.newInstance();
System.out.println(factory.getSchema()); // null
factory.setSchema(schema);
System.out.println(factory.getSchema().equals(schema)); // true
final var errorHandler = new DefaultHandler() {
@Override
public void error(SAXParseException e) {
System.out.println("-- ErrorHandler error --");
System.out.println(e);
}
};
{
final var xml = """
<root>abcd</root>
""";
final var builder = factory.newDocumentBuilder();
builder.setErrorHandler(errorHandler);
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
System.out.println(root.getTextContent()); // abcd
}
{
final var xml = """
<root><child>abcd</child></root>
""";
final var builder = factory.newDocumentBuilder();
builder.setErrorHandler(errorHandler);
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
// Result
// ↓
//-- ErrorHandler error --
//org.xml.sax.SAXParseException; lineNumber: 1; columnNumber: 33; cvc-type.3.1.2:
// Element 'root' is a simple type, so it must have no element information item [children].
}
boolean isCoalescing ()
Indicates whether or not the factory is configured to produce parsers which converts CDATA nodes to Text nodes and appends it to the adjacent (if any) Text node.
final var xml = """
<root>aaa<![CDATA[<&>]]></root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.isCoalescing();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
final var nodes = root.getChildNodes();
System.out.println("-- nodes --");
for (int i = 0; i < nodes.getLength(); i++) {
System.out.println(nodes.item(i));
}
// Result
// ↓
//-- nodes --
//[#text: aaa]
//[#cdata-section: <&>]
}
factory.setCoalescing(true);
{
final var ret = factory.isCoalescing();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
final var nodes = root.getChildNodes();
System.out.println("-- nodes --");
for (int i = 0; i < nodes.getLength(); i++) {
System.out.println(nodes.item(i));
}
// Result
// ↓
//-- nodes --
//[#text: aaa<&>]
}
boolean isExpandEntityReferences ()
Indicates whether or not the factory is configured to produce parsers which expand entity reference nodes.
final var xml = """
<!DOCTYPE root [
<!ENTITY aaa "bbb">
]>
<root>&aaa;</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.isExpandEntityReferences();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
final var child = root.getFirstChild();
System.out.println(child); // [#text: bbb]
}
factory.setExpandEntityReferences(false);
{
final var ret = factory.isExpandEntityReferences();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
if (root.getFirstChild() instanceof EntityReference entityReference) {
System.out.println(entityReference); // [aaa: null]
}
}
boolean isIgnoringComments ()
Indicates whether or not the factory is configured to produce parsers which ignores comments.
final var xml = """
<root>aaa<!--bbb--></root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.isIgnoringComments();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
final var nodes = root.getChildNodes();
System.out.println("-- nodes --");
for (int i = 0; i < nodes.getLength(); i++) {
System.out.println(nodes.item(i));
}
// Result
// ↓
//-- nodes --
//[#text: aaa]
//[#comment: bbb]
}
factory.setIgnoringComments(true);
{
final var ret = factory.isIgnoringComments();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
final var nodes = root.getChildNodes();
System.out.println("-- nodes --");
for (int i = 0; i < nodes.getLength(); i++) {
System.out.println(nodes.item(i));
}
// Result
// ↓
//-- nodes --
//[#text: aaa]
}
boolean isIgnoringElementContentWhitespace ()
Indicates whether or not the factory is configured to produce parsers which ignore ignorable whitespace in element content.
final var xml = """
<!DOCTYPE root [
<!ELEMENT child-a (dummy?)>
<!ELEMENT child-b (#PCDATA)>
]>
<root>
<child-a> </child-a>
<child-b> </child-b>
</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.isIgnoringElementContentWhitespace();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var childA = document.getElementsByTagName("child-a").item(0);
System.out.println(childA); // [child-a: null]
final var childB = document.getElementsByTagName("child-b").item(0);
System.out.println(childB); // [child-b: null]
System.out.println(childA.getFirstChild()); // [#text: ]
System.out.println(childB.getFirstChild()); // [#text: ]
}
factory.setIgnoringElementContentWhitespace(true);
{
final var ret = factory.isIgnoringElementContentWhitespace();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var childA = document.getElementsByTagName("child-a").item(0);
System.out.println(childA); // [child-a: null]
final var childB = document.getElementsByTagName("child-b").item(0);
System.out.println(childB); // [child-b: null]
System.out.println(childA.getFirstChild()); // null
System.out.println(childB.getFirstChild()); // [#text: ]
}
boolean isNamespaceAware ()
Indicates whether or not the factory is configured to produce parsers which are namespace aware.
final var xml = """
<ns:root xmlns:ns="sample">
<ns:child/>
</ns:root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.isNamespaceAware();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var child = document.getElementsByTagNameNS("sample", "child").item(0);
System.out.println(child); // null
}
factory.setNamespaceAware(true);
{
final var ret = factory.isNamespaceAware();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var child = document.getElementsByTagNameNS("sample", "child").item(0);
System.out.println(child); // [ns:child: null]
}
boolean isValidating ()
Indicates whether or not the factory is configured to produce parsers which validate the XML content during parse.
// The XML document intentionally does not match the DTD.
final var xml = """
<!DOCTYPE root [
<!ELEMENT root (child-a)>
]>
<root><child-z/></root>
""";
final var factory = DocumentBuilderFactory.newInstance();
final var errorHandler = new DefaultHandler() {
@Override
public void error(SAXParseException e) {
System.out.println("-- ErrorHandler error --");
System.out.println(e);
}
};
{
final var ret = factory.isValidating();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
builder.setErrorHandler(errorHandler);
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var childZ = document.getElementsByTagName("child-z").item(0);
System.out.println(childZ); // [child-z: null]
}
factory.setValidating(true);
{
final var ret = factory.isValidating();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
builder.setErrorHandler(errorHandler);
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
// Result
// ↓
//-- ErrorHandler error --
//org.xml.sax.SAXParseException; lineNumber: 4; columnNumber: 17;
// Element type "child-z" must be declared.
//-- ErrorHandler error --
//org.xml.sax.SAXParseException; lineNumber: 4; columnNumber: 24;
// The content of element type "root" must match "(child-a)".
}
boolean isXIncludeAware ()
Get state of XInclude processing.
final var sampleFile = Path.of("R:", "java-work", "sample.xml");
System.out.println(sampleFile); // R:\java-work\sample.xml
Files.writeString(sampleFile, """
<child>abcd</child>
""");
final var xml = """
<root xmlns:xi="http://www.w3.org/2001/XInclude">
<xi:include href="file:///R:/java-work/sample.xml" parse="xml" />
</root>
""";
final var factory = DocumentBuilderFactory.newNSInstance();
{
final var ret = factory.isXIncludeAware();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var nodes = document.getElementsByTagName("child");
System.out.println(nodes.getLength()); // 0
}
factory.setXIncludeAware(true);
{
final var ret = factory.isXIncludeAware();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var child = document.getElementsByTagName("child").item(0);
System.out.println(child); // [child: null]
System.out.println(child.getTextContent()); // abcd
}
static DocumentBuilderFactory newDefaultInstance ()
Creates a new instance of the DocumentBuilderFactory builtin system-default implementation.
final var xml = """
<root>
<child-a>AAA</child-a>
<child-b>BBB</child-b>
</root>
""";
final var factory = DocumentBuilderFactory.newDefaultInstance();
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var childA = document.getElementsByTagName("child-a").item(0);
System.out.println(childA); // [child-a: null]
System.out.println(childA.getTextContent()); // AAA
final var childB = document.getElementsByTagName("child-b").item(0);
System.out.println(childB); // [child-b: null]
System.out.println(childB.getTextContent()); // BBB
static DocumentBuilderFactory newDefaultNSInstance ()
Creates a new NamespaceAware instance of the DocumentBuilderFactory builtin system-default implementation.
final var nsFactory = DocumentBuilderFactory.newDefaultNSInstance();
System.out.println(nsFactory.isNamespaceAware()); // true
final var factory = DocumentBuilderFactory.newDefaultInstance();
System.out.println(factory.isNamespaceAware()); // false
abstract DocumentBuilder newDocumentBuilder ()
Creates a new instance of a DocumentBuilder using the currently configured parameters.
final var xml = """
<root>
<child-a>AAA</child-a>
<child-b>BBB</child-b>
</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var childA = document.getElementsByTagName("child-a").item(0);
System.out.println(childA); // [child-a: null]
System.out.println(childA.getTextContent()); // AAA
final var childB = document.getElementsByTagName("child-b").item(0);
System.out.println(childB); // [child-b: null]
System.out.println(childB.getTextContent()); // BBB
static DocumentBuilderFactory newInstance ()
Obtains a new instance of a DocumentBuilderFactory.
final var xml = """
<root>
<child-a>AAA</child-a>
<child-b>BBB</child-b>
</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var childA = document.getElementsByTagName("child-a").item(0);
System.out.println(childA); // [child-a: null]
System.out.println(childA.getTextContent()); // AAA
final var childB = document.getElementsByTagName("child-b").item(0);
System.out.println(childB); // [child-b: null]
System.out.println(childB.getTextContent()); // BBB
static DocumentBuilderFactory newInstance (String factoryClassName, ClassLoader classLoader)
Obtain a new instance of a DocumentBuilderFactory from class name.
This method is probably for third party libraries. Therefore, the code example is omitted.
static DocumentBuilderFactory newNSInstance ()
Creates a new NamespaceAware instance of a DocumentBuilderFactory.
final var nsFactory = DocumentBuilderFactory.newNSInstance();
System.out.println(nsFactory.isNamespaceAware()); // true
final var factory = DocumentBuilderFactory.newInstance();
System.out.println(factory.isNamespaceAware()); // false
static DocumentBuilderFactory newNSInstance (String factoryClassName, ClassLoader classLoader)
Creates a new NamespaceAware instance of a DocumentBuilderFactory from the class name.
This method is probably for third party libraries. Therefore, the code example is omitted.
abstract void setAttribute (String name, Object value)
Allows the user to set specific attributes on the underlying implementation.
final var dtdFile = Path.of("R:", "java-work", "sample.dtd");
System.out.println(dtdFile); // R:\java-work\sample.dtd
Files.writeString(dtdFile, """
<!ENTITY aaa "bbb">
""");
final var xml = """
<!DOCTYPE root SYSTEM "file:///R:/java-work/sample.dtd">
<root>&aaa;</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
factory.setAttribute(XMLConstants.ACCESS_EXTERNAL_DTD, "all");
final var ret = factory.getAttribute(XMLConstants.ACCESS_EXTERNAL_DTD);
System.out.println(ret); // "all"
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
System.out.println(root.getTextContent()); // bbb
}
{
factory.setAttribute(XMLConstants.ACCESS_EXTERNAL_DTD, "");
final var ret = factory.getAttribute(XMLConstants.ACCESS_EXTERNAL_DTD);
System.out.println(ret); // ""
final var builder = factory.newDocumentBuilder();
try {
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
} catch (SAXException e) {
System.out.println(e);
}
// Result
// ↓
//org.xml.sax.SAXParseException; lineNumber: 1; columnNumber: 57; External DTD:
// Failed to read external DTD 'sample.dtd', because 'file' access is not allowed due to
// restriction set by the accessExternalDTD property.
}
void setCoalescing (boolean coalescing)
Specifies that the parser produced by this code will convert CDATA nodes to Text nodes and append it to the adjacent (if any) text node.
final var xml = """
<root>aaa<![CDATA[<&>]]></root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.isCoalescing();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
final var nodes = root.getChildNodes();
System.out.println("-- nodes --");
for (int i = 0; i < nodes.getLength(); i++) {
System.out.println(nodes.item(i));
}
// Result
// ↓
//-- nodes --
//[#text: aaa]
//[#cdata-section: <&>]
}
factory.setCoalescing(true);
{
final var ret = factory.isCoalescing();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
final var nodes = root.getChildNodes();
System.out.println("-- nodes --");
for (int i = 0; i < nodes.getLength(); i++) {
System.out.println(nodes.item(i));
}
// Result
// ↓
//-- nodes --
//[#text: aaa<&>]
}
void setExpandEntityReferences (boolean expandEntityRef)
Specifies that the parser produced by this code will expand entity reference nodes.
final var xml = """
<!DOCTYPE root [
<!ENTITY aaa "bbb">
]>
<root>&aaa;</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.isExpandEntityReferences();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
final var child = root.getFirstChild();
System.out.println(child); // [#text: bbb]
}
factory.setExpandEntityReferences(false);
{
final var ret = factory.isExpandEntityReferences();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
if (root.getFirstChild() instanceof EntityReference entityReference) {
System.out.println(entityReference); // [aaa: null]
}
}
abstract void setFeature (String name, boolean value)
Set a feature for this DocumentBuilderFactory and DocumentBuilders created by this factory.
// An example of the exponential entity expansion attack.
final var xml = """
<!DOCTYPE root[
<!ENTITY x100 "X">
<!ENTITY x99 "&x100;&x100;">
<!ENTITY x98 "&x99;&x99;">
...
(omitted)
...
<!ENTITY x3 "&x4;&x4;">
<!ENTITY x2 "&x3;&x3;">
<!ENTITY x1 "&x2;&x2;">
]>
<root>&x1;</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.getFeature(XMLConstants.FEATURE_SECURE_PROCESSING);
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
try {
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
} catch (SAXException e) {
System.out.println(e);
}
// Result
// ↓
//org.xml.sax.SAXParseException; lineNumber: 1; columnNumber: 1; JAXP00010001:
// The parser has encountered more than "64000" entity expansions in this document;
// this is the limit imposed by the JDK.
}
factory.setFeature(XMLConstants.FEATURE_SECURE_PROCESSING, false);
{
final var ret = factory.getFeature(XMLConstants.FEATURE_SECURE_PROCESSING);
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
// Warning! Entities are growing exponentially, so parsing it takes a very long time.
//final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
}
void setIgnoringComments (boolean ignoreComments)
Specifies that the parser produced by this code will ignore comments.
final var xml = """
<root>aaa<!--bbb--></root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.isIgnoringComments();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
final var nodes = root.getChildNodes();
System.out.println("-- nodes --");
for (int i = 0; i < nodes.getLength(); i++) {
System.out.println(nodes.item(i));
}
// Result
// ↓
//-- nodes --
//[#text: aaa]
//[#comment: bbb]
}
factory.setIgnoringComments(true);
{
final var ret = factory.isIgnoringComments();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
final var nodes = root.getChildNodes();
System.out.println("-- nodes --");
for (int i = 0; i < nodes.getLength(); i++) {
System.out.println(nodes.item(i));
}
// Result
// ↓
//-- nodes --
//[#text: aaa]
}
void setIgnoringElementContentWhitespace (boolean whitespace)
Specifies that the parsers created by this factory must eliminate whitespace in element content (sometimes known loosely as 'ignorable whitespace') when parsing XML documents (see XML Rec 2.10).
final var xml = """
<!DOCTYPE root [
<!ELEMENT child-a (dummy?)>
<!ELEMENT child-b (#PCDATA)>
]>
<root>
<child-a> </child-a>
<child-b> </child-b>
</root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.isIgnoringElementContentWhitespace();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var childA = document.getElementsByTagName("child-a").item(0);
System.out.println(childA); // [child-a: null]
final var childB = document.getElementsByTagName("child-b").item(0);
System.out.println(childB); // [child-b: null]
System.out.println(childA.getFirstChild()); // [#text: ]
System.out.println(childB.getFirstChild()); // [#text: ]
}
factory.setIgnoringElementContentWhitespace(true);
{
final var ret = factory.isIgnoringElementContentWhitespace();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var childA = document.getElementsByTagName("child-a").item(0);
System.out.println(childA); // [child-a: null]
final var childB = document.getElementsByTagName("child-b").item(0);
System.out.println(childB); // [child-b: null]
System.out.println(childA.getFirstChild()); // null
System.out.println(childB.getFirstChild()); // [#text: ]
}
void setNamespaceAware (boolean awareness)
Specifies that the parser produced by this code will provide support for XML namespaces.
final var xml = """
<ns:root xmlns:ns="sample">
<ns:child/>
</ns:root>
""";
final var factory = DocumentBuilderFactory.newInstance();
{
final var ret = factory.isNamespaceAware();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var child = document.getElementsByTagNameNS("sample", "child").item(0);
System.out.println(child); // null
}
factory.setNamespaceAware(true);
{
final var ret = factory.isNamespaceAware();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var child = document.getElementsByTagNameNS("sample", "child").item(0);
System.out.println(child); // [ns:child: null]
}
void setSchema (Schema schema)
Set the Schema to be used by parsers created from this factory.
final var xsd = """
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:element name="root" type="xsd:string"/>
</xsd:schema>
""";
final var schemaFactory = SchemaFactory.newDefaultInstance();
final var schema = schemaFactory.newSchema(
new StreamSource(new ByteArrayInputStream(xsd.getBytes())));
final var factory = DocumentBuilderFactory.newInstance();
System.out.println(factory.getSchema()); // null
factory.setSchema(schema);
System.out.println(factory.getSchema().equals(schema)); // true
final var errorHandler = new DefaultHandler() {
@Override
public void error(SAXParseException e) {
System.out.println("-- ErrorHandler error --");
System.out.println(e);
}
};
{
final var xml = """
<root>abcd</root>
""";
final var builder = factory.newDocumentBuilder();
builder.setErrorHandler(errorHandler);
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var root = document.getDocumentElement();
System.out.println(root); // [root: null]
System.out.println(root.getTextContent()); // abcd
}
{
final var xml = """
<root><child>abcd</child></root>
""";
final var builder = factory.newDocumentBuilder();
builder.setErrorHandler(errorHandler);
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
// Result
// ↓
//-- ErrorHandler error --
//org.xml.sax.SAXParseException; lineNumber: 1; columnNumber: 33; cvc-type.3.1.2:
// Element 'root' is a simple type, so it must have no element information item [children].
}
void setValidating (boolean validating)
Specifies that the parser produced by this code will validate documents as they are parsed.
// The XML document intentionally does not match the DTD.
final var xml = """
<!DOCTYPE root [
<!ELEMENT root (child-a)>
]>
<root><child-z/></root>
""";
final var factory = DocumentBuilderFactory.newInstance();
final var errorHandler = new DefaultHandler() {
@Override
public void error(SAXParseException e) {
System.out.println("-- ErrorHandler error --");
System.out.println(e);
}
};
{
final var ret = factory.isValidating();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
builder.setErrorHandler(errorHandler);
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var childZ = document.getElementsByTagName("child-z").item(0);
System.out.println(childZ); // [child-z: null]
}
factory.setValidating(true);
{
final var ret = factory.isValidating();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
builder.setErrorHandler(errorHandler);
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
// Result
// ↓
//-- ErrorHandler error --
//org.xml.sax.SAXParseException; lineNumber: 4; columnNumber: 17;
// Element type "child-z" must be declared.
//-- ErrorHandler error --
//org.xml.sax.SAXParseException; lineNumber: 4; columnNumber: 24;
// The content of element type "root" must match "(child-a)".
}
void setXIncludeAware (boolean state)
Set state of XInclude processing.
final var sampleFile = Path.of("R:", "java-work", "sample.xml");
System.out.println(sampleFile); // R:\java-work\sample.xml
Files.writeString(sampleFile, """
<child>abcd</child>
""");
final var xml = """
<root xmlns:xi="http://www.w3.org/2001/XInclude">
<xi:include href="file:///R:/java-work/sample.xml" parse="xml" />
</root>
""";
final var factory = DocumentBuilderFactory.newNSInstance();
{
final var ret = factory.isXIncludeAware();
System.out.println(ret); // false
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var nodes = document.getElementsByTagName("child");
System.out.println(nodes.getLength()); // 0
}
factory.setXIncludeAware(true);
{
final var ret = factory.isXIncludeAware();
System.out.println(ret); // true
final var builder = factory.newDocumentBuilder();
final var document = builder.parse(new ByteArrayInputStream(xml.getBytes()));
final var child = document.getElementsByTagName("child").item(0);
System.out.println(child); // [child: null]
System.out.println(child.getTextContent()); // abcd
}