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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277
|
/* XMLElement.java
*
* $Revision: 1.2 $
* $Date: 2002/08/03 04:36:34 $
* $Name: $
*
* This file is part of NanoXML 2 Lite.
* Copyright (C) 2000-2002 Marc De Scheemaecker, All Rights Reserved.
*
* This software is provided 'as-is', without any express or implied warranty.
* In no event will the authors be held liable for any damages arising from the
* use of this software.
*
* Permission is granted to anyone to use this software for any purpose,
* including commercial applications, and to alter it and redistribute it
* freely, subject to the following restrictions:
*
* 1. The origin of this software must not be misrepresented; you must not
* claim that you wrote the original software. If you use this software in
* a product, an acknowledgment in the product documentation would be
* appreciated but is not required.
*
* 2. Altered source versions must be plainly marked as such, and must not be
* misrepresented as being the original software.
*
* 3. This notice may not be removed or altered from any source distribution.
*****************************************************************************/
/* JAM: hacked the source to remove unneeded methods and comments. */
package net.sourceforge.nanoxml;
import java.io.*;
import java.util.*;
import net.sourceforge.jnlp.runtime.JNLPRuntime;
/**
* XMLElement is a representation of an XML object. The object is able to parse
* XML code.
* <P><DL>
* <DT><B>Parsing XML Data</B></DT>
* <DD>
* You can parse XML data using the following code:
* <UL><CODE>
* XMLElement xml = new XMLElement();<BR>
* FileReader reader = new FileReader("filename.xml");<BR>
* xml.parseFromReader(reader);
* </CODE></UL></DD></DL>
* <DL><DT><B>Retrieving Attributes</B></DT>
* <DD>
* You can enumerate the attributes of an element using the method
* {@link #enumerateAttributeNames() enumerateAttributeNames}.
* The attribute values can be retrieved using the method
* {@link #getAttribute(java.lang.String) getAttribute}.
* The following example shows how to list the attributes of an element:
* <UL><CODE>
* XMLElement element = ...;<BR>
* Enumeration enum = element.enumerateAttributeNames();<BR>
* while (enum.hasMoreElements()) {<BR>
* String key = (String) enum.nextElement();<BR>
* String value = (String) element.getAttribute(key);<BR>
* System.out.println(key + " = " + value);<BR>
* }
* </CODE></UL></DD></DL>
* <DL><DT><B>Retrieving Child Elements</B></DT>
* <DD>
* You can enumerate the children of an element using
* {@link #enumerateChildren() enumerateChildren}.
* The number of child elements can be retrieved using
* {@link #countChildren() countChildren}.
* </DD></DL>
* <DL><DT><B>Elements Containing Character Data</B></DT>
* <DD>
* If an elements contains character data, like in the following example:
* <UL><CODE>
* <title>The Title</title>
* </CODE></UL>
* you can retrieve that data using the method
* {@link #getContent() getContent}.
* </DD></DL>
* <DL><DT><B>Subclassing XMLElement</B></DT>
* <DD>
* When subclassing XMLElement, you need to override the method
* {@link #createAnotherElement() createAnotherElement}
* which has to return a new copy of the receiver.
* </DD></DL>
* <P>
*
* @see net.sourceforge.nanoxml.XMLParseException
*
* @author Marc De Scheemaecker
* <<A href="mailto:cyberelf@mac.com">cyberelf@mac.com</A>>
* @version $Name: $, $Revision: 1.2 $
*/
public class XMLElement {
/**
* The attributes given to the element.
*
* <dl><dt><b>Invariants:</b></dt><dd>
* <ul><li>The field can be empty.
* <li>The field is never <code>null</code>.
* <li>The keys and the values are strings.
* </ul></dd></dl>
*/
private Hashtable<String, Object> attributes;
/**
* Child elements of the element.
*
* <dl><dt><b>Invariants:</b></dt><dd>
* <ul><li>The field can be empty.
* <li>The field is never <code>null</code>.
* <li>The elements are instances of <code>XMLElement</code>
* or a subclass of <code>XMLElement</code>.
* </ul></dd></dl>
*/
private Vector<XMLElement> children;
/**
* The name of the element.
*
* <dl><dt><b>Invariants:</b></dt><dd>
* <ul><li>The field is <code>null</code> iff the element is not
* initialized by either parse or setName.
* <li>If the field is not <code>null</code>, it's not empty.
* <li>If the field is not <code>null</code>, it contains a valid
* XML identifier.
* </ul></dd></dl>
*/
private String name;
/**
* The #PCDATA content of the object.
*
* <dl><dt><b>Invariants:</b></dt><dd>
* <ul><li>The field is <code>null</code> iff the element is not a
* #PCDATA element.
* <li>The field can be any string, including the empty string.
* </ul></dd></dl>
*/
private String contents;
/**
* Conversion table for &...; entities. The keys are the entity names
* without the & and ; delimiters.
*
* <dl><dt><b>Invariants:</b></dt><dd>
* <ul><li>The field is never <code>null</code>.
* <li>The field always contains the following associations:
* "lt" => "<", "gt" => ">",
* "quot" => "\"", "apos" => "'",
* "amp" => "&"
* <li>The keys are strings
* <li>The values are char arrays
* </ul></dd></dl>
*/
private Hashtable<String, char[]> entities;
/**
* The line number where the element starts.
*
* <dl><dt><b>Invariants:</b></dt><dd>
* <ul><li><code>lineNr >= 0</code>
* </ul></dd></dl>
*/
private int lineNr;
/**
* <code>true</code> if the case of the element and attribute names
* are case insensitive.
*/
private boolean ignoreCase;
/**
* <code>true</code> if the leading and trailing whitespace of #PCDATA
* sections have to be ignored.
*/
private boolean ignoreWhitespace;
/**
* Character read too much.
* This character provides push-back functionality to the input reader
* without having to use a PushbackReader.
* If there is no such character, this field is '\0'.
*/
private char charReadTooMuch;
/**
* Character read too much for the comment remover.
*/
private char sanitizeCharReadTooMuch;
/**
* The reader provided by the caller of the parse method.
*
* <dl><dt><b>Invariants:</b></dt><dd>
* <ul><li>The field is not <code>null</code> while the parse method
* is running.
* </ul></dd></dl>
*/
private Reader reader;
/**
* The current line number in the source content.
*
* <dl><dt><b>Invariants:</b></dt><dd>
* <ul><li>parserLineNr > 0 while the parse method is running.
* </ul></dd></dl>
*/
private int parserLineNr;
/**
* Creates and initializes a new XML element.
* Calling the construction is equivalent to:
* <ul><code>new XMLElement(new Hashtable(), false, true)
* </code></ul>
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li>countChildren() => 0
* <li>enumerateChildren() => empty enumeration
* <li>enumeratePropertyNames() => empty enumeration
* <li>getChildren() => empty vector
* <li>getContent() => ""
* <li>getLineNr() => 0
* <li>getName() => null
* </ul></dd></dl>
*
*/
public XMLElement() {
this(new Hashtable<String, char[]>(), false, true, true);
}
/**
* Creates and initializes a new XML element.
* <P>
* This constructor should <I>only</I> be called from
* {@link #createAnotherElement() createAnotherElement}
* to create child elements.
*
* @param entities
* The entity conversion table.
* @param skipLeadingWhitespace
* <code>true</code> if leading and trailing whitespace in PCDATA
* content has to be removed.
* @param fillBasicConversionTable
* <code>true</code> if the basic entities need to be added to
* the entity list (client code calling this constructor).
* @param ignoreCase
* <code>true</code> if the case of element and attribute names have
* to be ignored.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>entities != null</code>
* <li>if <code>fillBasicConversionTable == false</code>
* then <code>entities</code> contains at least the following
* entries: <code>amp</code>, <code>lt</code>, <code>gt</code>,
* <code>apos</code> and <code>quot</code>
* </ul></dd></dl>
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li>countChildren() => 0
* <li>enumerateChildren() => empty enumeration
* <li>enumeratePropertyNames() => empty enumeration
* <li>getChildren() => empty vector
* <li>getContent() => ""
* <li>getLineNr() => 0
* <li>getName() => null
* </ul></dd></dl><dl>
*
*/
protected XMLElement(Hashtable<String, char[]> entities,
boolean skipLeadingWhitespace,
boolean fillBasicConversionTable,
boolean ignoreCase) {
this.ignoreWhitespace = skipLeadingWhitespace;
this.ignoreCase = ignoreCase;
this.name = null;
this.contents = "";
this.attributes = new Hashtable<String, Object>();
this.children = new Vector<XMLElement>();
this.entities = entities;
this.lineNr = 0;
Enumeration<String> e = this.entities.keys();
while (e.hasMoreElements()) {
String key = e.nextElement();
Object value = this.entities.get(key);
if (value instanceof String) {
entities.put(key, ((String) value).toCharArray());
}
}
if (fillBasicConversionTable) {
this.entities.put("amp", new char[] { '&' });
this.entities.put("quot", new char[] { '"' });
this.entities.put("apos", new char[] { '\'' });
this.entities.put("lt", new char[] { '<' });
this.entities.put("gt", new char[] { '>' });
}
}
/**
* Adds a child element.
*
* @param child
* The child element to add.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>child != null</code>
* <li><code>child.getName() != null</code>
* <li><code>child</code> does not have a parent element
* </ul></dd></dl>
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li>countChildren() => old.countChildren() + 1
* <li>enumerateChildren() => old.enumerateChildren() + child
* <li>getChildren() => old.enumerateChildren() + child
* </ul></dd></dl><dl>
*
*/
public void addChild(XMLElement child) {
this.children.addElement(child);
}
/**
* Adds or modifies an attribute.
*
* @param name
* The name of the attribute.
* @param value
* The value of the attribute.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>name != null</code>
* <li><code>name</code> is a valid XML identifier
* <li><code>value != null</code>
* </ul></dd></dl>
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li>enumerateAttributeNames()
* => old.enumerateAttributeNames() + name
* <li>getAttribute(name) => value
* </ul></dd></dl><dl>
*
*/
public void setAttribute(String name,
Object value) {
if (this.ignoreCase) {
name = name.toUpperCase();
}
this.attributes.put(name, value.toString());
}
/**
* Returns the number of child elements of the element.
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li><code>result >= 0</code>
* </ul></dd></dl>
*
*/
public int countChildren() {
return this.children.size();
}
/**
* Enumerates the attribute names.
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li><code>result != null</code>
* </ul></dd></dl>
*
*/
public Enumeration enumerateAttributeNames() {
return this.attributes.keys();
}
/**
* Enumerates the child elements.
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li><code>result != null</code>
* </ul></dd></dl>
*
*/
public Enumeration enumerateChildren() {
return this.children.elements();
}
/**
* Returns the PCDATA content of the object. If there is no such content,
* <CODE>null</CODE> is returned.
*
*/
public String getContent() {
return this.contents;
}
/**
* Returns the line nr in the source data on which the element is found.
* This method returns <code>0</code> there is no associated source data.
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li><code>result >= 0</code>
* </ul></dd></dl>
*/
public int getLineNr() {
return this.lineNr;
}
/**
* Returns an attribute of the element.
* If the attribute doesn't exist, <code>null</code> is returned.
*
* @param name The name of the attribute.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>name != null</code>
* <li><code>name</code> is a valid XML identifier
* </ul></dd></dl><dl>
*
*/
public Object getAttribute(String name) {
if (this.ignoreCase) {
name = name.toUpperCase();
}
Object value = this.attributes.get(name);
return value;
}
/**
* Returns the name of the element.
*
*/
public String getName() {
return this.name;
}
/**
* Reads one XML element from a java.io.Reader and parses it.
*
* @param reader
* The reader from which to retrieve the XML data.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>reader != null</code>
* <li><code>reader</code> is not closed
* </ul></dd></dl>
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li>the state of the receiver is updated to reflect the XML element
* parsed from the reader
* <li>the reader points to the first character following the last
* '>' character of the XML element
* </ul></dd></dl><dl>
*
* @throws java.io.IOException
* If an error occured while reading the input.
* @throws net.sourceforge.nanoxml.XMLParseException
* If an error occured while parsing the read data.
*/
public void parseFromReader(Reader reader)
throws IOException, XMLParseException {
this.parseFromReader(reader, /*startingLineNr*/1);
}
/**
* Reads one XML element from a java.io.Reader and parses it.
*
* @param reader
* The reader from which to retrieve the XML data.
* @param startingLineNr
* The line number of the first line in the data.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>reader != null</code>
* <li><code>reader</code> is not closed
* </ul></dd></dl>
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li>the state of the receiver is updated to reflect the XML element
* parsed from the reader
* <li>the reader points to the first character following the last
* '>' character of the XML element
* </ul></dd></dl><dl>
*
* @throws java.io.IOException
* If an error occured while reading the input.
* @throws net.sourceforge.nanoxml.XMLParseException
* If an error occured while parsing the read data.
*/
public void parseFromReader(Reader reader,
int startingLineNr)
throws IOException, XMLParseException {
this.charReadTooMuch = '\0';
this.reader = reader;
this.parserLineNr = startingLineNr;
for (;;) {
char ch = this.scanWhitespace();
if (ch != '<') {
throw this.expectedInput("<", ch);
}
ch = this.readChar();
if ((ch == '!') || (ch == '?')) {
this.skipSpecialTag(0);
} else {
this.unreadChar(ch);
this.scanElement(this);
return;
}
}
}
/**
* Creates a new similar XML element.
* <P>
* You should override this method when subclassing XMLElement.
*/
protected XMLElement createAnotherElement() {
return new XMLElement(this.entities,
this.ignoreWhitespace,
false,
this.ignoreCase);
}
/**
* Changes the content string.
*
* @param content
* The new content string.
*/
public void setContent(String content) {
this.contents = content;
}
/**
* Changes the name of the element.
*
* @param name
* The new name.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>name != null</code>
* <li><code>name</code> is a valid XML identifier
* </ul></dd></dl>
*
*/
public void setName(String name) {
this.name = name;
}
/**
* Scans an identifier from the current reader.
* The scanned identifier is appended to <code>result</code>.
*
* @param result
* The buffer in which the scanned identifier will be put.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>result != null</code>
* <li>The next character read from the reader is a valid first
* character of an XML identifier.
* </ul></dd></dl>
*
* <dl><dt><b>Postconditions:</b></dt><dd>
* <ul><li>The next character read from the reader won't be an identifier
* character.
* </ul></dd></dl><dl>
*/
protected void scanIdentifier(StringBuffer result)
throws IOException {
for (;;) {
char ch = this.readChar();
if (((ch < 'A') || (ch > 'Z')) && ((ch < 'a') || (ch > 'z'))
&& ((ch < '0') || (ch > '9')) && (ch != '_') && (ch != '.')
&& (ch != ':') && (ch != '-') && (ch <= '\u007E')) {
this.unreadChar(ch);
return;
}
result.append(ch);
}
}
/**
* This method scans an identifier from the current reader.
*
* @return the next character following the whitespace.
*/
protected char scanWhitespace()
throws IOException {
for (;;) {
char ch = this.readChar();
switch (ch) {
case ' ':
case '\t':
case '\n':
case '\r':
break;
default:
return ch;
}
}
}
/**
* This method scans an identifier from the current reader.
* The scanned whitespace is appended to <code>result</code>.
*
* @return the next character following the whitespace.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>result != null</code>
* </ul></dd></dl>
*/
protected char scanWhitespace(StringBuffer result)
throws IOException {
for (;;) {
char ch = this.readChar();
switch (ch) {
case ' ':
case '\t':
case '\n':
result.append(ch);
break;
case '\r':
break;
default:
return ch;
}
}
}
/**
* This method scans a delimited string from the current reader.
* The scanned string without delimiters is appended to
* <code>string</code>.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>string != null</code>
* <li>the next char read is the string delimiter
* </ul></dd></dl>
*/
protected void scanString(StringBuffer string)
throws IOException {
char delimiter = this.readChar();
if ((delimiter != '\'') && (delimiter != '"')) {
throw this.expectedInput("' or \"");
}
for (;;) {
char ch = this.readChar();
if (ch == delimiter) {
return;
} else if (ch == '&') {
this.resolveEntity(string);
} else {
string.append(ch);
}
}
}
/**
* Scans a #PCDATA element. CDATA sections and entities are resolved.
* The next < char is skipped.
* The scanned data is appended to <code>data</code>.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>data != null</code>
* </ul></dd></dl>
*/
protected void scanPCData(StringBuffer data)
throws IOException {
for (;;) {
char ch = this.readChar();
if (ch == '<') {
ch = this.readChar();
if (ch == '!') {
this.checkCDATA(data);
} else {
this.unreadChar(ch);
return;
}
} else if (ch == '&') {
this.resolveEntity(data);
} else {
data.append(ch);
}
}
}
/**
* Scans a special tag and if the tag is a CDATA section, append its
* content to <code>buf</code>.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>buf != null</code>
* <li>The first < has already been read.
* </ul></dd></dl>
*/
protected boolean checkCDATA(StringBuffer buf)
throws IOException {
char ch = this.readChar();
if (ch != '[') {
this.unreadChar(ch);
this.skipSpecialTag(0);
return false;
} else if (!this.checkLiteral("CDATA[")) {
this.skipSpecialTag(1); // one [ has already been read
return false;
} else {
int delimiterCharsSkipped = 0;
while (delimiterCharsSkipped < 3) {
ch = this.readChar();
switch (ch) {
case ']':
if (delimiterCharsSkipped < 2) {
delimiterCharsSkipped += 1;
} else {
buf.append(']');
buf.append(']');
delimiterCharsSkipped = 0;
}
break;
case '>':
if (delimiterCharsSkipped < 2) {
for (int i = 0; i < delimiterCharsSkipped; i++) {
buf.append(']');
}
delimiterCharsSkipped = 0;
buf.append('>');
} else {
delimiterCharsSkipped = 3;
}
break;
default:
for (int i = 0; i < delimiterCharsSkipped; i += 1) {
buf.append(']');
}
buf.append(ch);
delimiterCharsSkipped = 0;
}
}
return true;
}
}
/**
* Skips a comment.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li>The first <!-- has already been read.
* </ul></dd></dl>
*/
protected void skipComment()
throws IOException {
int dashesToRead = 2;
while (dashesToRead > 0) {
char ch = this.readChar();
if (ch == '-') {
dashesToRead -= 1;
} else {
dashesToRead = 2;
}
// Be more tolerant of extra -- (double dashes)
// in comments.
if (dashesToRead == 0) {
ch = this.readChar();
if (ch == '>') {
return;
} else {
dashesToRead = 2;
this.unreadChar(ch);
}
}
}
/*
if (this.readChar() != '>') {
throw this.expectedInput(">");
}
*/
}
/**
* Skips a special tag or comment.
*
* @param bracketLevel The number of open square brackets ([) that have
* already been read.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li>The first <! has already been read.
* <li><code>bracketLevel >= 0</code>
* </ul></dd></dl>
*/
protected void skipSpecialTag(int bracketLevel)
throws IOException {
int tagLevel = 1; // <
char stringDelimiter = '\0';
if (bracketLevel == 0) {
char ch = this.readChar();
if (ch == '[') {
bracketLevel += 1;
} else if (ch == '-') {
ch = this.readChar();
if (ch == '[') {
bracketLevel += 1;
} else if (ch == ']') {
bracketLevel -= 1;
} else if (ch == '-') {
this.skipComment();
return;
}
}
}
while (tagLevel > 0) {
char ch = this.readChar();
if (stringDelimiter == '\0') {
if ((ch == '"') || (ch == '\'')) {
stringDelimiter = ch;
} else if (bracketLevel <= 0) {
if (ch == '<') {
tagLevel += 1;
} else if (ch == '>') {
tagLevel -= 1;
}
}
if (ch == '[') {
bracketLevel += 1;
} else if (ch == ']') {
bracketLevel -= 1;
}
} else {
if (ch == stringDelimiter) {
stringDelimiter = '\0';
}
}
}
}
/**
* Scans the data for literal text.
* Scanning stops when a character does not match or after the complete
* text has been checked, whichever comes first.
*
* @param literal the literal to check.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>literal != null</code>
* </ul></dd></dl>
*/
protected boolean checkLiteral(String literal)
throws IOException {
int length = literal.length();
for (int i = 0; i < length; i += 1) {
if (this.readChar() != literal.charAt(i)) {
return false;
}
}
return true;
}
/**
* Reads a character from a reader.
*/
protected char readChar()
throws IOException {
if (this.charReadTooMuch != '\0') {
char ch = this.charReadTooMuch;
this.charReadTooMuch = '\0';
return ch;
} else {
int i = this.reader.read();
if (i < 0) {
throw this.unexpectedEndOfData();
} else if (i == 10) {
this.parserLineNr += 1;
return '\n';
} else {
return (char) i;
}
}
}
/**
* Scans an XML element.
*
* @param elt The element that will contain the result.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li>The first < has already been read.
* <li><code>elt != null</code>
* </ul></dd></dl>
*/
protected void scanElement(XMLElement elt)
throws IOException {
StringBuffer buf = new StringBuffer();
this.scanIdentifier(buf);
String name = buf.toString();
elt.setName(name);
char ch = this.scanWhitespace();
while ((ch != '>') && (ch != '/')) {
buf.setLength(0);
this.unreadChar(ch);
this.scanIdentifier(buf);
String key = buf.toString();
ch = this.scanWhitespace();
if (ch != '=') {
throw this.expectedInput("=");
}
this.unreadChar(this.scanWhitespace());
buf.setLength(0);
this.scanString(buf);
elt.setAttribute(key, buf);
ch = this.scanWhitespace();
}
if (ch == '/') {
ch = this.readChar();
if (ch != '>') {
throw this.expectedInput(">");
}
return;
}
buf.setLength(0);
ch = this.scanWhitespace(buf);
if (ch != '<') {
this.unreadChar(ch);
this.scanPCData(buf);
} else {
for (;;) {
ch = this.readChar();
if (ch == '!') {
if (this.checkCDATA(buf)) {
this.scanPCData(buf);
break;
} else {
ch = this.scanWhitespace(buf);
if (ch != '<') {
this.unreadChar(ch);
this.scanPCData(buf);
break;
}
}
} else {
buf.setLength(0);
break;
}
}
}
if (buf.length() == 0) {
while (ch != '/') {
if (ch == '!') {
ch = this.readChar();
if (ch != '-') {
throw this.expectedInput("Comment or Element");
}
ch = this.readChar();
if (ch != '-') {
throw this.expectedInput("Comment or Element");
}
this.skipComment();
} else {
this.unreadChar(ch);
XMLElement child = this.createAnotherElement();
this.scanElement(child);
elt.addChild(child);
}
ch = this.scanWhitespace();
if (ch != '<') {
throw this.expectedInput("<");
}
ch = this.readChar();
}
this.unreadChar(ch);
} else {
if (this.ignoreWhitespace) {
elt.setContent(buf.toString().trim());
} else {
elt.setContent(buf.toString());
}
}
ch = this.readChar();
if (ch != '/') {
throw this.expectedInput("/");
}
this.unreadChar(this.scanWhitespace());
if (!this.checkLiteral(name)) {
throw this.expectedInput(name);
}
if (this.scanWhitespace() != '>') {
throw this.expectedInput(">");
}
}
/**
* Resolves an entity. The name of the entity is read from the reader.
* The value of the entity is appended to <code>buf</code>.
*
* @param buf Where to put the entity value.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li>The first & has already been read.
* <li><code>buf != null</code>
* </ul></dd></dl>
*/
protected void resolveEntity(StringBuffer buf)
throws IOException {
char ch = '\0';
StringBuffer keyBuf = new StringBuffer();
for (;;) {
ch = this.readChar();
if (ch == ';') {
break;
}
keyBuf.append(ch);
}
String key = keyBuf.toString();
if (key.charAt(0) == '#') {
try {
if (key.charAt(1) == 'x') {
ch = (char) Integer.parseInt(key.substring(2), 16);
} else {
ch = (char) Integer.parseInt(key.substring(1), 10);
}
} catch (NumberFormatException e) {
throw this.unknownEntity(key);
}
buf.append(ch);
} else {
char[] value = entities.get(key);
if (value == null) {
throw this.unknownEntity(key);
}
buf.append(value);
}
}
/**
* Pushes a character back to the read-back buffer.
*
* @param ch The character to push back.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li>The read-back buffer is empty.
* <li><code>ch != '\0'</code>
* </ul></dd></dl>
*/
protected void unreadChar(char ch) {
this.charReadTooMuch = ch;
}
/**
* Creates a parse exception for when an invalid valueset is given to
* a method.
*
* @param name The name of the entity.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>name != null</code>
* </ul></dd></dl>
*/
protected XMLParseException invalidValueSet(String name) {
String msg = "Invalid value set (entity name = \"" + name + "\")";
return new XMLParseException(this.getName(), this.parserLineNr, msg);
}
/**
* Creates a parse exception for when an invalid value is given to a
* method.
*
* @param name The name of the entity.
* @param value The value of the entity.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>name != null</code>
* <li><code>value != null</code>
* </ul></dd></dl>
*/
protected XMLParseException invalidValue(String name,
String value) {
String msg = "Attribute \"" + name + "\" does not contain a valid "
+ "value (\"" + value + "\")";
return new XMLParseException(this.getName(), this.parserLineNr, msg);
}
/**
* Creates a parse exception for when the end of the data input has been
* reached.
*/
protected XMLParseException unexpectedEndOfData() {
String msg = "Unexpected end of data reached";
return new XMLParseException(this.getName(), this.parserLineNr, msg);
}
/**
* Creates a parse exception for when a syntax error occured.
*
* @param context The context in which the error occured.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>context != null</code>
* <li><code>context.length() > 0</code>
* </ul></dd></dl>
*/
protected XMLParseException syntaxError(String context) {
String msg = "Syntax error while parsing " + context;
return new XMLParseException(this.getName(), this.parserLineNr, msg);
}
/**
* Creates a parse exception for when the next character read is not
* the character that was expected.
*
* @param charSet The set of characters (in human readable form) that was
* expected.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>charSet != null</code>
* <li><code>charSet.length() > 0</code>
* </ul></dd></dl>
*/
protected XMLParseException expectedInput(String charSet) {
String msg = "Expected: " + charSet;
return new XMLParseException(this.getName(), this.parserLineNr, msg);
}
/**
* Creates a parse exception for when the next character read is not
* the character that was expected.
*
* @param charSet The set of characters (in human readable form) that was
* expected.
* @param ch The character that was received instead.
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>charSet != null</code>
* <li><code>charSet.length() > 0</code>
* </ul></dd></dl>
*/
protected XMLParseException expectedInput(String charSet, char ch) {
String msg = "Expected: '" + charSet + "'" + " but got: '" + ch + "'";
return new XMLParseException(this.getName(), this.parserLineNr, msg);
}
/**
* Creates a parse exception for when an entity could not be resolved.
*
* @param name The name of the entity.
*
* </dl><dl><dt><b>Preconditions:</b></dt><dd>
* <ul><li><code>name != null</code>
* <li><code>name.length() > 0</code>
* </ul></dd></dl>
*/
protected XMLParseException unknownEntity(String name) {
String msg = "Unknown or invalid entity: &" + name + ";";
return new XMLParseException(this.getName(), this.parserLineNr, msg);
}
/**
* Reads an xml file and removes the comments, leaving only relevant
* xml code.
*
* @param isr The reader of the InputStream containing the xml.
* @param pout The PipedOutputStream that will be receiving the filtered
* xml file.
*/
public void sanitizeInput(Reader isr, OutputStream pout) {
try {
PrintStream out = new PrintStream(pout);
this.sanitizeCharReadTooMuch = '\0';
this.reader = isr;
this.parserLineNr = 0;
int newline = 2;
char prev = ' ';
while (true) {
char ch;
if (this.sanitizeCharReadTooMuch != '\0') {
ch = this.sanitizeCharReadTooMuch;
this.sanitizeCharReadTooMuch = '\0';
} else {
int i = this.reader.read();
if (i == -1) {
// no character in buffer, and nothing read
out.flush();
break;
} else if (i == 10) {
ch = '\n';
} else {
ch = (char) i;
}
}
char next;
int i = this.reader.read();
if (i == -1) {
// character in buffer and nothing read. write out
// what's in the buffer
out.print(ch);
out.flush();
if (JNLPRuntime.isDebug()) {
if (ch == 10) {
System.out.println();
System.out.print("line: " + newline + " ");
newline++;
} else {
System.out.print(ch);
}
}
break;
} else if (i == 10) {
next = '\n';
} else {
next = (char) i;
}
this.sanitizeCharReadTooMuch = next;
// If the next chars are !--, then we've hit a comment tag,
// and should skip it.
if (ch == '<' && sanitizeCharReadTooMuch == '!') {
ch = (char) this.reader.read();
if (ch == '-') {
ch = (char) this.reader.read();
if (ch == '-') {
this.skipComment();
this.sanitizeCharReadTooMuch = '\0';
} else {
out.print('<');
out.print('!');
out.print('-');
this.sanitizeCharReadTooMuch = ch;
if (JNLPRuntime.isDebug()) {
System.out.print('<');
System.out.print('!');
System.out.print('-');
}
}
} else {
out.print('<');
out.print('!');
this.sanitizeCharReadTooMuch = ch;
if (JNLPRuntime.isDebug()) {
System.out.print('<');
System.out.print('!');
}
}
}
// Otherwise we haven't hit a comment, and we should write ch.
else {
out.print(ch);
if (JNLPRuntime.isDebug()) {
if (ch == 10) {
System.out.println();
System.out.print("line: " + newline + " ");
newline++;
} else {
System.out.print(ch);
}
}
}
prev = next;
}
out.close();
isr.close();
} catch (Exception e) {
// Print the stack trace here -- xml.parseFromReader() will
// throw the ParseException if something goes wrong.
e.printStackTrace();
}
}
}
|