1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630
|
/**
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/
package nokogiri.internals.c14n;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.UnsupportedEncodingException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
import java.util.List;
import java.util.ListIterator;
import java.util.Map;
import java.util.Set;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import org.w3c.dom.Attr;
import org.w3c.dom.Comment;
import org.w3c.dom.Element;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.ProcessingInstruction;
/**
* Abstract base class for canonicalization algorithms.
*
* @author Christian Geuer-Pollmann <geuerp@apache.org>
*/
public abstract class CanonicalizerBase extends CanonicalizerSpi {
public static final String XML = "xml";
public static final String XMLNS = "xmlns";
protected static final AttrCompare COMPARE = new AttrCompare();
protected static final Attr nullNode;
private static final byte[] END_PI = {'?','>'};
private static final byte[] BEGIN_PI = {'<','?'};
private static final byte[] END_COMM = {'-','-','>'};
private static final byte[] BEGIN_COMM = {'<','!','-','-'};
private static final byte[] XA = {'&','#','x','A',';'};
private static final byte[] X9 = {'&','#','x','9',';'};
private static final byte[] QUOT = {'&','q','u','o','t',';'};
private static final byte[] XD = {'&','#','x','D',';'};
private static final byte[] GT = {'&','g','t',';'};
private static final byte[] LT = {'&','l','t',';'};
private static final byte[] END_TAG = {'<','/'};
private static final byte[] AMP = {'&','a','m','p',';'};
private static final byte[] equalsStr = {'=','\"'};
protected static final int NODE_BEFORE_DOCUMENT_ELEMENT = -1;
protected static final int NODE_NOT_BEFORE_OR_AFTER_DOCUMENT_ELEMENT = 0;
protected static final int NODE_AFTER_DOCUMENT_ELEMENT = 1;
static {
// The null xmlns definition.
try {
DocumentBuilder documentBuilder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
nullNode = documentBuilder.newDocument().createAttributeNS(Constants.NamespaceSpecNS, XMLNS);
nullNode.setValue("");
} catch (Exception e) {
throw new RuntimeException("Unable to create nullNode: " + e);
}
}
private List<NodeFilter> nodeFilter;
private final boolean includeComments;
//private Set<Node> xpathNodeSet;
/**
* The node to be skipped/excluded from the DOM tree
* in subtree canonicalizations.
*/
private Node excludeNode;
private OutputStream writer = new ByteArrayOutputStream();
/**
* Constructor CanonicalizerBase
*
* @param includeComments
*/
public CanonicalizerBase(boolean includeComments) {
this.includeComments = includeComments;
}
/**
* Method engineCanonicalizeSubTree
* @inheritDoc
* @param rootNode
* @throws CanonicalizationException
*/
@Override
public byte[] engineCanonicalizeSubTree(Node rootNode, CanonicalFilter filter)
throws CanonicalizationException {
return engineCanonicalizeSubTree(rootNode, (Node)null, filter);
}
/**
* @param writer The writer to set.
*/
@Override
public void setWriter(OutputStream writer) {
this.writer = writer;
}
/**
* Canonicalizes a Subtree node.
*
* @param rootNode
* the root of the subtree to canonicalize
* @param excludeNode
* a node to be excluded from the canonicalize operation
* @return The canonicalize stream.
* @throws CanonicalizationException
*/
protected byte[] engineCanonicalizeSubTree(Node rootNode, Node excludeNode, CanonicalFilter filter)
throws CanonicalizationException {
this.excludeNode = excludeNode;
try {
NameSpaceSymbTable ns = new NameSpaceSymbTable();
int nodeLevel = NODE_BEFORE_DOCUMENT_ELEMENT;
if (rootNode != null && Node.ELEMENT_NODE == rootNode.getNodeType()) {
//Fills the nssymbtable with the definitions of the parent of the root subnode
getParentNameSpaces((Element)rootNode, ns);
nodeLevel = NODE_NOT_BEFORE_OR_AFTER_DOCUMENT_ELEMENT;
}
this.canonicalizeSubTree(rootNode, ns, rootNode, nodeLevel, filter);
this.writer.flush();
if (this.writer instanceof ByteArrayOutputStream) {
byte[] result = ((ByteArrayOutputStream)this.writer).toByteArray();
if (reset) {
((ByteArrayOutputStream)this.writer).reset();
} else {
this.writer.close();
}
return result;
} else {
this.writer.close();
}
return null;
} catch (UnsupportedEncodingException ex) {
throw new CanonicalizationException("empty", ex);
} catch (IOException ex) {
throw new CanonicalizationException("empty", ex);
}
}
/**
* Method canonicalizeSubTree, this function is a recursive one.
*
* @param currentNode
* @param ns
* @param endnode
* @throws CanonicalizationException
* @throws IOException
*/
protected final void canonicalizeSubTree(
Node currentNode, NameSpaceSymbTable ns, Node endnode, int documentLevel, CanonicalFilter filter
) throws CanonicalizationException, IOException {
if (isVisibleInt(currentNode) == -1) {
return;
}
Node sibling = null;
Node parentNode = null;
final OutputStream writer = this.writer;
final Node excludeNode = this.excludeNode;
final boolean includeComments = this.includeComments;
Map<String, byte[]> cache = new HashMap<String, byte[]>();
do {
switch (currentNode.getNodeType()) {
case Node.ENTITY_NODE :
case Node.NOTATION_NODE :
case Node.ATTRIBUTE_NODE :
// illegal node type during traversal
throw new CanonicalizationException("empty");
case Node.DOCUMENT_FRAGMENT_NODE :
case Node.DOCUMENT_NODE :
ns.outputNodePush();
sibling = currentNode.getFirstChild();
break;
case Node.COMMENT_NODE :
if (includeComments) {
outputCommentToWriter((Comment) currentNode, writer, documentLevel);
}
break;
case Node.PROCESSING_INSTRUCTION_NODE :
outputPItoWriter((ProcessingInstruction) currentNode, writer, documentLevel);
break;
case Node.TEXT_NODE :
case Node.CDATA_SECTION_NODE :
outputTextToWriter(currentNode.getNodeValue(), writer);
break;
case Node.ELEMENT_NODE :
documentLevel = NODE_NOT_BEFORE_OR_AFTER_DOCUMENT_ELEMENT;
if (currentNode == excludeNode) {
break;
}
if (filter != null && !filter.includeNodes(currentNode, parentNode)) {
break;
}
Element currentElement = (Element)currentNode;
//Add a level to the nssymbtable. So latter can be pop-back.
ns.outputNodePush();
writer.write('<');
String name = currentElement.getTagName();
UtfHelpper.writeByte(name, writer, cache);
Iterator<Attr> attrs = this.handleAttributesSubtree(currentElement, ns);
if (attrs != null) {
//we output all Attrs which are available
while (attrs.hasNext()) {
Attr attr = attrs.next();
outputAttrToWriter(attr.getNodeName(), attr.getNodeValue(), writer, cache);
}
}
writer.write('>');
sibling = currentNode.getFirstChild();
if (sibling == null) {
writer.write(END_TAG);
UtfHelpper.writeStringToUtf8(name, writer);
writer.write('>');
//We finished with this level, pop to the previous definitions.
ns.outputNodePop();
if (parentNode != null) {
sibling = currentNode.getNextSibling();
}
} else {
parentNode = currentElement;
}
break;
case Node.DOCUMENT_TYPE_NODE :
default :
break;
}
while (sibling == null && parentNode != null) {
writer.write(END_TAG);
UtfHelpper.writeByte(((Element)parentNode).getTagName(), writer, cache);
writer.write('>');
//We finished with this level, pop to the previous definitions.
ns.outputNodePop();
if (parentNode == endnode) {
return;
}
sibling = parentNode.getNextSibling();
parentNode = parentNode.getParentNode();
if (parentNode == null || Node.ELEMENT_NODE != parentNode.getNodeType()) {
documentLevel = NODE_AFTER_DOCUMENT_ELEMENT;
parentNode = null;
}
}
if (sibling == null) {
return;
}
currentNode = sibling;
sibling = currentNode.getNextSibling();
} while(true);
}
protected int isVisibleDO(Node currentNode, int level) {
if (nodeFilter != null) {
Iterator<NodeFilter> it = nodeFilter.iterator();
while (it.hasNext()) {
int i = (it.next()).isNodeIncludeDO(currentNode, level);
if (i != 1) {
return i;
}
}
}
//if ((this.xpathNodeSet != null) && !this.xpathNodeSet.contains(currentNode)) {
// return 0;
//}
return 1;
}
protected int isVisibleInt(Node currentNode) {
if (nodeFilter != null) {
Iterator<NodeFilter> it = nodeFilter.iterator();
while (it.hasNext()) {
int i = (it.next()).isNodeInclude(currentNode);
if (i != 1) {
return i;
}
}
}
//if ((this.xpathNodeSet != null) && !this.xpathNodeSet.contains(currentNode)) {
// return 0;
//}
return 1;
}
protected boolean isVisible(Node currentNode) {
if (nodeFilter != null) {
Iterator<NodeFilter> it = nodeFilter.iterator();
while (it.hasNext()) {
if (it.next().isNodeInclude(currentNode) != 1) {
return false;
}
}
}
//if ((this.xpathNodeSet != null) && !this.xpathNodeSet.contains(currentNode)) {
// return false;
//}
return true;
}
protected void handleParent(Element e, NameSpaceSymbTable ns) {
if (!e.hasAttributes() && e.getNamespaceURI() == null) {
return;
}
NamedNodeMap attrs = e.getAttributes();
int attrsLength = attrs.getLength();
for (int i = 0; i < attrsLength; i++) {
Attr attribute = (Attr) attrs.item(i);
String NName = attribute.getLocalName();
String NValue = attribute.getNodeValue();
if (Constants.NamespaceSpecNS.equals(attribute.getNamespaceURI())
&& (!XML.equals(NName) || !Constants.XML_LANG_SPACE_SpecNS.equals(NValue))) {
ns.addMapping(NName, NValue, attribute);
}
}
if (e.getNamespaceURI() != null) {
String NName = e.getPrefix();
String NValue = e.getNamespaceURI();
String Name;
if (NName == null || NName.equals("")) {
NName = XMLNS;
Name = XMLNS;
} else {
Name = XMLNS + ":" + NName;
}
Attr n = e.getOwnerDocument().createAttributeNS("http://www.w3.org/2000/xmlns/", Name);
n.setValue(NValue);
ns.addMapping(NName, NValue, n);
}
}
/**
* Adds to ns the definitions from the parent elements of el
* @param el
* @param ns
*/
protected final void getParentNameSpaces(Element el, NameSpaceSymbTable ns) {
Node n1 = el.getParentNode();
if (n1 == null || Node.ELEMENT_NODE != n1.getNodeType()) {
return;
}
//Obtain all the parents of the element
List<Element> parents = new ArrayList<Element>();
Node parent = n1;
while (parent != null && Node.ELEMENT_NODE == parent.getNodeType()) {
parents.add((Element)parent);
parent = parent.getParentNode();
}
//Visit them in reverse order.
ListIterator<Element> it = parents.listIterator(parents.size());
while (it.hasPrevious()) {
Element ele = it.previous();
handleParent(ele, ns);
}
parents.clear();
Attr nsprefix;
if (((nsprefix = ns.getMappingWithoutRendered(XMLNS)) != null)
&& "".equals(nsprefix.getValue())) {
ns.addMappingAndRender(XMLNS, "", nullNode);
}
}
/**
* Obtain the attributes to output for this node in XPathNodeSet c14n.
*
* @param element
* @param ns
* @return the attributes nodes to output.
* @throws CanonicalizationException
*/
abstract Iterator<Attr> handleAttributes(Element element, NameSpaceSymbTable ns)
throws CanonicalizationException;
/**
* Obtain the attributes to output for this node in a Subtree c14n.
*
* @param element
* @param ns
* @return the attributes nodes to output.
* @throws CanonicalizationException
*/
abstract Iterator<Attr> handleAttributesSubtree(Element element, NameSpaceSymbTable ns)
throws CanonicalizationException;
//abstract void circumventBugIfNeeded(XMLSignatureInput input)
// throws CanonicalizationException, ParserConfigurationException, IOException, SAXException;
/**
* Outputs an Attribute to the internal Writer.
*
* The string value of the node is modified by replacing
* <UL>
* <LI>all ampersands (&) with <CODE>&amp;</CODE></LI>
* <LI>all open angle brackets (<) with <CODE>&lt;</CODE></LI>
* <LI>all quotation mark characters with <CODE>&quot;</CODE></LI>
* <LI>and the whitespace characters <CODE>#x9</CODE>, #xA, and #xD, with character
* references. The character references are written in uppercase
* hexadecimal with no leading zeroes (for example, <CODE>#xD</CODE> is represented
* by the character reference <CODE>&#xD;</CODE>)</LI>
* </UL>
*
* @param name
* @param value
* @param writer
* @throws IOException
*/
protected static final void outputAttrToWriter(
final String name, final String value,
final OutputStream writer, final Map<String, byte[]> cache
) throws IOException {
writer.write(' ');
UtfHelpper.writeByte(name, writer, cache);
writer.write(equalsStr);
byte[] toWrite;
final int length = value.length();
int i = 0;
while (i < length) {
char c = value.charAt(i++);
switch (c) {
case '&' :
toWrite = AMP;
break;
case '<' :
toWrite = LT;
break;
case '"' :
toWrite = QUOT;
break;
case 0x09 : // '\t'
toWrite = X9;
break;
case 0x0A : // '\n'
toWrite = XA;
break;
case 0x0D : // '\r'
toWrite = XD;
break;
default :
if (c < 0x80) {
writer.write(c);
} else {
UtfHelpper.writeCharToUtf8(c, writer);
}
continue;
}
writer.write(toWrite);
}
writer.write('\"');
}
/**
* Outputs a PI to the internal Writer.
*
* @param currentPI
* @param writer where to write the things
* @throws IOException
*/
protected void outputPItoWriter(
ProcessingInstruction currentPI, OutputStream writer, int position
) throws IOException {
if (position == NODE_AFTER_DOCUMENT_ELEMENT) {
writer.write('\n');
}
writer.write(BEGIN_PI);
final String target = currentPI.getTarget();
int length = target.length();
for (int i = 0; i < length; i++) {
char c = target.charAt(i);
if (c == 0x0D) {
writer.write(XD);
} else {
if (c < 0x80) {
writer.write(c);
} else {
UtfHelpper.writeCharToUtf8(c, writer);
}
}
}
final String data = currentPI.getData();
length = data.length();
if (length > 0) {
writer.write(' ');
for (int i = 0; i < length; i++) {
char c = data.charAt(i);
if (c == 0x0D) {
writer.write(XD);
} else {
UtfHelpper.writeCharToUtf8(c, writer);
}
}
}
writer.write(END_PI);
if (position == NODE_BEFORE_DOCUMENT_ELEMENT) {
writer.write('\n');
}
}
/**
* Method outputCommentToWriter
*
* @param currentComment
* @param writer writer where to write the things
* @throws IOException
*/
protected void outputCommentToWriter(
Comment currentComment, OutputStream writer, int position
) throws IOException {
if (position == NODE_AFTER_DOCUMENT_ELEMENT) {
writer.write('\n');
}
writer.write(BEGIN_COMM);
final String data = currentComment.getData();
final int length = data.length();
for (int i = 0; i < length; i++) {
char c = data.charAt(i);
if (c == 0x0D) {
writer.write(XD);
} else {
if (c < 0x80) {
writer.write(c);
} else {
UtfHelpper.writeCharToUtf8(c, writer);
}
}
}
writer.write(END_COMM);
if (position == NODE_BEFORE_DOCUMENT_ELEMENT) {
writer.write('\n');
}
}
/**
* Outputs a Text of CDATA section to the internal Writer.
*
* @param text
* @param writer writer where to write the things
* @throws IOException
*/
protected static final void outputTextToWriter(
final String text, final OutputStream writer
) throws IOException {
final int length = text.length();
byte[] toWrite;
for (int i = 0; i < length; i++) {
char c = text.charAt(i);
switch (c) {
case '&' :
toWrite = AMP;
break;
case '<' :
toWrite = LT;
break;
case '>' :
toWrite = GT;
break;
case 0xD :
toWrite = XD;
break;
default :
if (c < 0x80) {
writer.write(c);
} else {
UtfHelpper.writeCharToUtf8(c, writer);
}
continue;
}
writer.write(toWrite);
}
}
}
|