[14053] | 1 | package org.greenstone.gatherer.util;
|
---|
| 2 |
|
---|
| 3 |
|
---|
| 4 | import java.io.*;
|
---|
| 5 | import java.net.*;
|
---|
| 6 | import java.util.*;
|
---|
| 7 | import org.apache.xerces.parsers.*;
|
---|
| 8 | import org.apache.xml.serialize.*;
|
---|
| 9 | import org.greenstone.gatherer.DebugStream;
|
---|
| 10 | import org.w3c.dom.*;
|
---|
| 11 | import org.xml.sax.*;
|
---|
| 12 |
|
---|
| 13 | import java.io.FileReader;
|
---|
| 14 | import java.io.IOException;
|
---|
| 15 | import java.io.StringReader;
|
---|
| 16 |
|
---|
| 17 | // SAX
|
---|
| 18 | import org.xml.sax.XMLReader;
|
---|
| 19 | import org.xml.sax.SAXException;
|
---|
| 20 | import org.xml.sax.SAXParseException;
|
---|
| 21 | import org.xml.sax.helpers.DefaultHandler;
|
---|
| 22 | import org.xml.sax.InputSource;
|
---|
| 23 |
|
---|
| 24 | // JAXP
|
---|
| 25 | import javax.xml.parsers.FactoryConfigurationError;
|
---|
| 26 | import javax.xml.parsers.ParserConfigurationException;
|
---|
| 27 | import javax.xml.parsers.SAXParser;
|
---|
| 28 | import javax.xml.parsers.SAXParserFactory;
|
---|
| 29 |
|
---|
| 30 | /** This class is a static class containing useful XML functions */
|
---|
| 31 | public class XMLTools {
|
---|
| 32 | /** extracts the text out of a node */
|
---|
| 33 | public static Node getNodeTextNode (Element param) {
|
---|
| 34 | param.normalize ();
|
---|
| 35 | Node n = param.getFirstChild ();
|
---|
| 36 | while (n!=null && n.getNodeType () !=Node.TEXT_NODE) {
|
---|
| 37 | n=n.getNextSibling ();
|
---|
| 38 | }
|
---|
| 39 | return n;
|
---|
| 40 | }
|
---|
| 41 |
|
---|
| 42 | /** extracts the text out of a node */
|
---|
| 43 | public static String getNodeText (Element param) {
|
---|
| 44 | Node text_node = getNodeTextNode (param);
|
---|
| 45 | if (text_node == null) {
|
---|
| 46 | return "";
|
---|
| 47 | }
|
---|
| 48 | return text_node.getNodeValue ();
|
---|
| 49 | }
|
---|
| 50 | public static void setNodeText (Element elem, String text) {
|
---|
| 51 | Node old_text_node = getNodeTextNode (elem);
|
---|
| 52 | if (old_text_node != null) {
|
---|
| 53 | elem.removeChild (old_text_node);
|
---|
| 54 | }
|
---|
| 55 | Text t = elem.getOwnerDocument ().createTextNode (text);
|
---|
| 56 | elem.appendChild (t);
|
---|
| 57 | }
|
---|
| 58 | /** returns the (first) child element with the given name */
|
---|
| 59 | public static Node getChildByTagName (Node n, String name) {
|
---|
| 60 |
|
---|
| 61 | Node child = n.getFirstChild ();
|
---|
| 62 | while (child!=null) {
|
---|
| 63 | if (child.getNodeName ().equals (name)) {
|
---|
| 64 | return child;
|
---|
| 65 | }
|
---|
| 66 | child = child.getNextSibling ();
|
---|
| 67 | }
|
---|
| 68 | return null; //not found
|
---|
| 69 | }
|
---|
| 70 |
|
---|
| 71 | /** returns the (nth) child element with the given name
|
---|
| 72 | * index numbers start at 0 */
|
---|
| 73 | public static Node getChildByTagNameIndexed (Node n, String name, int index) {
|
---|
| 74 | if (index == -1) {
|
---|
| 75 | return getChildByTagName (n, name);
|
---|
| 76 | }
|
---|
| 77 | int count = 0;
|
---|
| 78 | Node child = n.getFirstChild ();
|
---|
| 79 | while (child!=null) {
|
---|
| 80 | if (child.getNodeName ().equals (name)) {
|
---|
| 81 | if (count == index) {
|
---|
| 82 | return child;
|
---|
| 83 | } else {
|
---|
| 84 | count++;
|
---|
| 85 | }
|
---|
| 86 | }
|
---|
| 87 | child = child.getNextSibling ();
|
---|
| 88 | }
|
---|
| 89 | return null; //not found
|
---|
| 90 | }
|
---|
| 91 |
|
---|
| 92 | /** returns the element parent/node_name[@attribute_name='attribute_value']
|
---|
| 93 | */
|
---|
| 94 | public static Element getNamedElement (Element parent, String node_name,
|
---|
| 95 | String attribute_name,
|
---|
| 96 | String attribute_value) {
|
---|
| 97 |
|
---|
| 98 | NodeList children = parent.getChildNodes ();
|
---|
| 99 | for (int i=0; i<children.getLength (); i++) {
|
---|
| 100 | Node child = children.item (i);
|
---|
| 101 | //logger.debug("getnamed elem, node nmae="+child.getNodeName());
|
---|
| 102 | if (child.getNodeName ().equals (node_name)) {
|
---|
| 103 | if (((Element)child).getAttribute (attribute_name).equals (attribute_value))
|
---|
| 104 | return (Element)child;
|
---|
| 105 | }
|
---|
| 106 | }
|
---|
| 107 | // not found
|
---|
| 108 | return null;
|
---|
| 109 | }
|
---|
| 110 | /** returns a list of elements parent/node_name[@attribute_name='attribute_value']
|
---|
| 111 | */
|
---|
| 112 | public static ArrayList getNamedElementList (Element parent, String node_name,
|
---|
| 113 | String attribute_name,
|
---|
| 114 | String attribute_value) {
|
---|
| 115 | ArrayList elements = new ArrayList ();
|
---|
| 116 | NodeList children = parent.getChildNodes ();
|
---|
| 117 | for (int i=0; i<children.getLength (); i++) {
|
---|
| 118 | //System.out.println("getNamedElementList");
|
---|
| 119 | Node child = children.item (i);
|
---|
| 120 | //logger.debug("getnamed elem, node nmae="+child.getNodeName());
|
---|
| 121 | if (child.getNodeName ().equals (node_name)) {
|
---|
| 122 | if (((Element)child).getAttribute (attribute_name).equals (attribute_value))
|
---|
| 123 | elements.add ((Element)child);
|
---|
| 124 | }
|
---|
| 125 | }
|
---|
| 126 | // not found
|
---|
| 127 | if (elements.size () == 0) {
|
---|
| 128 | elements = null;
|
---|
| 129 | }
|
---|
| 130 | return elements;
|
---|
| 131 | }
|
---|
| 132 | public static void copyAllChildren (Element to, Element from) {
|
---|
| 133 |
|
---|
| 134 | Document to_doc = to.getOwnerDocument ();
|
---|
| 135 | Node child = from.getFirstChild ();
|
---|
| 136 | while (child != null) {
|
---|
| 137 | to.appendChild (to_doc.importNode (child, true));
|
---|
| 138 | child = child.getNextSibling ();
|
---|
| 139 | }
|
---|
| 140 | }
|
---|
| 141 | /** Duplicates an element */
|
---|
| 142 | public static Element duplicateElement (Document owner, Element element, boolean with_attributes) {
|
---|
| 143 | return duplicateElementNS (owner, element, null, with_attributes);
|
---|
| 144 | }
|
---|
| 145 |
|
---|
| 146 | /** Duplicates an element */
|
---|
| 147 | public static Element duplicateElementNS (Document owner,
|
---|
| 148 | Element element,
|
---|
| 149 | String namespace_uri,
|
---|
| 150 | boolean with_attributes) {
|
---|
| 151 | Element duplicate;
|
---|
| 152 | if (namespace_uri == null) {
|
---|
| 153 | duplicate = owner.createElement (element.getTagName ());
|
---|
| 154 | } else {
|
---|
| 155 | duplicate = owner.createElementNS (namespace_uri, element.getTagName ());
|
---|
| 156 | }
|
---|
| 157 | // Copy element attributes
|
---|
| 158 | if (with_attributes) {
|
---|
| 159 | NamedNodeMap attributes = element.getAttributes ();
|
---|
| 160 | for (int i = 0; i < attributes.getLength (); i++) {
|
---|
| 161 | Node attribute = attributes.item (i);
|
---|
| 162 | duplicate.setAttribute (attribute.getNodeName (), attribute.getNodeValue ());
|
---|
| 163 | }
|
---|
| 164 | }
|
---|
| 165 |
|
---|
| 166 | // Copy element children
|
---|
| 167 | NodeList children = element.getChildNodes ();
|
---|
| 168 | for (int i = 0; i < children.getLength (); i++) {
|
---|
| 169 | Node child = children.item (i);
|
---|
| 170 | duplicate.appendChild (owner.importNode (child, true));
|
---|
| 171 | }
|
---|
| 172 |
|
---|
| 173 | return duplicate;
|
---|
| 174 | }
|
---|
| 175 |
|
---|
| 176 |
|
---|
| 177 | /** Remove all of the child nodes from a certain node. */
|
---|
| 178 | static final public void clear (Node node) {
|
---|
| 179 | while (node.hasChildNodes ()) {
|
---|
| 180 | node.removeChild (node.getFirstChild ());
|
---|
| 181 | }
|
---|
| 182 | }
|
---|
| 183 |
|
---|
| 184 |
|
---|
| 185 | static public ArrayList getChildElementsByTagName (Element parent_element, String element_name) {
|
---|
| 186 | ArrayList child_elements = new ArrayList ();
|
---|
| 187 |
|
---|
| 188 | NodeList children_nodelist = parent_element.getChildNodes ();
|
---|
| 189 | for (int i = 0; i < children_nodelist.getLength (); i++) {
|
---|
| 190 | Node child_node = children_nodelist.item (i);
|
---|
| 191 | if (child_node.getNodeType () == Node.ELEMENT_NODE && child_node.getNodeName ().equals (element_name)) {
|
---|
| 192 | child_elements.add (child_node);
|
---|
| 193 | }
|
---|
| 194 | }
|
---|
| 195 |
|
---|
| 196 | return child_elements;
|
---|
| 197 | }
|
---|
| 198 |
|
---|
| 199 |
|
---|
| 200 | static public String getElementTextValue (Element element) {
|
---|
| 201 | // Find the first text node child
|
---|
| 202 | NodeList children_nodelist = element.getChildNodes ();
|
---|
| 203 | for (int i = 0; i < children_nodelist.getLength (); i++) {
|
---|
| 204 | Node child_node = children_nodelist.item (i);
|
---|
| 205 | if (child_node.getNodeType () == Node.TEXT_NODE) {
|
---|
| 206 | return child_node.getNodeValue ();
|
---|
| 207 | }
|
---|
| 208 | }
|
---|
| 209 |
|
---|
| 210 | // None found
|
---|
| 211 | return "";
|
---|
| 212 | }
|
---|
| 213 |
|
---|
| 214 |
|
---|
| 215 | /** Method to retrieve the value of a given node.
|
---|
| 216 | * @param element The <strong>Element</strong> whose value we wish to find.
|
---|
| 217 | * Soon to be deprecated!
|
---|
| 218 | */
|
---|
| 219 | static final public String getValue (Node element) {
|
---|
| 220 | if (element == null) {
|
---|
| 221 | return "";
|
---|
| 222 | }
|
---|
| 223 | // If we've been given a subject node first retrieve its value node.
|
---|
| 224 | if(element.getNodeName ().equals ("Subject")) {
|
---|
| 225 | element = getNodeFromNamed (element, "Value");
|
---|
| 226 | }
|
---|
| 227 | // If we've got a value node, then reconstruct the text. Remember that DOM will split text over 256 characters into several text nodes
|
---|
| 228 | if(element != null && element.hasChildNodes ()) {
|
---|
| 229 | StringBuffer text_buffer = new StringBuffer ();
|
---|
| 230 | NodeList text_nodes = element.getChildNodes ();
|
---|
| 231 | for(int i = 0; i < text_nodes.getLength (); i++) {
|
---|
| 232 | Node possible_text = text_nodes.item (i);
|
---|
| 233 | if(possible_text.getNodeName ().equals (StaticStrings.TEXT_NODE)) {
|
---|
| 234 | text_buffer.append (possible_text.getNodeValue ());
|
---|
| 235 | }
|
---|
| 236 | }
|
---|
| 237 | return text_buffer.toString ();
|
---|
| 238 | }
|
---|
| 239 | return "";
|
---|
| 240 | }
|
---|
| 241 |
|
---|
| 242 |
|
---|
| 243 | /** Method to retrieve from the node given, a certain child node with the specified name.
|
---|
| 244 | * @param parent The <strong>Node</strong> whose children should be searched.
|
---|
| 245 | * @param name The required nodes name as a <strong>String</strong>.
|
---|
| 246 | * @return The requested <strong>Node</strong> if it is found, <i>null</i> otherwise.
|
---|
| 247 | * Soon to be deprecated!
|
---|
| 248 | */
|
---|
| 249 | static final public Node getNodeFromNamed (Node parent, String name) {
|
---|
| 250 | Node child = null;
|
---|
| 251 | for(Node i = parent.getFirstChild (); i != null && child == null;
|
---|
| 252 | i = i.getNextSibling ()) {
|
---|
| 253 | if(i.getNodeName ().equals (name)) {
|
---|
| 254 | child = i;
|
---|
| 255 | }
|
---|
| 256 | }
|
---|
| 257 | return child;
|
---|
| 258 | }
|
---|
| 259 |
|
---|
| 260 | static final public String WELLFORMED= "well-formed !";
|
---|
| 261 | static final public String NOTWELLFORMED= "not well-formed";
|
---|
| 262 | static final private String HEADER = "<?xml version='1.0' encoding='UTF-8'?><collectionConfig xmlns:gsf='http://www.greenstone.org/greenstone3/schema/ConfigFormat' xmlns:xsl='http://www.w3.org/1999/XSL/Transform'>";
|
---|
[18170] | 263 | static final private String FOOTER = "</collectionConfig>";
|
---|
[14053] | 264 |
|
---|
| 265 | public static String parse (String xml_str) {
|
---|
| 266 | String validation_msg = WELLFORMED;
|
---|
| 267 | xml_str = HEADER + xml_str + FOOTER;
|
---|
| 268 | try {
|
---|
| 269 | SAXParserFactory factory = SAXParserFactory.newInstance ();
|
---|
| 270 | factory.setNamespaceAware (true);
|
---|
| 271 | //factory.setValidating (true);
|
---|
| 272 | SAXParser parser = factory.newSAXParser ();
|
---|
| 273 | InputSource iSource = new InputSource ( new StringReader ( xml_str ) );
|
---|
| 274 | // parser.parse (iSource, new DefaultHandler ());
|
---|
| 275 |
|
---|
| 276 | org.xml.sax.XMLReader reader = parser.getXMLReader ();
|
---|
| 277 | reader.setContentHandler(new DefaultHandler());
|
---|
| 278 | reader.setErrorHandler(new DefaultHandler());
|
---|
| 279 | reader.parse(iSource);
|
---|
| 280 | } catch (FactoryConfigurationError e) {
|
---|
| 281 | validation_msg = "unable to get a document builder factory";
|
---|
| 282 | } catch (ParserConfigurationException e) {
|
---|
| 283 | validation_msg = "unable to configure parser";
|
---|
| 284 | } catch (SAXParseException e) {
|
---|
| 285 | validation_msg = NOTWELLFORMED + getLocationString(e) + e.getMessage ();
|
---|
| 286 | } catch (SAXException e) {
|
---|
| 287 | validation_msg += " Fatal error: " + e.toString ();
|
---|
| 288 | } catch (IOException e) {
|
---|
| 289 | validation_msg = "Unable to read the input, i/o error";
|
---|
| 290 | }
|
---|
| 291 |
|
---|
| 292 | return validation_msg;
|
---|
| 293 | }
|
---|
| 294 | //In this method, the parsed string xml_str is not wrapped by the header and footer strings.
|
---|
| 295 | public static String parseDOM (String xml_str) {
|
---|
| 296 | String validation_msg = WELLFORMED;
|
---|
| 297 |
|
---|
| 298 | try {
|
---|
| 299 | SAXParserFactory factory = SAXParserFactory.newInstance ();
|
---|
| 300 | factory.setNamespaceAware (true);
|
---|
| 301 | //factory.setValidating (true);
|
---|
| 302 | SAXParser parser = factory.newSAXParser ();
|
---|
| 303 | InputSource iSource = new InputSource ( new StringReader ( xml_str ) );
|
---|
| 304 | // parser.parse (iSource, new DefaultHandler ());
|
---|
| 305 |
|
---|
| 306 | org.xml.sax.XMLReader reader = parser.getXMLReader ();
|
---|
| 307 | reader.setContentHandler(new DefaultHandler());
|
---|
| 308 | reader.setErrorHandler(new DefaultHandler());
|
---|
| 309 | reader.parse(iSource);
|
---|
| 310 | } catch (FactoryConfigurationError e) {
|
---|
| 311 | validation_msg = "unable to get a document builder factory";
|
---|
| 312 | } catch (ParserConfigurationException e) {
|
---|
| 313 | validation_msg = "unable to configure parser";
|
---|
| 314 | } catch (SAXParseException e) {
|
---|
| 315 | validation_msg = NOTWELLFORMED + getLocationString(e) + e.getMessage ();
|
---|
| 316 | } catch (SAXException e) {
|
---|
| 317 | validation_msg += " " + e.toString ();
|
---|
| 318 | } catch (IOException e) {
|
---|
| 319 | validation_msg = "Unable to read the input, i/o error";
|
---|
| 320 | }
|
---|
| 321 |
|
---|
| 322 | return validation_msg;
|
---|
| 323 | }
|
---|
| 324 |
|
---|
| 325 | public static String parse (File xml_file) {
|
---|
| 326 | String validation_msg = WELLFORMED;
|
---|
| 327 |
|
---|
| 328 | try {
|
---|
| 329 | SAXParserFactory factory = SAXParserFactory.newInstance ();
|
---|
| 330 | factory.setNamespaceAware (true);
|
---|
| 331 | //factory.setValidating (true);
|
---|
| 332 | SAXParser parser = factory.newSAXParser ();
|
---|
| 333 | FileReader r = new FileReader(xml_file);
|
---|
[18170] | 334 | InputSource iSource = new InputSource(r);
|
---|
[14053] | 335 | XMLReader reader = parser.getXMLReader ();
|
---|
| 336 | reader.setContentHandler(new DefaultHandler());
|
---|
| 337 | reader.setErrorHandler(new DefaultHandler());
|
---|
| 338 | reader.parse(iSource);
|
---|
| 339 | } catch (FactoryConfigurationError e) {
|
---|
| 340 | validation_msg = "unable to get a document builder factory";
|
---|
| 341 | } catch (ParserConfigurationException e) {
|
---|
| 342 | validation_msg = "unable to configure parser";
|
---|
| 343 | } catch (SAXParseException e) {
|
---|
| 344 | validation_msg = NOTWELLFORMED + getLocationString(e) + e.getMessage ();
|
---|
| 345 | } catch (SAXException e) {
|
---|
| 346 | validation_msg += " Fatal error: " + e.toString ();
|
---|
| 347 | } catch (IOException e) {
|
---|
| 348 | validation_msg = "Unable to read the input, i/o error";
|
---|
| 349 | }
|
---|
| 350 |
|
---|
| 351 | return validation_msg;
|
---|
| 352 | }
|
---|
| 353 | /** Returns a string of the location. */
|
---|
| 354 | private static String getLocationString(SAXParseException ex) {
|
---|
| 355 | StringBuffer str = new StringBuffer();
|
---|
| 356 |
|
---|
| 357 | String systemId = ex.getSystemId();
|
---|
| 358 | if (systemId != null) {
|
---|
| 359 | int index = systemId.lastIndexOf('/');
|
---|
| 360 | if (index != -1)
|
---|
| 361 | systemId = systemId.substring(index + 1);
|
---|
| 362 | str.append(systemId);
|
---|
| 363 | }
|
---|
| 364 | str.append("(line ");
|
---|
| 365 | str.append(ex.getLineNumber()-1);
|
---|
| 366 | str.append(", column ");
|
---|
| 367 | str.append(ex.getColumnNumber());
|
---|
| 368 | str.append("): ");
|
---|
| 369 |
|
---|
| 370 | return str.toString();
|
---|
| 371 |
|
---|
| 372 | } // getLocationString(SAXParseException):String
|
---|
| 373 |
|
---|
[15581] | 374 |
|
---|
[14053] | 375 | /** Parse an XML document from a given file path */
|
---|
| 376 | static public Document parseXMLFile (String xml_file_path, boolean use_class_loader) {
|
---|
| 377 | if (use_class_loader == true) {
|
---|
| 378 | InputStream is = JarTools.getResourceAsStream ("/" + xml_file_path);
|
---|
| 379 | if (is != null) {
|
---|
| 380 | return parseXML (is);
|
---|
| 381 | }
|
---|
| 382 | }
|
---|
| 383 |
|
---|
| 384 | // Try the file outside the classes directory
|
---|
| 385 | return parseXMLFile (new File (xml_file_path));
|
---|
| 386 | }
|
---|
| 387 |
|
---|
| 388 |
|
---|
| 389 | /** Parse an XML document from a given file */
|
---|
| 390 | static public Document parseXMLFile (File xml_file) {
|
---|
| 391 | // No file? No point trying!
|
---|
| 392 | if (xml_file.exists () == false) {
|
---|
| 393 | return null;
|
---|
| 394 | }
|
---|
| 395 |
|
---|
| 396 | try {
|
---|
| 397 | return parseXML (new FileInputStream (xml_file));
|
---|
| 398 | }
|
---|
| 399 | catch (Exception exception) {
|
---|
| 400 | DebugStream.printStackTrace (exception);
|
---|
| 401 | return null;
|
---|
| 402 | }
|
---|
| 403 | }
|
---|
| 404 |
|
---|
| 405 |
|
---|
| 406 | /** Parse an XML document from a given input stream */
|
---|
| 407 | static public Document parseXML (InputStream xml_input_stream) {
|
---|
| 408 | Document document = null;
|
---|
| 409 |
|
---|
| 410 | try {
|
---|
| 411 | InputStreamReader isr = new InputStreamReader (xml_input_stream, "UTF-8");
|
---|
[18170] | 412 | document = parseXML(isr);
|
---|
[14053] | 413 | isr.close ();
|
---|
| 414 | xml_input_stream.close ();
|
---|
| 415 | }
|
---|
| 416 | catch (Exception exception) {
|
---|
| 417 | DebugStream.printStackTrace (exception);
|
---|
| 418 | }
|
---|
| 419 |
|
---|
| 420 | return document;
|
---|
| 421 | }
|
---|
| 422 |
|
---|
| 423 |
|
---|
| 424 | /** Parse an XML document from a given reader */
|
---|
| 425 | static public Document parseXML (Reader xml_reader) {
|
---|
[18170] | 426 | Document document = null;
|
---|
| 427 |
|
---|
| 428 | // If debugging, the following will store the XML contents to be parsed,
|
---|
| 429 | // which can then be inspected upon encountering a SAXException (need to run GLI with -debug on)
|
---|
| 430 | String xmlContents = "";
|
---|
[15581] | 431 |
|
---|
[18170] | 432 | try {
|
---|
| 433 | Reader reader = null;
|
---|
| 434 |
|
---|
| 435 | // (1) By default, GLI will remove any contents preceeding (and invalidating)
|
---|
| 436 | // the XML and present these lines separately to the user
|
---|
| 437 | if(!DebugStream.isDebuggingEnabled()) {
|
---|
| 438 | try {
|
---|
| 439 | reader = new BufferedReader( new RemoveContentBeforeRootElementXMLReader(xml_reader) );
|
---|
| 440 | } catch ( Exception e ) {
|
---|
| 441 | System.err.println( "Exception while wrapping the reader in parseXML(Reader)" );
|
---|
| 442 | e.printStackTrace();
|
---|
| 443 | }
|
---|
| 444 | }
|
---|
| 445 |
|
---|
| 446 | // (2) If we are running GLI in debug mode:
|
---|
| 447 | // In case parsing exceptions are thrown (SAX Exceptions), we want to get some
|
---|
| 448 | // idea of where things went wrong. This will print the "XML" contents to either
|
---|
| 449 | // system.out (if debugging is off) or to the DebugStream otherwise.
|
---|
| 450 | // We need to read the XML twice to know the line where things went wrong, so
|
---|
| 451 | // do the additional reading only if we're debugging
|
---|
| 452 | else {
|
---|
| 453 | StringBuffer buf = new StringBuffer();
|
---|
| 454 | char[] buffer = new char[500];
|
---|
| 455 | int numCharsRead = xml_reader.read(buffer, 0, buffer.length);
|
---|
| 456 | while(numCharsRead != -1) {
|
---|
| 457 | buf.append(buffer, 0, numCharsRead);
|
---|
| 458 | numCharsRead = xml_reader.read(buffer, 0, buffer.length);
|
---|
| 459 | }
|
---|
| 460 | xmlContents = buf.toString();
|
---|
| 461 | xml_reader.close(); // closing the old Reader
|
---|
| 462 | xml_reader = null;
|
---|
| 463 | buffer = null;
|
---|
| 464 | buf = null;
|
---|
| 465 | // we need a Reader to parse the same contents as the Reader that was just closed
|
---|
| 466 | reader = new BufferedReader(new StringReader(xmlContents));
|
---|
| 467 | }
|
---|
[15581] | 468 |
|
---|
[18170] | 469 | // (2) The actual XML parsing
|
---|
| 470 | InputSource isc = new InputSource (reader);
|
---|
| 471 | DOMParser parser = new DOMParser ();
|
---|
| 472 | parser.setFeature ("http://xml.org/sax/features/validation", false);
|
---|
| 473 | parser.setFeature ("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
|
---|
| 474 | // May or may not be ignored, the documentation for Xerces is contradictory. If it works then parsing -should- be faster.
|
---|
| 475 | parser.setFeature ("http://apache.org/xml/features/dom/defer-node-expansion", true);
|
---|
| 476 | parser.setFeature ("http://apache.org/xml/features/dom/include-ignorable-whitespace", false);
|
---|
| 477 | parser.parse (isc);
|
---|
| 478 | document = parser.getDocument ();
|
---|
| 479 |
|
---|
| 480 | } catch(SAXParseException e) {
|
---|
| 481 | showXMLParseFailureLine(e, xmlContents);
|
---|
| 482 | } catch (SAXException exception) {
|
---|
| 483 | System.err.println ("SAX exception: " + exception.getMessage ());
|
---|
| 484 | if(DebugStream.isDebuggingEnabled()) {
|
---|
| 485 | DebugStream.println("Encountered a SAX exception when parsing the following:\n*********START\n"
|
---|
| 486 | + xmlContents + "\n************END\n");
|
---|
| 487 | // Exit to let the user view the erroneous line/xml before it goes past the screen buffer?
|
---|
| 488 | DebugStream.println("Debug mode: Exiting the program as there was trouble parsing the XML...");
|
---|
| 489 | System.exit(-1);
|
---|
| 490 | }
|
---|
| 491 | // else, not running in debug mode, so don't exit after exception
|
---|
| 492 | System.out.println("***Turn debugging on (run GLI with -debug) to view the XML contents that could not be parsed.");
|
---|
| 493 | DebugStream.printStackTrace (exception);
|
---|
[14053] | 494 | }
|
---|
| 495 | catch (Exception exception) {
|
---|
| 496 | DebugStream.printStackTrace (exception);
|
---|
| 497 | }
|
---|
| 498 |
|
---|
| 499 | return document;
|
---|
| 500 | }
|
---|
[15581] | 501 |
|
---|
| 502 | /** Displays the line (string) where the SAXParseException occurred, given a String of the
|
---|
| 503 | * entire xml that was being parsed and the SAXParseException object that was caught.
|
---|
| 504 | * The messages are printed to DebugStream, so run GLI/FLI with -debug to view this output.
|
---|
| 505 | * @param xmlContents is the entire xml that was being parsed when the exception occurred
|
---|
| 506 | * @param e is the SAXParseException object that was thrown upon parsing the xmlContents.
|
---|
| 507 | */
|
---|
| 508 | public static void showXMLParseFailureLine(SAXParseException e, String xmlContents) {
|
---|
[18170] | 509 |
|
---|
| 510 | // There should be no characters at all that preceed the <?xml>... bit.
|
---|
| 511 | // The first check is for starting spaces:
|
---|
| 512 | if(xmlContents.startsWith("\n") || xmlContents.startsWith(" ") || xmlContents.startsWith("\t")) {
|
---|
| 513 | DebugStream.println("ERROR: illegal start of XML. Space/tab/newline should not preceed xml declaration.\n");
|
---|
| 514 | DebugStream.println("xmlContents (length is " + xmlContents.length() + "):\n" + xmlContents);
|
---|
| 515 | return; // nothing more to do, first error identified
|
---|
| 516 | }
|
---|
| 517 |
|
---|
| 518 | // the actual line (String literal) where parsing failed and the SAXParseException occurred.
|
---|
| 519 | String line = "";
|
---|
| 520 | int linenumber = e.getLineNumber();
|
---|
| 521 | DebugStream.println("\n****SAXParseException on LINE NUMBER: " + linenumber);
|
---|
| 522 | if(DebugStream.isDebuggingEnabled()) {
|
---|
| 523 | if(linenumber != -1) {
|
---|
| 524 | // find the line in xmlContents string (xmlContents is only set if GLI is run with debugging turned on)
|
---|
| 525 | int start = 0;
|
---|
| 526 | int end = xmlContents.length();
|
---|
| 527 | for(int i = 1; i <= linenumber; i++) {
|
---|
| 528 | end = xmlContents.indexOf("\n");
|
---|
| 529 | if(end > 0) {
|
---|
| 530 | line = xmlContents.substring(start, end);
|
---|
| 531 | }
|
---|
| 532 | start = end+1;
|
---|
| 533 | }
|
---|
| 534 | DebugStream.println("The parsing error occurred on this line:\n***********START\n" + line + "\n***********END");
|
---|
| 535 | DebugStream.println("SAXParseException message: " + e.getMessage() + "\n");
|
---|
| 536 | } else { // no particular line number, print out all the xml so debugger can inspect it
|
---|
| 537 | DebugStream.println("Encountered a SAX exception when parsing the following:\n*********START\n"
|
---|
| 538 | + xmlContents + "\n************END\n");
|
---|
| 539 | }
|
---|
| 540 | // Exit to let the user view the erroneous line/xml before it goes past the screen buffer?
|
---|
| 541 | DebugStream.println("\nDebug mode: Exiting the program as there was trouble parsing the XML...");
|
---|
| 542 | System.exit(-1);
|
---|
| 543 | } else { // not running in debug mode
|
---|
| 544 | System.out.println("***Turn debugging on (run GLI with -debug) to view the XML contents/line that could not be parsed.");
|
---|
| 545 | }
|
---|
[15581] | 546 | }
|
---|
| 547 |
|
---|
[14053] | 548 |
|
---|
| 549 | static public StringBuffer readXMLStream (InputStream input_stream) {
|
---|
| 550 | StringBuffer xml = new StringBuffer ("");
|
---|
| 551 |
|
---|
| 552 | try {
|
---|
| 553 | InputStreamReader isr = new InputStreamReader (input_stream, "UTF-8");
|
---|
| 554 | BufferedReader buffered_in = new BufferedReader (isr);
|
---|
| 555 |
|
---|
| 556 | String line = "";
|
---|
| 557 | boolean xml_content = false;
|
---|
| 558 | while((line = buffered_in.readLine ()) != null) {
|
---|
| 559 | if(xml_content) {
|
---|
| 560 | xml.append (line);
|
---|
| 561 | xml.append ("\n");
|
---|
| 562 | }
|
---|
| 563 | else if(line.trim ().startsWith ("<?xml")) {
|
---|
| 564 | xml_content = true;
|
---|
| 565 | xml.append (line);
|
---|
| 566 | xml.append ("\n");
|
---|
| 567 | }
|
---|
| 568 | }
|
---|
| 569 | buffered_in = null;
|
---|
| 570 | }
|
---|
| 571 | catch (Exception error) {
|
---|
| 572 | System.err.println ("Failed when trying to parse XML stream");
|
---|
| 573 | error.printStackTrace ();
|
---|
| 574 | }
|
---|
| 575 |
|
---|
| 576 | return xml;
|
---|
| 577 | }
|
---|
| 578 |
|
---|
| 579 |
|
---|
| 580 | /** Removes characters that are invalid in XML (see http://www.w3.org/TR/2000/REC-xml-20001006#charsets) */
|
---|
| 581 | static public String removeInvalidCharacters (String text) {
|
---|
| 582 | char[] safe_characters = new char[text.length ()];
|
---|
| 583 | int j = 0;
|
---|
| 584 |
|
---|
| 585 | char[] raw_characters = new char[text.length ()];
|
---|
| 586 | text.getChars (0, text.length (), raw_characters, 0);
|
---|
| 587 | for (int i = 0; i < raw_characters.length; i++) {
|
---|
| 588 | char character = raw_characters[i];
|
---|
| 589 | if ((character >= 0x20 && character <= 0xD7FF) || character == 0x09 || character == 0x0A || character == 0x0D || (character >= 0xE000 && character <= 0xFFFD) || (character >= 0x10000 && character <= 0x10FFFF)) {
|
---|
| 590 | safe_characters[j] = character;
|
---|
| 591 | j++;
|
---|
| 592 | }
|
---|
| 593 | }
|
---|
| 594 |
|
---|
| 595 | return new String (safe_characters, 0, j);
|
---|
| 596 | }
|
---|
| 597 |
|
---|
| 598 |
|
---|
| 599 | static public void setElementTextValue (Element element, String text) {
|
---|
| 600 | // Remove all text node children
|
---|
| 601 | NodeList children_nodelist = element.getChildNodes ();
|
---|
| 602 | for (int i = children_nodelist.getLength () - 1; i >= 0; i--) {
|
---|
| 603 | Node child_node = children_nodelist.item (i);
|
---|
| 604 | if (child_node.getNodeType () == Node.TEXT_NODE) {
|
---|
| 605 | element.removeChild (child_node);
|
---|
| 606 | }
|
---|
| 607 | }
|
---|
| 608 |
|
---|
| 609 | // Add a new text node
|
---|
| 610 | if (text != null) {
|
---|
| 611 | element.appendChild (element.getOwnerDocument ().createTextNode (text));
|
---|
| 612 | }
|
---|
| 613 | }
|
---|
| 614 |
|
---|
| 615 |
|
---|
| 616 | /** Set the #text node value of some element.
|
---|
| 617 | * @param element the Element whose value we wish to set
|
---|
| 618 | * @param value the new value for the element as a String
|
---|
| 619 | * Soon to be deprecated!
|
---|
| 620 | */
|
---|
| 621 | static final public void setValue (Element element, String value) {
|
---|
| 622 | // Remove any existing child node(s)
|
---|
| 623 | clear (element);
|
---|
| 624 | // Add new text node.
|
---|
| 625 | if (value != null) {
|
---|
| 626 | element.appendChild (element.getOwnerDocument ().createTextNode (value));
|
---|
| 627 | }
|
---|
| 628 | }
|
---|
| 629 |
|
---|
| 630 | /** Write an XML document to a given file with the text node of the specified element unescaped*/
|
---|
| 631 | static public void writeXMLFile (File xml_file, Document document, String[] nonEscapingTagNames) {
|
---|
| 632 | try {
|
---|
| 633 | OutputStream os = new FileOutputStream (xml_file);
|
---|
| 634 | // Create an output format for our document.
|
---|
| 635 | OutputFormat f = new OutputFormat (document);
|
---|
| 636 | f.setEncoding ("UTF-8");
|
---|
| 637 | f.setIndenting (true);
|
---|
| 638 | f.setLineWidth (0); // Why isn't this working!
|
---|
| 639 | f.setPreserveSpace (false);
|
---|
[16988] | 640 | if (nonEscapingTagNames != null) {
|
---|
[18170] | 641 | f.setNonEscapingElements (nonEscapingTagNames);
|
---|
| 642 | }
|
---|
[14053] | 643 | // Create the necessary writer stream for serialization.
|
---|
| 644 | OutputStreamWriter osw = new OutputStreamWriter (os, "UTF-8");
|
---|
| 645 | Writer w = new BufferedWriter (osw);
|
---|
| 646 | // Generate a new serializer from the above.
|
---|
| 647 | XMLSerializer s = new XMLSerializer (w, f);
|
---|
| 648 | s.asDOMSerializer ();
|
---|
| 649 | // Finally serialize the document to file.
|
---|
| 650 | s.serialize (document);
|
---|
| 651 | // And close.
|
---|
| 652 | os.close ();
|
---|
| 653 | }
|
---|
| 654 | catch (Exception exception) {
|
---|
| 655 | DebugStream.printStackTrace (exception);
|
---|
| 656 | }
|
---|
| 657 | }
|
---|
| 658 |
|
---|
| 659 | /** Write an XML document to a given file */
|
---|
| 660 | static public void writeXMLFile (File xml_file, Document document) {
|
---|
[16988] | 661 | writeXMLFile(xml_file, document, null);
|
---|
[14053] | 662 | }
|
---|
[16988] | 663 |
|
---|
[14053] | 664 | public static void printXMLNode (Node e) {
|
---|
| 665 | printXMLNode (e, 0) ;
|
---|
| 666 | }
|
---|
| 667 |
|
---|
| 668 | public static void printXMLNode (Node e, int depth) { //recursive method call using DOM API...
|
---|
| 669 |
|
---|
| 670 | for (int i=0 ; i<depth ; i++)
|
---|
| 671 | System.out.print (' ') ;
|
---|
| 672 |
|
---|
| 673 | if (e.getNodeType () == Node.TEXT_NODE){
|
---|
| 674 | //System.out.println("text") ;
|
---|
| 675 | if (e.getNodeValue () != "") {
|
---|
| 676 | System.out.println (e.getNodeValue ()) ;
|
---|
| 677 | }
|
---|
| 678 | return ;
|
---|
| 679 | }
|
---|
| 680 |
|
---|
| 681 | System.out.print ('<');
|
---|
| 682 | System.out.print (e.getNodeName ());
|
---|
| 683 | NamedNodeMap attrs = e.getAttributes ();
|
---|
| 684 | if (attrs != null) {
|
---|
| 685 | for (int i = 0; i < attrs.getLength (); i++) {
|
---|
| 686 | Node attr = attrs.item (i);
|
---|
| 687 | System.out.print (' ');
|
---|
| 688 | System.out.print (attr.getNodeName ());
|
---|
| 689 | System.out.print ("=\"");
|
---|
| 690 | System.out.print (attr.getNodeValue ());
|
---|
| 691 | System.out.print ('"');
|
---|
| 692 | }
|
---|
| 693 | }
|
---|
| 694 | NodeList children = e.getChildNodes ();
|
---|
| 695 |
|
---|
| 696 | if (children == null || children.getLength () == 0)
|
---|
| 697 | System.out.println ("/>") ;
|
---|
| 698 | else {
|
---|
| 699 |
|
---|
| 700 | System.out.println ('>') ;
|
---|
| 701 |
|
---|
| 702 | int len = children.getLength ();
|
---|
| 703 | for (int i = 0; i < len; i++) {
|
---|
| 704 | printXMLNode (children.item (i), depth + 1);
|
---|
| 705 | }
|
---|
| 706 |
|
---|
| 707 | for (int i=0 ; i<depth ; i++)
|
---|
| 708 | System.out.print (' ') ;
|
---|
| 709 |
|
---|
| 710 | System.out.println ("</" + e.getNodeName () + ">");
|
---|
| 711 | }
|
---|
| 712 |
|
---|
| 713 | }
|
---|
| 714 | public static String xmlNodeToString (Node e){
|
---|
| 715 | StringBuffer sb = new StringBuffer ("");
|
---|
| 716 | xmlNodeToString (sb,e,0);
|
---|
| 717 | return sb.toString ();
|
---|
| 718 | }
|
---|
| 719 |
|
---|
| 720 | private static void xmlNodeToString (StringBuffer sb, Node e, int depth){
|
---|
| 721 |
|
---|
| 722 | for (int i=0 ; i<depth ; i++)
|
---|
| 723 | sb.append (' ') ;
|
---|
| 724 |
|
---|
| 725 | if (e.getNodeType () == Node.TEXT_NODE){
|
---|
| 726 | if (e.getNodeValue () != "") {
|
---|
| 727 | sb.append (e.getNodeValue ()) ;
|
---|
| 728 | }
|
---|
| 729 | return ;
|
---|
| 730 | }
|
---|
| 731 |
|
---|
| 732 | sb.append ('<');
|
---|
| 733 | sb.append (e.getNodeName ());
|
---|
| 734 | NamedNodeMap attrs = e.getAttributes ();
|
---|
| 735 | if (attrs != null) {
|
---|
| 736 | for (int i = 0; i < attrs.getLength (); i++) {
|
---|
| 737 | Node attr = attrs.item (i);
|
---|
| 738 | sb.append (' ');
|
---|
| 739 | sb.append (attr.getNodeName ());
|
---|
| 740 | sb.append ("=\"");
|
---|
| 741 | sb.append (attr.getNodeValue ());
|
---|
| 742 | sb.append ('"');
|
---|
| 743 | }
|
---|
| 744 | }
|
---|
| 745 | NodeList children = e.getChildNodes ();
|
---|
| 746 |
|
---|
| 747 | if (children == null || children.getLength () == 0)
|
---|
| 748 | sb.append ("/>\n") ;
|
---|
| 749 | else {
|
---|
| 750 |
|
---|
| 751 | sb.append (">\n") ;
|
---|
| 752 |
|
---|
| 753 | int len = children.getLength ();
|
---|
| 754 | for (int i = 0; i < len; i++) {
|
---|
| 755 | xmlNodeToString (sb,children.item (i), depth + 1);
|
---|
| 756 | }
|
---|
| 757 |
|
---|
| 758 | for (int i=0 ; i<depth ; i++)
|
---|
| 759 | sb.append (' ') ;
|
---|
| 760 |
|
---|
| 761 | sb.append ("</" + e.getNodeName () + ">\n");
|
---|
| 762 | }
|
---|
| 763 |
|
---|
| 764 |
|
---|
| 765 | }
|
---|
[16988] | 766 |
|
---|
| 767 | public static String xmlNodeToStringWithoutIndenting (Node e) {
|
---|
| 768 | StringBuffer sb = new StringBuffer ("");
|
---|
| 769 | xmlNodeToStringWithoutNewline(sb, e, -1);
|
---|
| 770 | return sb.toString();
|
---|
| 771 | }
|
---|
[14053] | 772 | public static String xmlNodeToStringWithoutNewline (Node e){
|
---|
| 773 | StringBuffer sb = new StringBuffer ("");
|
---|
| 774 | xmlNodeToStringWithoutNewline (sb,e,0);
|
---|
| 775 | return sb.toString ();
|
---|
| 776 | }
|
---|
| 777 |
|
---|
| 778 | private static void xmlNodeToStringWithoutNewline (StringBuffer sb, Node e, int depth){
|
---|
| 779 |
|
---|
| 780 | for (int i=0 ; i<depth ; i++)
|
---|
| 781 | sb.append (' ') ;
|
---|
[16988] | 782 |
|
---|
[14053] | 783 | if (e.getNodeType () == Node.TEXT_NODE){
|
---|
| 784 | if (e.getNodeValue () != "") {
|
---|
| 785 | sb.append (e.getNodeValue ()) ;
|
---|
| 786 | }
|
---|
| 787 | return ;
|
---|
| 788 | }
|
---|
| 789 |
|
---|
| 790 | sb.append ('<');
|
---|
| 791 | sb.append (e.getNodeName ());
|
---|
| 792 | NamedNodeMap attrs = e.getAttributes ();
|
---|
| 793 | if (attrs != null) {
|
---|
| 794 | for (int i = 0; i < attrs.getLength (); i++) {
|
---|
| 795 | Node attr = attrs.item (i);
|
---|
| 796 | sb.append (' ');
|
---|
| 797 | sb.append (attr.getNodeName ());
|
---|
| 798 | sb.append ("=\"");
|
---|
| 799 | sb.append (attr.getNodeValue ());
|
---|
| 800 | sb.append ('"');
|
---|
| 801 | }
|
---|
| 802 | }
|
---|
| 803 | NodeList children = e.getChildNodes ();
|
---|
| 804 |
|
---|
| 805 | if (children == null || children.getLength () == 0)
|
---|
| 806 | sb.append ("/>") ;
|
---|
| 807 | else {
|
---|
| 808 |
|
---|
| 809 | sb.append (">") ;
|
---|
| 810 |
|
---|
| 811 | int len = children.getLength ();
|
---|
| 812 | for (int i = 0; i < len; i++) {
|
---|
[18170] | 813 | if (depth >= 0) {
|
---|
[14053] | 814 | xmlNodeToStringWithoutNewline (sb,children.item (i), depth + 1);
|
---|
[18170] | 815 | } else {
|
---|
| 816 | xmlNodeToStringWithoutNewline (sb,children.item (i), depth);
|
---|
| 817 | }
|
---|
[14053] | 818 | }
|
---|
| 819 |
|
---|
| 820 | for (int i=0 ; i<depth ; i++)
|
---|
| 821 | sb.append (' ') ;
|
---|
| 822 |
|
---|
| 823 | sb.append ("</" + e.getNodeName () + ">");
|
---|
| 824 | }
|
---|
| 825 | }
|
---|
| 826 | }
|
---|