1 | package org.greenstone.gatherer.util;
|
---|
2 |
|
---|
3 | import java.io.*;
|
---|
4 | import java.net.*;
|
---|
5 | import java.util.*;
|
---|
6 | import org.apache.xerces.parsers.*;
|
---|
7 | import org.apache.xml.serialize.*;
|
---|
8 | import org.greenstone.gatherer.DebugStream;
|
---|
9 | import org.w3c.dom.*;
|
---|
10 | import org.xml.sax.*;
|
---|
11 |
|
---|
12 | import java.io.FileReader;
|
---|
13 | import java.io.IOException;
|
---|
14 | import java.io.StringReader;
|
---|
15 |
|
---|
16 | // SAX
|
---|
17 | import org.xml.sax.XMLReader;
|
---|
18 | import org.xml.sax.SAXException;
|
---|
19 | import org.xml.sax.SAXParseException;
|
---|
20 | import org.xml.sax.helpers.DefaultHandler;
|
---|
21 | import org.xml.sax.InputSource;
|
---|
22 |
|
---|
23 | // JAXP
|
---|
24 | import javax.xml.parsers.DocumentBuilder;
|
---|
25 | import javax.xml.parsers.DocumentBuilderFactory;
|
---|
26 | import javax.xml.parsers.FactoryConfigurationError;
|
---|
27 | import javax.xml.parsers.ParserConfigurationException;
|
---|
28 | import javax.xml.parsers.SAXParser;
|
---|
29 | import javax.xml.parsers.SAXParserFactory;
|
---|
30 |
|
---|
31 |
|
---|
32 | /** This class is a static class containing useful XML functions */
|
---|
33 | public class XMLTools
|
---|
34 | {
|
---|
35 | /** extracts the text out of a node */
|
---|
36 | public static Node getNodeTextNode(Element param)
|
---|
37 | {
|
---|
38 | param.normalize();
|
---|
39 | Node n = param.getFirstChild();
|
---|
40 | while (n != null && n.getNodeType() != Node.TEXT_NODE)
|
---|
41 | {
|
---|
42 | n = n.getNextSibling();
|
---|
43 | }
|
---|
44 | return n;
|
---|
45 | }
|
---|
46 |
|
---|
47 | /** extracts the text out of a node */
|
---|
48 | public static String getNodeText(Element param)
|
---|
49 | {
|
---|
50 | Node text_node = getNodeTextNode(param);
|
---|
51 | if (text_node == null)
|
---|
52 | {
|
---|
53 | return "";
|
---|
54 | }
|
---|
55 | return text_node.getNodeValue();
|
---|
56 | }
|
---|
57 |
|
---|
58 | public static void setNodeText(Element elem, String text)
|
---|
59 | {
|
---|
60 | Node old_text_node = getNodeTextNode(elem);
|
---|
61 | if (old_text_node != null)
|
---|
62 | {
|
---|
63 | elem.removeChild(old_text_node);
|
---|
64 | }
|
---|
65 | Text t = elem.getOwnerDocument().createTextNode(text);
|
---|
66 | elem.appendChild(t);
|
---|
67 | }
|
---|
68 |
|
---|
69 | /** returns the (first) child element with the given name */
|
---|
70 | public static Node getChildByTagName(Node n, String name)
|
---|
71 | {
|
---|
72 |
|
---|
73 | Node child = n.getFirstChild();
|
---|
74 | while (child != null)
|
---|
75 | {
|
---|
76 | if (child.getNodeName().equals(name))
|
---|
77 | {
|
---|
78 | return child;
|
---|
79 | }
|
---|
80 | child = child.getNextSibling();
|
---|
81 | }
|
---|
82 | return null; //not found
|
---|
83 | }
|
---|
84 |
|
---|
85 | /**
|
---|
86 | * returns the (nth) child element with the given name index numbers start
|
---|
87 | * at 0
|
---|
88 | */
|
---|
89 | public static Node getChildByTagNameIndexed(Node n, String name, int index)
|
---|
90 | {
|
---|
91 | if (index == -1)
|
---|
92 | {
|
---|
93 | return getChildByTagName(n, name);
|
---|
94 | }
|
---|
95 | int count = 0;
|
---|
96 | Node child = n.getFirstChild();
|
---|
97 | while (child != null)
|
---|
98 | {
|
---|
99 | if (child.getNodeName().equals(name))
|
---|
100 | {
|
---|
101 | if (count == index)
|
---|
102 | {
|
---|
103 | return child;
|
---|
104 | }
|
---|
105 | else
|
---|
106 | {
|
---|
107 | count++;
|
---|
108 | }
|
---|
109 | }
|
---|
110 | child = child.getNextSibling();
|
---|
111 | }
|
---|
112 | return null; //not found
|
---|
113 | }
|
---|
114 |
|
---|
115 | /**
|
---|
116 | * returns the element parent/node_name[@attribute_name='attribute_value']
|
---|
117 | */
|
---|
118 | public static Element getNamedElement(Element parent, String node_name, String attribute_name, String attribute_value)
|
---|
119 | {
|
---|
120 |
|
---|
121 | NodeList children = parent.getChildNodes();
|
---|
122 | for (int i = 0; i < children.getLength(); i++)
|
---|
123 | {
|
---|
124 | Node child = children.item(i);
|
---|
125 | //logger.debug("getnamed elem, node nmae="+child.getNodeName());
|
---|
126 | if (child.getNodeName().equals(node_name))
|
---|
127 | {
|
---|
128 | if (((Element) child).getAttribute(attribute_name).equals(attribute_value))
|
---|
129 | return (Element) child;
|
---|
130 | }
|
---|
131 | }
|
---|
132 | // not found
|
---|
133 | return null;
|
---|
134 | }
|
---|
135 |
|
---|
136 | /**
|
---|
137 | * returns a list of elements
|
---|
138 | * parent/node_name[@attribute_name='attribute_value']
|
---|
139 | */
|
---|
140 | public static ArrayList getNamedElementList(Element parent, String node_name, String attribute_name, String attribute_value)
|
---|
141 | {
|
---|
142 | ArrayList elements = new ArrayList();
|
---|
143 | NodeList children = parent.getChildNodes();
|
---|
144 | for (int i = 0; i < children.getLength(); i++)
|
---|
145 | {
|
---|
146 | //System.out.println("getNamedElementList");
|
---|
147 | Node child = children.item(i);
|
---|
148 | //logger.debug("getnamed elem, node nmae="+child.getNodeName());
|
---|
149 | if (child.getNodeName().equals(node_name))
|
---|
150 | {
|
---|
151 | if (((Element) child).getAttribute(attribute_name).equals(attribute_value))
|
---|
152 | elements.add((Element) child);
|
---|
153 | }
|
---|
154 | }
|
---|
155 | // not found
|
---|
156 | if (elements.size() == 0)
|
---|
157 | {
|
---|
158 | elements = null;
|
---|
159 | }
|
---|
160 | return elements;
|
---|
161 | }
|
---|
162 |
|
---|
163 | public static void copyAllChildren(Element to, Element from)
|
---|
164 | {
|
---|
165 |
|
---|
166 | Document to_doc = to.getOwnerDocument();
|
---|
167 | Node child = from.getFirstChild();
|
---|
168 | while (child != null)
|
---|
169 | {
|
---|
170 | to.appendChild(to_doc.importNode(child, true));
|
---|
171 | child = child.getNextSibling();
|
---|
172 | }
|
---|
173 | }
|
---|
174 |
|
---|
175 | /** duplicates all elements in list elements and appends to toElement */
|
---|
176 | public static void duplicateElementList(Document owner, Element toElement, NodeList elements, boolean with_attributes) {
|
---|
177 | int num_elems = elements.getLength();
|
---|
178 | if (num_elems < 1)
|
---|
179 | {
|
---|
180 | return;
|
---|
181 | }
|
---|
182 | for (int i = 0; i < num_elems; i++)
|
---|
183 | {
|
---|
184 | Element to_element = XMLTools.duplicateElement(owner, (Element) elements.item(i), with_attributes);
|
---|
185 | toElement.appendChild(to_element);
|
---|
186 | }
|
---|
187 |
|
---|
188 | }
|
---|
189 | /** Duplicates an element */
|
---|
190 | public static Element duplicateElement(Document owner, Element element, boolean with_attributes)
|
---|
191 | {
|
---|
192 | return duplicateElementNS(owner, element, null, with_attributes);
|
---|
193 | }
|
---|
194 |
|
---|
195 | /** Duplicates an element */
|
---|
196 | public static Element duplicateElementNS(Document owner, Element element, String namespace_uri, boolean with_attributes)
|
---|
197 | {
|
---|
198 | Element duplicate;
|
---|
199 | if (namespace_uri == null)
|
---|
200 | {
|
---|
201 | duplicate = owner.createElement(element.getTagName());
|
---|
202 | }
|
---|
203 | else
|
---|
204 | {
|
---|
205 | duplicate = owner.createElementNS(namespace_uri, element.getTagName());
|
---|
206 | }
|
---|
207 | // Copy element attributes
|
---|
208 | if (with_attributes)
|
---|
209 | {
|
---|
210 | NamedNodeMap attributes = element.getAttributes();
|
---|
211 | for (int i = 0; i < attributes.getLength(); i++)
|
---|
212 | {
|
---|
213 | Node attribute = attributes.item(i);
|
---|
214 | duplicate.setAttribute(attribute.getNodeName(), attribute.getNodeValue());
|
---|
215 | }
|
---|
216 | }
|
---|
217 |
|
---|
218 | // Copy element children
|
---|
219 | NodeList children = element.getChildNodes();
|
---|
220 | for (int i = 0; i < children.getLength(); i++)
|
---|
221 | {
|
---|
222 | Node child = children.item(i);
|
---|
223 | duplicate.appendChild(owner.importNode(child, true));
|
---|
224 | }
|
---|
225 |
|
---|
226 | return duplicate;
|
---|
227 | }
|
---|
228 |
|
---|
229 | /** Remove all of the child nodes from a certain node. */
|
---|
230 | static final public void clear(Node node)
|
---|
231 | {
|
---|
232 | while (node.hasChildNodes())
|
---|
233 | {
|
---|
234 | node.removeChild(node.getFirstChild());
|
---|
235 | }
|
---|
236 | }
|
---|
237 |
|
---|
238 | static public ArrayList getChildElementsByTagName(Element parent_element, String element_name)
|
---|
239 | {
|
---|
240 | ArrayList child_elements = new ArrayList();
|
---|
241 |
|
---|
242 | NodeList children_nodelist = parent_element.getChildNodes();
|
---|
243 | for (int i = 0; i < children_nodelist.getLength(); i++)
|
---|
244 | {
|
---|
245 | Node child_node = children_nodelist.item(i);
|
---|
246 | if (child_node.getNodeType() == Node.ELEMENT_NODE && child_node.getNodeName().equals(element_name))
|
---|
247 | {
|
---|
248 | child_elements.add(child_node);
|
---|
249 | }
|
---|
250 | }
|
---|
251 |
|
---|
252 | return child_elements;
|
---|
253 | }
|
---|
254 |
|
---|
255 | static public String getElementTextValue(Element element)
|
---|
256 | {
|
---|
257 | // Find the first text node child
|
---|
258 | NodeList children_nodelist = element.getChildNodes();
|
---|
259 | for (int i = 0; i < children_nodelist.getLength(); i++)
|
---|
260 | {
|
---|
261 | Node child_node = children_nodelist.item(i);
|
---|
262 | if (child_node.getNodeType() == Node.TEXT_NODE)
|
---|
263 | {
|
---|
264 | return child_node.getNodeValue();
|
---|
265 | }
|
---|
266 | }
|
---|
267 |
|
---|
268 | // None found
|
---|
269 | return "";
|
---|
270 | }
|
---|
271 |
|
---|
272 | /**
|
---|
273 | * Method to retrieve the value of a given node.
|
---|
274 | *
|
---|
275 | * @param element
|
---|
276 | * The <strong>Element</strong> whose value we wish to find. Soon
|
---|
277 | * to be deprecated!
|
---|
278 | */
|
---|
279 | static final public String getValue(Node element)
|
---|
280 | {
|
---|
281 | if (element == null)
|
---|
282 | {
|
---|
283 | return "";
|
---|
284 | }
|
---|
285 | // If we've been given a subject node first retrieve its value node.
|
---|
286 | if (element.getNodeName().equals("Subject"))
|
---|
287 | {
|
---|
288 | element = getNodeFromNamed(element, "Value");
|
---|
289 | }
|
---|
290 | // If we've got a value node, then reconstruct the text. Remember that DOM will split text over 256 characters into several text nodes
|
---|
291 | if (element != null && element.hasChildNodes())
|
---|
292 | {
|
---|
293 | StringBuffer text_buffer = new StringBuffer();
|
---|
294 | NodeList text_nodes = element.getChildNodes();
|
---|
295 | for (int i = 0; i < text_nodes.getLength(); i++)
|
---|
296 | {
|
---|
297 | Node possible_text = text_nodes.item(i);
|
---|
298 | if (possible_text.getNodeName().equals(StaticStrings.TEXT_NODE))
|
---|
299 | {
|
---|
300 | text_buffer.append(possible_text.getNodeValue());
|
---|
301 | }
|
---|
302 | }
|
---|
303 | return text_buffer.toString();
|
---|
304 | }
|
---|
305 | return "";
|
---|
306 | }
|
---|
307 |
|
---|
308 | /**
|
---|
309 | * Method to retrieve from the node given, a certain child node with the
|
---|
310 | * specified name.
|
---|
311 | *
|
---|
312 | * @param parent
|
---|
313 | * The <strong>Node</strong> whose children should be searched.
|
---|
314 | * @param name
|
---|
315 | * The required nodes name as a <strong>String</strong>.
|
---|
316 | * @return The requested <strong>Node</strong> if it is found, <i>null</i>
|
---|
317 | * otherwise. Soon to be deprecated!
|
---|
318 | */
|
---|
319 | static final public Node getNodeFromNamed(Node parent, String name)
|
---|
320 | {
|
---|
321 | Node child = null;
|
---|
322 | for (Node i = parent.getFirstChild(); i != null && child == null; i = i.getNextSibling())
|
---|
323 | {
|
---|
324 | if (i.getNodeName().equals(name))
|
---|
325 | {
|
---|
326 | child = i;
|
---|
327 | }
|
---|
328 | }
|
---|
329 | return child;
|
---|
330 | }
|
---|
331 |
|
---|
332 | static final public String WELLFORMED = "well-formed !";
|
---|
333 | static final public String NOTWELLFORMED = "not well-formed";
|
---|
334 | 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'>";
|
---|
335 | static final private String FOOTER = "</collectionConfig>";
|
---|
336 |
|
---|
337 |
|
---|
338 | public static Document getDOM(String xml_str)
|
---|
339 | {
|
---|
340 | Document doc = null;
|
---|
341 | try {
|
---|
342 |
|
---|
343 | DocumentBuilder db = DocumentBuilderFactory.newInstance().newDocumentBuilder();
|
---|
344 | InputSource is = new InputSource();
|
---|
345 | is.setCharacterStream(new StringReader(xml_str));
|
---|
346 | doc = db.parse(is);
|
---|
347 |
|
---|
348 | } catch (Exception e) {
|
---|
349 | e.printStackTrace();
|
---|
350 | }
|
---|
351 | return doc;
|
---|
352 | }
|
---|
353 |
|
---|
354 | public static String parse(String xml_str)
|
---|
355 | {
|
---|
356 | String validation_msg = WELLFORMED;
|
---|
357 | xml_str = HEADER + xml_str + FOOTER;
|
---|
358 | try
|
---|
359 | {
|
---|
360 | SAXParserFactory factory = SAXParserFactory.newInstance();
|
---|
361 | factory.setNamespaceAware(true);
|
---|
362 | //factory.setValidating (true);
|
---|
363 | SAXParser parser = factory.newSAXParser();
|
---|
364 | InputSource iSource = new InputSource(new StringReader(xml_str));
|
---|
365 | // parser.parse (iSource, new DefaultHandler ());
|
---|
366 |
|
---|
367 | org.xml.sax.XMLReader reader = parser.getXMLReader();
|
---|
368 | reader.setContentHandler(new DefaultHandler());
|
---|
369 | reader.setErrorHandler(new DefaultHandler());
|
---|
370 | reader.parse(iSource);
|
---|
371 | }
|
---|
372 | catch (FactoryConfigurationError e)
|
---|
373 | {
|
---|
374 | validation_msg = "unable to get a document builder factory";
|
---|
375 | }
|
---|
376 | catch (ParserConfigurationException e)
|
---|
377 | {
|
---|
378 | validation_msg = "unable to configure parser";
|
---|
379 | }
|
---|
380 | catch (SAXParseException e)
|
---|
381 | {
|
---|
382 | validation_msg = NOTWELLFORMED + getLocationString(e) + e.getMessage();
|
---|
383 | }
|
---|
384 | catch (SAXException e)
|
---|
385 | {
|
---|
386 | validation_msg += " Fatal error: " + e.toString();
|
---|
387 | }
|
---|
388 | catch (IOException e)
|
---|
389 | {
|
---|
390 | validation_msg = "Unable to read the input, i/o error";
|
---|
391 | }
|
---|
392 |
|
---|
393 | return validation_msg;
|
---|
394 | }
|
---|
395 |
|
---|
396 | //In this method, the parsed string xml_str is not wrapped by the header and footer strings.
|
---|
397 | public static String parseDOM(String xml_str)
|
---|
398 | {
|
---|
399 | String validation_msg = WELLFORMED;
|
---|
400 |
|
---|
401 | try
|
---|
402 | {
|
---|
403 | SAXParserFactory factory = SAXParserFactory.newInstance();
|
---|
404 | factory.setNamespaceAware(true);
|
---|
405 | //factory.setValidating (true);
|
---|
406 | SAXParser parser = factory.newSAXParser();
|
---|
407 | InputSource iSource = new InputSource(new StringReader(xml_str));
|
---|
408 | // parser.parse (iSource, new DefaultHandler ());
|
---|
409 |
|
---|
410 | org.xml.sax.XMLReader reader = parser.getXMLReader();
|
---|
411 | reader.setContentHandler(new DefaultHandler());
|
---|
412 | reader.setErrorHandler(new DefaultHandler());
|
---|
413 | reader.parse(iSource);
|
---|
414 | }
|
---|
415 | catch (FactoryConfigurationError e)
|
---|
416 | {
|
---|
417 | validation_msg = "unable to get a document builder factory";
|
---|
418 | }
|
---|
419 | catch (ParserConfigurationException e)
|
---|
420 | {
|
---|
421 | validation_msg = "unable to configure parser";
|
---|
422 | }
|
---|
423 | catch (SAXParseException e)
|
---|
424 | {
|
---|
425 | validation_msg = NOTWELLFORMED + getLocationString(e) + e.getMessage();
|
---|
426 | }
|
---|
427 | catch (SAXException e)
|
---|
428 | {
|
---|
429 | validation_msg += " " + e.toString();
|
---|
430 | }
|
---|
431 | catch (IOException e)
|
---|
432 | {
|
---|
433 | validation_msg = "Unable to read the input, i/o error";
|
---|
434 | }
|
---|
435 |
|
---|
436 | return validation_msg;
|
---|
437 | }
|
---|
438 |
|
---|
439 | public static String parse(File xml_file)
|
---|
440 | {
|
---|
441 | String validation_msg = WELLFORMED;
|
---|
442 |
|
---|
443 | try
|
---|
444 | {
|
---|
445 | SAXParserFactory factory = SAXParserFactory.newInstance();
|
---|
446 | factory.setNamespaceAware(true);
|
---|
447 | //factory.setValidating (true);
|
---|
448 | SAXParser parser = factory.newSAXParser();
|
---|
449 | FileReader r = new FileReader(xml_file);
|
---|
450 | InputSource iSource = new InputSource(r);
|
---|
451 | XMLReader reader = parser.getXMLReader();
|
---|
452 | reader.setContentHandler(new DefaultHandler());
|
---|
453 | reader.setErrorHandler(new DefaultHandler());
|
---|
454 | reader.parse(iSource);
|
---|
455 | }
|
---|
456 | catch (FactoryConfigurationError e)
|
---|
457 | {
|
---|
458 | validation_msg = "unable to get a document builder factory";
|
---|
459 | }
|
---|
460 | catch (ParserConfigurationException e)
|
---|
461 | {
|
---|
462 | validation_msg = "unable to configure parser";
|
---|
463 | }
|
---|
464 | catch (SAXParseException e)
|
---|
465 | {
|
---|
466 | validation_msg = NOTWELLFORMED + getLocationString(e) + e.getMessage();
|
---|
467 | }
|
---|
468 | catch (SAXException e)
|
---|
469 | {
|
---|
470 | validation_msg += " Fatal error: " + e.toString();
|
---|
471 | }
|
---|
472 | catch (IOException e)
|
---|
473 | {
|
---|
474 | validation_msg = "Unable to read the input, i/o error";
|
---|
475 | }
|
---|
476 |
|
---|
477 | return validation_msg;
|
---|
478 | }
|
---|
479 |
|
---|
480 | /** Returns a string of the location. */
|
---|
481 | private static String getLocationString(SAXParseException ex)
|
---|
482 | {
|
---|
483 | StringBuffer str = new StringBuffer();
|
---|
484 |
|
---|
485 | String systemId = ex.getSystemId();
|
---|
486 | if (systemId != null)
|
---|
487 | {
|
---|
488 | int index = systemId.lastIndexOf('/');
|
---|
489 | if (index != -1)
|
---|
490 | systemId = systemId.substring(index + 1);
|
---|
491 | str.append(systemId);
|
---|
492 | }
|
---|
493 | str.append("(line ");
|
---|
494 | str.append(ex.getLineNumber() - 1);
|
---|
495 | str.append(", column ");
|
---|
496 | str.append(ex.getColumnNumber());
|
---|
497 | str.append("): ");
|
---|
498 |
|
---|
499 | return str.toString();
|
---|
500 |
|
---|
501 | } // getLocationString(SAXParseException):String
|
---|
502 |
|
---|
503 | /** Parse an XML document from a given file path */
|
---|
504 | static public Document parseXMLFile(String xml_file_path, boolean use_class_loader)
|
---|
505 | {
|
---|
506 | if (use_class_loader == true)
|
---|
507 | {
|
---|
508 | InputStream is = JarTools.getResourceAsStream("/" + xml_file_path);
|
---|
509 | if (is != null)
|
---|
510 | {
|
---|
511 | return parseXML(is);
|
---|
512 | }
|
---|
513 | }
|
---|
514 |
|
---|
515 | // Try the file outside the classes directory
|
---|
516 | return parseXMLFile(new File(xml_file_path));
|
---|
517 | }
|
---|
518 |
|
---|
519 | /** Parse an XML document from a given file */
|
---|
520 | static public Document parseXMLFile(File xml_file)
|
---|
521 | {
|
---|
522 | // No file? No point trying!
|
---|
523 | if (xml_file.exists() == false)
|
---|
524 | {
|
---|
525 | return null;
|
---|
526 | }
|
---|
527 |
|
---|
528 | try
|
---|
529 | {
|
---|
530 | return parseXML(new FileInputStream(xml_file));
|
---|
531 | }
|
---|
532 | catch (Exception exception)
|
---|
533 | {
|
---|
534 | DebugStream.printStackTrace(exception);
|
---|
535 | return null;
|
---|
536 | }
|
---|
537 | }
|
---|
538 |
|
---|
539 | /** Parse an XML document from a given input stream */
|
---|
540 | static public Document parseXML(InputStream xml_input_stream)
|
---|
541 | {
|
---|
542 | Document document = null;
|
---|
543 |
|
---|
544 | try
|
---|
545 | {
|
---|
546 | InputStreamReader isr = new InputStreamReader(xml_input_stream, "UTF-8");
|
---|
547 | document = parseXML(isr);
|
---|
548 | isr.close();
|
---|
549 | xml_input_stream.close();
|
---|
550 | }
|
---|
551 | catch (Exception exception)
|
---|
552 | {
|
---|
553 | DebugStream.printStackTrace(exception);
|
---|
554 | }
|
---|
555 |
|
---|
556 | return document;
|
---|
557 | }
|
---|
558 |
|
---|
559 | /** Parse an XML document from a given reader */
|
---|
560 | static public Document parseXML(Reader xml_reader)
|
---|
561 | {
|
---|
562 | Document document = null;
|
---|
563 |
|
---|
564 | // If debugging, the following will store the XML contents to be parsed,
|
---|
565 | // which can then be inspected upon encountering a SAXException (need to run GLI with -debug on)
|
---|
566 | String xmlContents = "";
|
---|
567 |
|
---|
568 | try
|
---|
569 | {
|
---|
570 | Reader reader = null;
|
---|
571 |
|
---|
572 | // (1) By default, GLI will remove any contents preceeding (and invalidating)
|
---|
573 | // the XML and present these lines separately to the user
|
---|
574 | if (!DebugStream.isDebuggingEnabled())
|
---|
575 | {
|
---|
576 | try
|
---|
577 | {
|
---|
578 | reader = new BufferedReader(new RemoveContentBeforeRootElementXMLReader(xml_reader));
|
---|
579 | }
|
---|
580 | catch (Exception e)
|
---|
581 | {
|
---|
582 | System.err.println("Exception while wrapping the reader in parseXML(Reader)");
|
---|
583 | e.printStackTrace();
|
---|
584 | }
|
---|
585 | }
|
---|
586 |
|
---|
587 | // (2) If we are running GLI in debug mode:
|
---|
588 | // In case parsing exceptions are thrown (SAX Exceptions), we want to get some
|
---|
589 | // idea of where things went wrong. This will print the "XML" contents to either
|
---|
590 | // system.out (if debugging is off) or to the DebugStream otherwise.
|
---|
591 | // We need to read the XML twice to know the line where things went wrong, so
|
---|
592 | // do the additional reading only if we're debugging
|
---|
593 | else
|
---|
594 | {
|
---|
595 | StringBuffer buf = new StringBuffer();
|
---|
596 | char[] buffer = new char[500];
|
---|
597 | int numCharsRead = xml_reader.read(buffer, 0, buffer.length);
|
---|
598 | while (numCharsRead != -1)
|
---|
599 | {
|
---|
600 | buf.append(buffer, 0, numCharsRead);
|
---|
601 | numCharsRead = xml_reader.read(buffer, 0, buffer.length);
|
---|
602 | }
|
---|
603 | xmlContents = buf.toString();
|
---|
604 | xml_reader.close(); // closing the old Reader
|
---|
605 | xml_reader = null;
|
---|
606 | buffer = null;
|
---|
607 | buf = null;
|
---|
608 | // we need a Reader to parse the same contents as the Reader that was just closed
|
---|
609 | reader = new BufferedReader(new StringReader(xmlContents));
|
---|
610 | //System.err.println("xmlContents:\n" + xmlContents);
|
---|
611 | }
|
---|
612 |
|
---|
613 | // (2) The actual XML parsing
|
---|
614 | InputSource isc = new InputSource(reader);
|
---|
615 | DOMParser parser = new DOMParser();
|
---|
616 | parser.setFeature("http://xml.org/sax/features/validation", false);
|
---|
617 | parser.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
|
---|
618 | // May or may not be ignored, the documentation for Xerces is contradictory. If it works then parsing -should- be faster.
|
---|
619 | parser.setFeature("http://apache.org/xml/features/dom/defer-node-expansion", true);
|
---|
620 | parser.setFeature("http://apache.org/xml/features/dom/include-ignorable-whitespace", false);
|
---|
621 | parser.setEntityResolver(new GLIEntityResolver());
|
---|
622 | parser.parse(isc);
|
---|
623 | document = parser.getDocument();
|
---|
624 |
|
---|
625 | }
|
---|
626 | catch (SAXParseException e)
|
---|
627 | {
|
---|
628 | showXMLParseFailureLine(e, xmlContents);
|
---|
629 | }
|
---|
630 | catch (SAXException exception)
|
---|
631 | {
|
---|
632 | System.err.println("SAX exception: " + exception.getMessage());
|
---|
633 | if (DebugStream.isDebuggingEnabled())
|
---|
634 | {
|
---|
635 | DebugStream.println("Encountered a SAX exception when parsing the following:\n*********START\n" + xmlContents + "\n************END\n");
|
---|
636 | // Exit to let the user view the erroneous line/xml before it goes past the screen buffer?
|
---|
637 | DebugStream.println("Debug mode: Exiting the program as there was trouble parsing the XML...");
|
---|
638 | System.exit(-1);
|
---|
639 | }
|
---|
640 | // else, not running in debug mode, so don't exit after exception
|
---|
641 | System.out.println("***Turn debugging on (run GLI with -debug) to view the XML contents that could not be parsed.");
|
---|
642 | DebugStream.printStackTrace(exception);
|
---|
643 | }
|
---|
644 | catch (Exception exception)
|
---|
645 | {
|
---|
646 | DebugStream.printStackTrace(exception);
|
---|
647 | }
|
---|
648 |
|
---|
649 | return document;
|
---|
650 | }
|
---|
651 |
|
---|
652 | /**
|
---|
653 | * Displays the line (string) where the SAXParseException occurred, given a
|
---|
654 | * String of the entire xml that was being parsed and the SAXParseException
|
---|
655 | * object that was caught. The messages are printed to DebugStream, so run
|
---|
656 | * GLI/FLI with -debug to view this output.
|
---|
657 | *
|
---|
658 | * @param xmlContents
|
---|
659 | * is the entire xml that was being parsed when the exception
|
---|
660 | * occurred
|
---|
661 | * @param e
|
---|
662 | * is the SAXParseException object that was thrown upon parsing
|
---|
663 | * the xmlContents.
|
---|
664 | */
|
---|
665 | public static void showXMLParseFailureLine(SAXParseException e, String xmlContents)
|
---|
666 | {
|
---|
667 |
|
---|
668 | // There should be no characters at all that preceed the <?xml>... bit.
|
---|
669 | // The first check is for starting spaces:
|
---|
670 | if (xmlContents.startsWith("\n") || xmlContents.startsWith(" ") || xmlContents.startsWith("\t"))
|
---|
671 | {
|
---|
672 | DebugStream.println("ERROR: illegal start of XML. Space/tab/newline should not preceed xml declaration.\n");
|
---|
673 | DebugStream.println("xmlContents (length is " + xmlContents.length() + "):\n" + xmlContents);
|
---|
674 | return; // nothing more to do, first error identified
|
---|
675 | }
|
---|
676 |
|
---|
677 | // the actual line (String literal) where parsing failed and the SAXParseException occurred.
|
---|
678 | String line = "";
|
---|
679 | int linenumber = e.getLineNumber();
|
---|
680 | DebugStream.print("\n****SAXParseException on LINE NUMBER: " + linenumber);
|
---|
681 | if (DebugStream.isDebuggingEnabled())
|
---|
682 | {
|
---|
683 | if (linenumber != -1)
|
---|
684 | {
|
---|
685 | String[] lines = xmlContents.split("\n");
|
---|
686 | if (lines.length > 0)
|
---|
687 | {
|
---|
688 | DebugStream.println(" (number of lines: " + lines.length + ")");
|
---|
689 | if (lines.length >= linenumber)
|
---|
690 | {
|
---|
691 | line = lines[linenumber - 1];
|
---|
692 | }
|
---|
693 | else
|
---|
694 | { // error is past the last line
|
---|
695 | line = "Error is past the last line (" + lines.length + "): " + lines[lines.length - 1];
|
---|
696 | }
|
---|
697 | }
|
---|
698 | else
|
---|
699 | {
|
---|
700 | DebugStream.print("\n");
|
---|
701 | }
|
---|
702 | lines = null;
|
---|
703 |
|
---|
704 | DebugStream.println("The parsing error occurred on this line:\n***********START\n" + line + "\n***********END");
|
---|
705 | DebugStream.println("SAXParseException message: " + e.getMessage() + "\n");
|
---|
706 |
|
---|
707 | // Uncomment if you want to print out the entire contents of the XML doc:
|
---|
708 | //DebugStream.println("\n\nThis was the XML:\n*********START\n"
|
---|
709 | // + xmlContents + "\n************END\n");
|
---|
710 | }
|
---|
711 | else
|
---|
712 | { // no particular line number, print out all the xml so debugger can inspect it
|
---|
713 | DebugStream.println("Encountered a SAX exception when parsing the following:\n*********START\n" + xmlContents + "\n************END\n");
|
---|
714 | }
|
---|
715 | // Exit to let the user view the erroneous line/xml before it goes past the screen buffer?
|
---|
716 | DebugStream.println("\nDebug mode: Exiting the program as there was trouble parsing the XML...");
|
---|
717 | System.exit(-1);
|
---|
718 | }
|
---|
719 | else
|
---|
720 | { // not running in debug mode
|
---|
721 | System.out.println("***Turn debugging on (run GLI with -debug) to view the XML contents/line that could not be parsed.");
|
---|
722 | }
|
---|
723 | }
|
---|
724 |
|
---|
725 | static public StringBuffer readXMLStream(InputStream input_stream)
|
---|
726 | {
|
---|
727 | StringBuffer xml = new StringBuffer("");
|
---|
728 |
|
---|
729 | try
|
---|
730 | {
|
---|
731 | InputStreamReader isr = new InputStreamReader(input_stream, "UTF-8");
|
---|
732 | BufferedReader buffered_in = new BufferedReader(isr);
|
---|
733 |
|
---|
734 | String line = "";
|
---|
735 | boolean xml_content = false;
|
---|
736 | while ((line = buffered_in.readLine()) != null)
|
---|
737 | {
|
---|
738 | if (xml_content)
|
---|
739 | {
|
---|
740 | xml.append(line);
|
---|
741 | xml.append("\n");
|
---|
742 | }
|
---|
743 | else if (line.trim().startsWith("<?xml"))
|
---|
744 | {
|
---|
745 | xml_content = true;
|
---|
746 | xml.append(line);
|
---|
747 | xml.append("\n");
|
---|
748 | }
|
---|
749 | else
|
---|
750 | {
|
---|
751 | System.err.println(line);
|
---|
752 | }
|
---|
753 | }
|
---|
754 | buffered_in = null;
|
---|
755 | }
|
---|
756 | catch (Exception error)
|
---|
757 | {
|
---|
758 | System.err.println("Failed when trying to parse XML stream");
|
---|
759 | error.printStackTrace();
|
---|
760 | }
|
---|
761 |
|
---|
762 | return xml;
|
---|
763 | }
|
---|
764 |
|
---|
765 | /**
|
---|
766 | * Removes characters that are invalid in XML (see
|
---|
767 | * http://www.w3.org/TR/2000/REC-xml-20001006#charsets)
|
---|
768 | */
|
---|
769 | static public String removeInvalidCharacters(String text)
|
---|
770 | {
|
---|
771 | char[] safe_characters = new char[text.length()];
|
---|
772 | int j = 0;
|
---|
773 |
|
---|
774 | char[] raw_characters = new char[text.length()];
|
---|
775 | text.getChars(0, text.length(), raw_characters, 0);
|
---|
776 | for (int i = 0; i < raw_characters.length; i++)
|
---|
777 | {
|
---|
778 | char character = raw_characters[i];
|
---|
779 | if ((character >= 0x20 && character <= 0xD7FF) || character == 0x09 || character == 0x0A || character == 0x0D || (character >= 0xE000 && character <= 0xFFFD) || (character >= 0x10000 && character <= 0x10FFFF))
|
---|
780 | {
|
---|
781 | safe_characters[j] = character;
|
---|
782 | j++;
|
---|
783 | }
|
---|
784 | }
|
---|
785 |
|
---|
786 | return new String(safe_characters, 0, j);
|
---|
787 | }
|
---|
788 |
|
---|
789 | static public void setElementTextValue(Element element, String text)
|
---|
790 | {
|
---|
791 | // Remove all text node children
|
---|
792 | NodeList children_nodelist = element.getChildNodes();
|
---|
793 | for (int i = children_nodelist.getLength() - 1; i >= 0; i--)
|
---|
794 | {
|
---|
795 | Node child_node = children_nodelist.item(i);
|
---|
796 | if (child_node.getNodeType() == Node.TEXT_NODE)
|
---|
797 | {
|
---|
798 | element.removeChild(child_node);
|
---|
799 | }
|
---|
800 | }
|
---|
801 |
|
---|
802 | // Add a new text node
|
---|
803 | if (text != null)
|
---|
804 | {
|
---|
805 | element.appendChild(element.getOwnerDocument().createTextNode(text));
|
---|
806 | }
|
---|
807 | }
|
---|
808 |
|
---|
809 | /**
|
---|
810 | * Set the #text node value of some element.
|
---|
811 | *
|
---|
812 | * @param element
|
---|
813 | * the Element whose value we wish to set
|
---|
814 | * @param value
|
---|
815 | * the new value for the element as a String Soon to be
|
---|
816 | * deprecated!
|
---|
817 | */
|
---|
818 | static final public void setValue(Element element, String value)
|
---|
819 | {
|
---|
820 | // Remove any existing child node(s)
|
---|
821 | clear(element);
|
---|
822 | // Add new text node.
|
---|
823 | if (value != null)
|
---|
824 | {
|
---|
825 | element.appendChild(element.getOwnerDocument().createTextNode(value));
|
---|
826 | }
|
---|
827 | }
|
---|
828 |
|
---|
829 | static public void indentXML(Element elem, int depth)
|
---|
830 | {
|
---|
831 | Document doc = elem.getOwnerDocument();
|
---|
832 |
|
---|
833 | String startIndentString = "\n";
|
---|
834 | for (int i = 0; i < depth; i++)
|
---|
835 | {
|
---|
836 | startIndentString += "\t";
|
---|
837 | }
|
---|
838 | Node startTextNode = doc.createTextNode(startIndentString);
|
---|
839 |
|
---|
840 | String endIndentString = "\n";
|
---|
841 | for (int i = 0; i < depth - 1; i++)
|
---|
842 | {
|
---|
843 | endIndentString += "\t";
|
---|
844 | }
|
---|
845 | Node endTextNode = doc.createTextNode(endIndentString);
|
---|
846 |
|
---|
847 | boolean found = false;
|
---|
848 | Node child = elem.getFirstChild();
|
---|
849 | while (child != null)
|
---|
850 | {
|
---|
851 | // first clear all empty text nodes (those containing space characters like \n,\r,\t and such)
|
---|
852 | if(child.getNodeType() == Node.TEXT_NODE && child.getNodeValue().matches("^\\s*$"))
|
---|
853 | {
|
---|
854 | Node spaceTextNode = child;
|
---|
855 | child = child.getNextSibling();
|
---|
856 | elem.removeChild(spaceTextNode);
|
---|
857 |
|
---|
858 | if(child == null) break;
|
---|
859 | }
|
---|
860 |
|
---|
861 | // now process normal element nodes as intended
|
---|
862 | if (child.getNodeType() == Node.ELEMENT_NODE)
|
---|
863 | {
|
---|
864 | found = true;
|
---|
865 | break;
|
---|
866 | }
|
---|
867 | child = child.getNextSibling();
|
---|
868 | }
|
---|
869 |
|
---|
870 | if (found)
|
---|
871 | {
|
---|
872 | elem.appendChild(endTextNode);
|
---|
873 | }
|
---|
874 |
|
---|
875 | child = elem.getFirstChild();
|
---|
876 | while (child != null)
|
---|
877 | {
|
---|
878 | // Again, need to first clear all empty text nodes (those containing space characters like \n,\r,\t and such)
|
---|
879 | // because the first while loop above would break out when it found an element node and wouldn't have got rid
|
---|
880 | // of all the empty text nodes yet.
|
---|
881 | // This time, beware not to delete the special end and start empty textnodes just added, since
|
---|
882 | // they've been created and inserted specifically.
|
---|
883 | if(child != endTextNode && child != startTextNode
|
---|
884 | && child.getNodeType() == Node.TEXT_NODE && child.getNodeValue().matches("^\\s*$"))
|
---|
885 | {
|
---|
886 | Node spaceTextNode = child;
|
---|
887 | child = child.getNextSibling();
|
---|
888 | elem.removeChild(spaceTextNode);
|
---|
889 |
|
---|
890 | if(child == null) break;
|
---|
891 | }
|
---|
892 |
|
---|
893 | // go back to processing normal element nodes as intended
|
---|
894 | if (child.getNodeType() == Node.ELEMENT_NODE)
|
---|
895 | {
|
---|
896 | elem.insertBefore(startTextNode.cloneNode(false), child);
|
---|
897 | indentXML((Element) child, depth + 1);
|
---|
898 | }
|
---|
899 | child = child.getNextSibling();
|
---|
900 | }
|
---|
901 | }
|
---|
902 |
|
---|
903 | /**
|
---|
904 | * Write an XML document to a given file with the text node of the specified
|
---|
905 | * element unescaped
|
---|
906 | */
|
---|
907 | static public void writeXMLFile(File xml_file, Document document, String[] nonEscapingTagNames)
|
---|
908 | {
|
---|
909 | indentXML(document.getDocumentElement(), 1);
|
---|
910 | try
|
---|
911 | {
|
---|
912 | OutputStream os = new FileOutputStream(xml_file);
|
---|
913 | // Create an output format for our document.
|
---|
914 | OutputFormat f = new OutputFormat(document);
|
---|
915 | f.setEncoding("UTF-8");
|
---|
916 | f.setIndenting(true);
|
---|
917 | f.setLineWidth(0); // Why isn't this working!
|
---|
918 | f.setPreserveSpace(true);
|
---|
919 | if (nonEscapingTagNames != null)
|
---|
920 | {
|
---|
921 | f.setNonEscapingElements(nonEscapingTagNames);
|
---|
922 | }
|
---|
923 | // Create the necessary writer stream for serialization.
|
---|
924 | OutputStreamWriter osw = new OutputStreamWriter(os, "UTF-8");
|
---|
925 | Writer w = new BufferedWriter(osw);
|
---|
926 | // Generate a new serializer from the above.
|
---|
927 | XMLSerializer s = new XMLSerializer(w, f);
|
---|
928 | s.asDOMSerializer();
|
---|
929 | // Finally serialize the document to file.
|
---|
930 | s.serialize(document);
|
---|
931 | // And close.
|
---|
932 | os.close();
|
---|
933 | }
|
---|
934 | catch (Exception exception)
|
---|
935 | {
|
---|
936 | DebugStream.printStackTrace(exception);
|
---|
937 | }
|
---|
938 | }
|
---|
939 |
|
---|
940 | /** Write an XML document to a given file */
|
---|
941 | static public void writeXMLFile(File xml_file, Document document)
|
---|
942 | {
|
---|
943 | writeXMLFile(xml_file, document, null);
|
---|
944 | }
|
---|
945 |
|
---|
946 | public static void printXMLNode(Node e)
|
---|
947 | {
|
---|
948 | printXMLNode(e, 0);
|
---|
949 | }
|
---|
950 |
|
---|
951 | public static void printXMLNode(Node e, int depth)
|
---|
952 | { //recursive method call using DOM API...
|
---|
953 |
|
---|
954 | for (int i = 0; i < depth; i++)
|
---|
955 | System.out.print(' ');
|
---|
956 |
|
---|
957 | if (e.getNodeType() == Node.TEXT_NODE)
|
---|
958 | {
|
---|
959 | //System.out.println("text") ;
|
---|
960 | if (e.getNodeValue() != "")
|
---|
961 | {
|
---|
962 | System.out.println(e.getNodeValue());
|
---|
963 | }
|
---|
964 | return;
|
---|
965 | }
|
---|
966 |
|
---|
967 | System.out.print('<');
|
---|
968 | System.out.print(e.getNodeName());
|
---|
969 | NamedNodeMap attrs = e.getAttributes();
|
---|
970 | if (attrs != null)
|
---|
971 | {
|
---|
972 | for (int i = 0; i < attrs.getLength(); i++)
|
---|
973 | {
|
---|
974 | Node attr = attrs.item(i);
|
---|
975 | System.out.print(' ');
|
---|
976 | System.out.print(attr.getNodeName());
|
---|
977 | System.out.print("=\"");
|
---|
978 | System.out.print(attr.getNodeValue());
|
---|
979 | System.out.print('"');
|
---|
980 | }
|
---|
981 | }
|
---|
982 | NodeList children = e.getChildNodes();
|
---|
983 |
|
---|
984 | if (children == null || children.getLength() == 0)
|
---|
985 | System.out.println("/>");
|
---|
986 | else
|
---|
987 | {
|
---|
988 |
|
---|
989 | System.out.println('>');
|
---|
990 |
|
---|
991 | int len = children.getLength();
|
---|
992 | for (int i = 0; i < len; i++)
|
---|
993 | {
|
---|
994 | printXMLNode(children.item(i), depth + 1);
|
---|
995 | }
|
---|
996 |
|
---|
997 | for (int i = 0; i < depth; i++)
|
---|
998 | System.out.print(' ');
|
---|
999 |
|
---|
1000 | System.out.println("</" + e.getNodeName() + ">");
|
---|
1001 | }
|
---|
1002 |
|
---|
1003 | }
|
---|
1004 |
|
---|
1005 | public static String xmlNodeToString(Node e)
|
---|
1006 | {
|
---|
1007 | StringBuffer sb = new StringBuffer("");
|
---|
1008 | xmlNodeToString(sb, e, true, "\t", 2);
|
---|
1009 | return sb.toString();
|
---|
1010 | }
|
---|
1011 |
|
---|
1012 | public static void xmlNodeToString(StringBuffer sb, Node e, boolean indent, String indentString, int depth)
|
---|
1013 | {
|
---|
1014 |
|
---|
1015 | if (e.getNodeType() == Node.CDATA_SECTION_NODE)
|
---|
1016 | {
|
---|
1017 | if (e.getNodeValue() != "")
|
---|
1018 | {
|
---|
1019 | String text = e.getNodeValue();
|
---|
1020 | sb.append("<![CDATA[");
|
---|
1021 | sb.append(text);
|
---|
1022 | sb.append("]]>");
|
---|
1023 | }
|
---|
1024 | return;
|
---|
1025 | }
|
---|
1026 |
|
---|
1027 | if (e.getNodeType() == Node.TEXT_NODE)
|
---|
1028 | {
|
---|
1029 | if (e.getNodeValue() != "")
|
---|
1030 | {
|
---|
1031 | String text = e.getNodeValue();
|
---|
1032 | text = text.replaceAll("&", "&").replaceAll("<", "<").replaceAll(">", ">").replaceAll("[\\n\\r\\t\\s]*$", "");
|
---|
1033 | for (Character c : text.toCharArray())
|
---|
1034 | {
|
---|
1035 | if (c.equals('\n'))
|
---|
1036 | {
|
---|
1037 | text = text.replaceAll("^[\\n\\r\\t\\s]*", "");
|
---|
1038 | break;
|
---|
1039 | }
|
---|
1040 |
|
---|
1041 | if (!Character.isWhitespace(c))
|
---|
1042 | {
|
---|
1043 | break;
|
---|
1044 | }
|
---|
1045 | }
|
---|
1046 | sb.append(text);
|
---|
1047 | }
|
---|
1048 | return;
|
---|
1049 | }
|
---|
1050 |
|
---|
1051 | if (e.getNodeType() == Node.COMMENT_NODE)
|
---|
1052 | {
|
---|
1053 | if (e.getNodeValue() != "")
|
---|
1054 | {
|
---|
1055 | sb.append("<!--\n" + e.getNodeValue().trim() + "\n-->\n");
|
---|
1056 | }
|
---|
1057 | return;
|
---|
1058 | }
|
---|
1059 |
|
---|
1060 | if (indent)
|
---|
1061 | {
|
---|
1062 | for (int i = 0; i < depth; i++)
|
---|
1063 | {
|
---|
1064 | sb.append(indentString);
|
---|
1065 | }
|
---|
1066 | }
|
---|
1067 |
|
---|
1068 | sb.append('<');
|
---|
1069 | sb.append(e.getNodeName());
|
---|
1070 | NamedNodeMap attrs = e.getAttributes();
|
---|
1071 | if (attrs != null)
|
---|
1072 | {
|
---|
1073 | for (int i = 0; i < attrs.getLength(); i++)
|
---|
1074 | {
|
---|
1075 | Node attr = attrs.item(i);
|
---|
1076 | sb.append(' ');
|
---|
1077 | sb.append(attr.getNodeName());
|
---|
1078 | sb.append("=\"");
|
---|
1079 | sb.append(attr.getNodeValue().replaceAll("&", "&").replaceAll("<", "<").replaceAll(">", ">"));
|
---|
1080 | sb.append('"');
|
---|
1081 | }
|
---|
1082 | }
|
---|
1083 | NodeList children = e.getChildNodes();
|
---|
1084 |
|
---|
1085 | boolean hasElements = false;
|
---|
1086 | boolean indentSwapped = false;
|
---|
1087 | for (int i = 0; i < children.getLength(); i++)
|
---|
1088 | {
|
---|
1089 | if (children.item(i).getNodeType() == Node.ELEMENT_NODE)
|
---|
1090 | {
|
---|
1091 | hasElements = true;
|
---|
1092 | }
|
---|
1093 | if ((children.item(i).getNodeType() == Node.TEXT_NODE || children.item(i).getNodeType() == Node.CDATA_SECTION_NODE) && indent)
|
---|
1094 | {
|
---|
1095 | if (children.item(i).getNodeValue().trim().length() > 0)
|
---|
1096 | {
|
---|
1097 | indentSwapped = true;
|
---|
1098 | indent = false;
|
---|
1099 | }
|
---|
1100 | }
|
---|
1101 | }
|
---|
1102 |
|
---|
1103 | if (children == null || children.getLength() == 0)
|
---|
1104 | {
|
---|
1105 | sb.append("/>");
|
---|
1106 |
|
---|
1107 | if (indent)
|
---|
1108 | {
|
---|
1109 | sb.append("\n");
|
---|
1110 | }
|
---|
1111 | }
|
---|
1112 | else
|
---|
1113 | {
|
---|
1114 | sb.append(">");
|
---|
1115 | if (hasElements && indent)
|
---|
1116 | {
|
---|
1117 | sb.append("\n");
|
---|
1118 | }
|
---|
1119 |
|
---|
1120 | int len = children.getLength();
|
---|
1121 | for (int i = 0; i < len; i++)
|
---|
1122 | {
|
---|
1123 | xmlNodeToString(sb, children.item(i), indent, indentString, depth + 1);
|
---|
1124 | }
|
---|
1125 |
|
---|
1126 | if (indent)
|
---|
1127 | {
|
---|
1128 | for (int i = 0; i < depth; i++)
|
---|
1129 | {
|
---|
1130 | sb.append(indentString);
|
---|
1131 | }
|
---|
1132 | }
|
---|
1133 |
|
---|
1134 | sb.append("</" + e.getNodeName() + ">");
|
---|
1135 |
|
---|
1136 | if ((hasElements && indent) || indentSwapped)
|
---|
1137 | {
|
---|
1138 | sb.append("\n");
|
---|
1139 | }
|
---|
1140 | }
|
---|
1141 | }
|
---|
1142 |
|
---|
1143 | public static String xmlNodeToStringWithoutIndenting(Node e)
|
---|
1144 | {
|
---|
1145 | StringBuffer sb = new StringBuffer("");
|
---|
1146 | xmlNodeToStringWithoutNewline(sb, e, -1);
|
---|
1147 | return sb.toString();
|
---|
1148 | }
|
---|
1149 |
|
---|
1150 | public static String xmlNodeToStringWithoutNewline(Node e)
|
---|
1151 | {
|
---|
1152 | StringBuffer sb = new StringBuffer("");
|
---|
1153 | xmlNodeToStringWithoutNewline(sb, e, 0);
|
---|
1154 | return sb.toString();
|
---|
1155 | }
|
---|
1156 |
|
---|
1157 | private static void xmlNodeToStringWithoutNewline(StringBuffer sb, Node e, int depth)
|
---|
1158 | {
|
---|
1159 |
|
---|
1160 | for (int i = 0; i < depth; i++)
|
---|
1161 | {
|
---|
1162 | sb.append(' ');
|
---|
1163 | }
|
---|
1164 |
|
---|
1165 | if (e.getNodeType() == Node.TEXT_NODE)
|
---|
1166 | {
|
---|
1167 | if (e.getNodeValue() != "")
|
---|
1168 | {
|
---|
1169 | sb.append(e.getNodeValue().replaceAll("&", "&").replaceAll("<", "<").replace(">", ">"));
|
---|
1170 | }
|
---|
1171 | return;
|
---|
1172 | }
|
---|
1173 |
|
---|
1174 | if (e.getNodeType() == Node.COMMENT_NODE)
|
---|
1175 | {
|
---|
1176 | if (e.getNodeValue() != "")
|
---|
1177 | {
|
---|
1178 | sb.append("<!--" + e.getNodeValue() + "-->");
|
---|
1179 | }
|
---|
1180 | return;
|
---|
1181 | }
|
---|
1182 |
|
---|
1183 | sb.append('<');
|
---|
1184 | sb.append(e.getNodeName());
|
---|
1185 | NamedNodeMap attrs = e.getAttributes();
|
---|
1186 | if (attrs != null)
|
---|
1187 | {
|
---|
1188 | for (int i = 0; i < attrs.getLength(); i++)
|
---|
1189 | {
|
---|
1190 | Node attr = attrs.item(i);
|
---|
1191 | sb.append(' ');
|
---|
1192 | sb.append(attr.getNodeName());
|
---|
1193 | sb.append("=\"");
|
---|
1194 | sb.append(attr.getNodeValue());
|
---|
1195 | sb.append('"');
|
---|
1196 | }
|
---|
1197 | }
|
---|
1198 | NodeList children = e.getChildNodes();
|
---|
1199 |
|
---|
1200 | if (children == null || children.getLength() == 0)
|
---|
1201 | sb.append("/>");
|
---|
1202 | else
|
---|
1203 | {
|
---|
1204 |
|
---|
1205 | sb.append(">");
|
---|
1206 |
|
---|
1207 | int len = children.getLength();
|
---|
1208 | for (int i = 0; i < len; i++)
|
---|
1209 | {
|
---|
1210 | if (depth >= 0)
|
---|
1211 | {
|
---|
1212 | xmlNodeToStringWithoutNewline(sb, children.item(i), depth + 1);
|
---|
1213 | }
|
---|
1214 | else
|
---|
1215 | {
|
---|
1216 | xmlNodeToStringWithoutNewline(sb, children.item(i), depth);
|
---|
1217 | }
|
---|
1218 | }
|
---|
1219 |
|
---|
1220 | for (int i = 0; i < depth; i++)
|
---|
1221 | sb.append(' ');
|
---|
1222 |
|
---|
1223 | sb.append("</" + e.getNodeName() + ">");
|
---|
1224 | }
|
---|
1225 | }
|
---|
1226 | }
|
---|