com.itextpdf.kernel.xmp.XmlDomWriter Maven / Gradle / Ivy
/*
* Copyright 1999-2005 The Apache Software Foundation.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package com.itextpdf.kernel.xmp;
import org.w3c.dom.Attr;
import org.w3c.dom.Document;
import org.w3c.dom.DocumentType;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import java.nio.charset.Charset;
/**
* This class writes the DOM structure of the XML to the specified output.
*/
public class XmlDomWriter {
/**
* Print writer.
*/
protected PrintWriter fOut;
/**
* Canonical output.
*/
protected boolean fCanonical;
/**
* Processing XML 1.1 document.
*/
protected boolean fXML11;
//
// Constructors
//
/**
* Default constructor.
*/
public XmlDomWriter() {
} // ()
/**
* Creates an XmlDomWriter.
*
* @param canonical should the writer write canonical output or not
*/
public XmlDomWriter(boolean canonical) {
fCanonical = canonical;
} // (boolean)
//
// Public methods
//
/**
* Sets whether output is canonical.
*
* @param canonical should the writer write canonical output or not
*/
public void setCanonical(boolean canonical) {
fCanonical = canonical;
} // setCanonical(boolean)
/**
* Sets the output stream for printing.
*
* @param stream the {@link OutputStream} to which data will be written
* @param encoding output stream encoding
*/
public void setOutput(OutputStream stream, String encoding) {
if (encoding == null) {
encoding = "UTF8";
}
OutputStreamWriter osw = new OutputStreamWriter(stream, Charset.forName(encoding));
fOut = new PrintWriter(osw);
} // setOutput(OutputStream,String)
/**
* Writes the specified node, recursively.
*
* @param node the type of {@link Node} for writing
*/
public void write(Node node) {
// is there anything to do?
if (node == null) {
return;
}
short type = node.getNodeType();
switch (type) {
case Node.DOCUMENT_NODE: {
Document document = (Document) node;
fXML11 = false; //"1.1".equals(getVersion(document));
if (!fCanonical) {
if (fXML11) {
fOut.print("");
} else {
fOut.print("");
}
fOut.print("\n");
fOut.flush();
write(document.getDoctype());
}
write(document.getDocumentElement());
break;
}
case Node.DOCUMENT_TYPE_NODE: {
DocumentType doctype = (DocumentType) node;
fOut.print("');
fOut.print('\n');
break;
}
case Node.ELEMENT_NODE: {
fOut.print('<');
fOut.print(node.getNodeName());
Attr[] attrs = sortAttributes(node.getAttributes());
for (int i = 0; i < attrs.length; i++) {
Attr attr = attrs[i];
fOut.print(' ');
fOut.print(attr.getNodeName());
fOut.print("=\"");
normalizeAndPrint(attr.getNodeValue(), true);
fOut.print('"');
}
fOut.print('>');
fOut.flush();
Node child = node.getFirstChild();
while (child != null) {
write(child);
child = child.getNextSibling();
}
break;
}
case Node.ENTITY_REFERENCE_NODE: {
if (fCanonical) {
Node child = node.getFirstChild();
while (child != null) {
write(child);
child = child.getNextSibling();
}
} else {
fOut.print('&');
fOut.print(node.getNodeName());
fOut.print(';');
fOut.flush();
}
break;
}
case Node.CDATA_SECTION_NODE: {
if (fCanonical) {
normalizeAndPrint(node.getNodeValue(), false);
} else {
fOut.print("");
}
fOut.flush();
break;
}
case Node.TEXT_NODE: {
normalizeAndPrint(node.getNodeValue(), false);
fOut.flush();
break;
}
case Node.PROCESSING_INSTRUCTION_NODE: {
fOut.print(" 0) {
fOut.print(' ');
fOut.print(data);
}
fOut.print("?>");
fOut.flush();
break;
}
case Node.COMMENT_NODE: {
if (!fCanonical) {
fOut.print("");
fOut.flush();
}
}
}
if (type == Node.ELEMENT_NODE) {
fOut.print("');
fOut.flush();
}
} // write(Node)
/**
* Returns a sorted list of attributes.
*
* @param attrs objects implementing {@link NamedNodeMap} that will be sorted
* @return a sorted list of attributes
*/
protected Attr[] sortAttributes(NamedNodeMap attrs) {
int len = (attrs != null) ? attrs.getLength() : 0;
Attr[] array = new Attr[len];
for (int i = 0; i < len; i++) {
array[i] = (Attr) attrs.item(i);
}
for (int i = 0; i < len - 1; i++) {
String name = array[i].getNodeName();
int index = i;
for (int j = i + 1; j < len; j++) {
String curName = array[j].getNodeName();
if (curName.compareTo(name) < 0) {
name = curName;
index = j;
}
}
if (index != i) {
Attr temp = array[i];
array[i] = array[index];
array[index] = temp;
}
}
return array;
} // sortAttributes(NamedNodeMap):Attr[]
//
// Protected methods
//
/**
* Normalizes and prints the given string.
*
* @param s the {@link String} that should be printed
* @param isAttValue this flag determines whether some characters will be escaped
*/
protected void normalizeAndPrint(String s, boolean isAttValue) {
int len = (s != null) ? s.length() : 0;
for (int i = 0; i < len; i++) {
char c = s.charAt(i);
normalizeAndPrint(c, isAttValue);
}
} // normalizeAndPrint(String,boolean)
/**
* Normalizes and print the given character.
*
* @param c character that should be printed
* @param isAttValue this flag determines whether some characters will be escaped
*/
protected void normalizeAndPrint(char c, boolean isAttValue) {
switch (c) {
case '<': {
fOut.print("<");
break;
}
case '>': {
fOut.print(">");
break;
}
case '&': {
fOut.print("&");
break;
}
case '"': {
// A '"' that appears in character data
// does not need to be escaped.
if (isAttValue) {
fOut.print(""");
} else {
fOut.print("\"");
}
break;
}
case '\r': {
// If CR is part of the document's content, it
// must not be printed as a literal otherwise
// it would be normalized to LF when the document
// is reparsed.
fOut.print("
");
break;
}
case '\n': {
if (fCanonical) {
fOut.print("
");
break;
}
// else, default print char
}
default: {
// In XML 1.1, control chars in the ranges [#x1-#x1F, #x7F-#x9F] must be escaped.
//
// Escape space characters that would be normalized to #x20 in attribute values
// when the document is reparsed.
//
// Escape NEL (0x85) and LSEP (0x2028) that appear in content
// if the document is XML 1.1, since they would be normalized to LF
// when the document is reparsed.
if (fXML11 && ((c >= 0x01 && c <= 0x1F && c != 0x09 && c != 0x0A)
|| (c >= 0x7F && c <= 0x9F) || c == 0x2028)
|| isAttValue && (c == 0x09 || c == 0x0A)) {
fOut.print("&#x");
fOut.print(Integer.toHexString(c).toUpperCase());
fOut.print(";");
} else {
fOut.print(c);
}
}
}
}
}