/*
* The Apache Software License, Version 1.1
*
*
* Copyright (c) 1999-2002 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Xerces" and "Apache Software Foundation" must
* not be used to endorse or promote products derived from this
* software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* nor may "Apache" appear in their name, without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation and was
* originally based on software copyright (c) 1999, International
* Business Machines, Inc., http://www.apache.org. For more
* information on the Apache Software Foundation, please see
* <http://www.apache.org/>.
*/
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import java.io.UnsupportedEncodingException;
import org.w3c.dom.Attr;
import org.w3c.dom.Document;
import org.w3c.dom.DocumentType;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import com.lowagie.text.pdf.ArabicShaping;
/**
* A sample DOM writer. This sample program illustrates how to
* traverse a DOM tree in order to print a document that is parsed.
*
* @author Andy Clark, IBM
*
* @version $Id: FoShaper.java,v 1.1.1.1 2004/05/05 11:15:41 gisadmin Exp $
*/
public class FoShaper {
//
// Constants
//
// feature ids
/** Namespaces feature id (http://xml.org/sax/features/namespaces). */
protected static final String NAMESPACES_FEATURE_ID = "http://xml.org/sax/features/namespaces";
/** Validation feature id (http://xml.org/sax/features/validation). */
protected static final String VALIDATION_FEATURE_ID = "http://xml.org/sax/features/validation";
/** Schema validation feature id (http://apache.org/xml/features/validation/schema). */
protected static final String SCHEMA_VALIDATION_FEATURE_ID = "http://apache.org/xml/features/validation/schema";
/** Schema full checking feature id (http://apache.org/xml/features/validation/schema-full-checking). */
protected static final String SCHEMA_FULL_CHECKING_FEATURE_ID = "http://apache.org/xml/features/validation/schema-full-checking";
// property ids
/** Lexical handler property id (http://xml.org/sax/properties/lexical-handler). */
protected static final String LEXICAL_HANDLER_PROPERTY_ID = "http://xml.org/sax/properties/lexical-handler";
// default settings
/** Default parser name. */
protected static final String DEFAULT_PARSER_NAME = "dom.wrappers.Xerces";
/** Default namespaces support (true). */
protected static final boolean DEFAULT_NAMESPACES = true;
/** Default validation support (false). */
protected static final boolean DEFAULT_VALIDATION = false;
/** Default Schema validation support (false). */
protected static final boolean DEFAULT_SCHEMA_VALIDATION = false;
/** Default Schema full checking support (false). */
protected static final boolean DEFAULT_SCHEMA_FULL_CHECKING = false;
/** Default canonical output (false). */
protected static final boolean DEFAULT_CANONICAL = false;
//
// Data
//
/** Print writer. */
protected PrintWriter fOut;
/** Canonical output. */
protected boolean fCanonical;
//
// Constructors
//
/** Default constructor. */
public FoShaper() {
} // <init>()
public FoShaper(boolean canonical) {
fCanonical = canonical;
} // <init>(boolean)
//
// Public methods
//
/** Sets whether output is canonical. */
public void setCanonical(boolean canonical) {
fCanonical = canonical;
} // setCanonical(boolean)
/** Sets the output stream for printing. */
public void setOutput(OutputStream stream, String encoding)
throws UnsupportedEncodingException {
if (encoding == null) {
encoding = "UTF8";
}
java.io.Writer writer = new OutputStreamWriter(stream, encoding);
fOut = new PrintWriter(writer);
} // setOutput(OutputStream,String)
/** Sets the output writer. */
public void setOutput(java.io.Writer writer) {
fOut = writer instanceof PrintWriter
? (PrintWriter)writer : new PrintWriter(writer);
} // setOutput(java.io.Writer)
/** Writes the specified node, recursively. */
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;
if (!fCanonical) {
fOut.println("<?xml version=\"1.0\" encoding=\"UTF-8\"?>");
fOut.flush();
write(document.getDoctype());
}
write(document.getDocumentElement());
break;
}
case Node.DOCUMENT_TYPE_NODE: {
DocumentType doctype = (DocumentType)node;
fOut.print("<!DOCTYPE ");
fOut.print(doctype.getName());
String publicId = doctype.getPublicId();
String systemId = doctype.getSystemId();
if (publicId != null) {
fOut.print(" PUBLIC '");
fOut.print(publicId);
fOut.print("' '");
fOut.print(systemId);
fOut.print('\'');
}
else {
fOut.print(" SYSTEM '");
fOut.print(systemId);
fOut.print('\'');
}
String internalSubset = doctype.getInternalSubset();
if (internalSubset != null) {
fOut.println(" [");
fOut.print(internalSubset);
fOut.print(']');
}
fOut.println('>');
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());
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());
}
else {
fOut.print("<![CDATA[");
fOut.print(node.getNodeValue());
fOut.print("]]>");
}
fOut.flush();
break;
}
case Node.TEXT_NODE: {
normalizeAndPrint(node.getNodeValue());
fOut.flush();
break;
}
case Node.PROCESSING_INSTRUCTION_NODE: {
fOut.print("<?");
fOut.print(node.getNodeName());
String data = node.getNodeValue();
if (data != null && data.length() > 0) {
fOut.print(' ');
fOut.print(data);
}
fOut.println("?>");
fOut.flush();
break;
}
}
if (type == Node.ELEMENT_NODE) {
fOut.print("</");
fOut.print(node.getNodeName());
fOut.print('>');
fOut.flush();
}
} // write(Node)
/** Returns 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. */
protected void normalizeAndPrint(String s) {
int len = (s != null) ? s.length() : 0;
for (int i = 0; i < len; i++) {
char c = s.charAt(i);
normalizeAndPrint(c);
}
} // normalizeAndPrint(String)
/** Normalizes and print the given character. */
protected void normalizeAndPrint(char c) {
switch (c) {
case '<': {
fOut.print("<");
break;
}
case '>': {
fOut.print(">");
break;
}
case '&': {
fOut.print("&");
break;
}
case '"': {
fOut.print(""");
break;
}
case '\r':
case '\n': {
if (fCanonical) {
fOut.print("&#");
fOut.print(Integer.toString(c));
fOut.print(';');
break;
}
// else, default print char
}
default: {
fOut.print(c);
}
}
} // normalizeAndPrint(char)
//
// Main
//
/** Main program entry point. */
public static void main(String argv[]) {
// is there anything to do?
if (argv.length == 0) {
printUsage();
System.exit(1);
}
// variables
FoShaper writer = null;
dom.ParserWrapper parser = null;
boolean namespaces = DEFAULT_NAMESPACES;
boolean validation = DEFAULT_VALIDATION;
boolean schemaValidation = DEFAULT_SCHEMA_VALIDATION;
boolean schemaFullChecking = DEFAULT_SCHEMA_FULL_CHECKING;
boolean canonical = DEFAULT_CANONICAL;
// process arguments
for (int i = 0; i < argv.length; i++) {
String arg = argv[i];
if (arg.startsWith("-")) {
String option = arg.substring(1);
if (option.equals("p")) {
// get parser name
if (++i == argv.length) {
System.err.println("error: Missing argument to -p option.");
}
String parserName = argv[i];
// create parser
try {
parser = (dom.ParserWrapper)Class.forName(parserName).newInstance();
}
catch (Exception e) {
parser = null;
System.err.println("error: Unable to instantiate parser ("+parserName+")");
}
continue;
}
if (option.equalsIgnoreCase("n")) {
namespaces = option.equals("n");
continue;
}
if (option.equalsIgnoreCase("v")) {
validation = option.equals("v");
continue;
}
if (option.equalsIgnoreCase("s")) {
schemaValidation = option.equals("s");
continue;
}
if (option.equalsIgnoreCase("f")) {
schemaFullChecking = option.equals("f");
continue;
}
if (option.equalsIgnoreCase("c")) {
canonical = option.equals("c");
continue;
}
if (option.equals("h")) {
printUsage();
continue;
}
}
// use default parser?
if (parser == null) {
// create parser
try {
parser = (dom.ParserWrapper)Class.forName(DEFAULT_PARSER_NAME).newInstance();
}
catch (Exception e) {
System.err.println("error: Unable to instantiate parser ("+DEFAULT_PARSER_NAME+")");
continue;
}
}
// set parser features
try {
parser.setFeature(NAMESPACES_FEATURE_ID, namespaces);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+NAMESPACES_FEATURE_ID+")");
}
try {
parser.setFeature(VALIDATION_FEATURE_ID, validation);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+VALIDATION_FEATURE_ID+")");
}
try {
parser.setFeature(SCHEMA_VALIDATION_FEATURE_ID, schemaValidation);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+SCHEMA_VALIDATION_FEATURE_ID+")");
}
try {
parser.setFeature(SCHEMA_FULL_CHECKING_FEATURE_ID, schemaFullChecking);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+SCHEMA_FULL_CHECKING_FEATURE_ID+")");
}
// setup writer
if (writer == null) {
writer = new FoShaper();
try {
writer.setOutput(System.out, "UTF8");
}
catch (UnsupportedEncodingException e) {
System.err.println("error: Unable to set output. Exiting.");
System.exit(1);
}
}
// parse file
writer.setCanonical(canonical);
try {
Document document = parser.parse(arg);
// begin changes
NodeList elements;
int elementCount;
Element element;
NodeList childs;
int childCount;
Node child;
int j;
int k;
int l;
int m;
int nameCount;
String reversed;
String value;
boolean inverse;
String nodeName;
ArabicShaping arabicshaper = new ArabicShaping(
ArabicShaping.LETTERS_SHAPE|
ArabicShaping.TEXT_DIRECTION_LOGICAL|
ArabicShaping.LENGTH_GROW_SHRINK);
String elementNames[] = {"fo:block", "fo:inline",
"fo:basic-link"};
//nameCount = elementNames.length();
nameCount = 3;
for(l = 0; l < nameCount; l++) {
elements = document.getElementsByTagName(elementNames[l]);
if (elements != null) {
elementCount = elements.getLength();
for (k = 0; k < elementCount; k++) {
element = (Element)elements.item(k);
element.setAttribute("direction", "rtl");
if(element.hasChildNodes()) {
childs = element.getChildNodes();
childCount = childs.getLength();
// check whether node only contains inline and link elements
inverse = true;
for (j = 0; j < childCount; j++) {
child = childs.item(j);
if(child.getNodeType() == Node.TEXT_NODE) {
if((child.getNodeValue().replaceAll(" ", "").length() > 1)) {
value = childs.item(j).getNodeValue();
value = arabicshaper.shape(value);
value = invertArabic(value);
/*reversed = "";
for(m = value.length()-1; m >= 0; m--) {
reversed += value.charAt(m);
}*/
childs.item(j).setNodeValue(value);
}
} else{
nodeName = child.getNodeName();
if((nodeName != "fo:inline")&&(nodeName != "fo:basic-link")) {
inverse = false;
}
}
}
if(inverse) {
for(j = childCount-2; j>=0; j--) {
child = element.removeChild(childs.item(j));
element.appendChild(child);
}
}
}
}
}
}
// end changes
writer.write(document);
}
catch (SAXParseException e) {
// ignore
}
catch (Exception e) {
System.err.println("error: Parse error occurred - "+e.getMessage());
if (e instanceof SAXException) {
e = ((SAXException)e).getException();
}
e.printStackTrace(System.err);
}
}
} // main(String[])
//
// Private static methods
//
/** Prints the usage. */
private static void printUsage() {
System.err.println("usage: java FoShaper (options) uri ...");
System.err.println();
System.err.println("options:");
System.err.println(" -p name Select parser by name.");
System.err.println(" -n | -N Turn on/off namespace processing.");
System.err.println(" -v | -V Turn on/off validation.");
System.err.println(" -s | -S Turn on/off Schema validation support.");
System.err.println(" NOTE: Not supported by all parsers.");
System.err.println(" -f | -F Turn on/off Schema full checking.");
System.err.println(" NOTE: Requires use of -s and not supported by all parsers.");
System.err.println(" -c | -C Turn on/off Canonical XML output.");
System.err.println(" NOTE: This is not W3C canonical output.");
System.err.println(" -h This help screen.");
System.err.println();
System.err.println("defaults:");
System.err.println(" Parser: "+DEFAULT_PARSER_NAME);
System.err.print(" Namespaces: ");
System.err.println(DEFAULT_NAMESPACES ? "on" : "off");
System.err.print(" Validation: ");
System.err.println(DEFAULT_VALIDATION ? "on" : "off");
System.err.print(" Schema: ");
System.err.println(DEFAULT_SCHEMA_VALIDATION ? "on" : "off");
System.err.print(" Schema full checking: ");
System.err.println(DEFAULT_SCHEMA_FULL_CHECKING ? "on" : "off");
System.err.print(" Canonical: ");
System.err.println(DEFAULT_CANONICAL ? "on" : "off");
} // printUsage()
private static String invertArabic(String arabic) {
if(arabic == "") {
return "";
}
StringBuffer buffer = new StringBuffer(arabic);
StringBuffer result = new StringBuffer();
int sectionCount = 0;
int i;
int offset = 0;
int bufferCount = buffer.length();
boolean toggleArabic = isArabicCharacter(buffer.charAt(0));
String reversed;
sectionCount = 0;
offset = 0;
bufferCount = buffer.length();
toggleArabic = isArabicCharacter(buffer.charAt(0));
while(sectionCount+offset < bufferCount) {
while((sectionCount+offset < bufferCount)&&
((toggleArabic == isArabicCharacter(buffer.charAt(sectionCount+offset)))||
((buffer.charAt(sectionCount+offset)) == 32))) {
sectionCount++;
}
if(toggleArabic) {
reversed = "";
for(i = sectionCount+offset-1; i >= offset; i--) {
reversed += buffer.charAt(i);
}
result.append(reversed);
toggleArabic = false;
} else {
result.append(buffer.substring(offset, sectionCount+offset));
toggleArabic = true;
}
offset += sectionCount;
sectionCount = 0;
}
return result.toString();
}
private static boolean isArabicCharacter(int c) {
if((c > 0xfe00)&&(c < 0xfeff)) {
return true;
} else {
return false;
}
}
} // class FoShaper