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
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
package org.jivesoftware.util;
import org.dom4j.*;
import org.dom4j.io.OutputFormat;
import org.dom4j.tree.NamespaceStack;
import org.xml.sax.*;
import org.xml.sax.ext.LexicalHandler;
import org.xml.sax.helpers.XMLFilterImpl;
import java.io.*;
import java.util.*;
/**
* Replacement class of the original XMLWriter.java (version: 1.77) since the original is still
* using StringBuffer which is not fast.
*/
public class XMLWriter extends XMLFilterImpl implements LexicalHandler {
private static final String PAD_TEXT = " ";
protected static final String[] LEXICAL_HANDLER_NAMES = {
"http://xml.org/sax/properties/lexical-handler",
"http://xml.org/sax/handlers/LexicalHandler"
};
protected static final OutputFormat DEFAULT_FORMAT = new OutputFormat();
/** Should entityRefs by resolved when writing ? */
private boolean resolveEntityRefs = true;
/** Stores the last type of node written so algorithms can refer to the
* previous node type */
protected int lastOutputNodeType;
/** Stores the xml:space attribute value of preserve for whitespace flag */
protected boolean preserve=false;
/** The Writer used to output to */
protected Writer writer;
/** The Stack of namespaceStack written so far */
private NamespaceStack namespaceStack = new NamespaceStack();
/** The format used by this writer */
private OutputFormat format;
/** whether we should escape text */
private boolean escapeText = true;
/** The initial number of indentations (so you can print a whole
document indented, if you like) **/
private int indentLevel = 0;
/** buffer used when escaping strings */
private StringBuilder buffer = new StringBuilder();
/** whether we have added characters before from the same chunk of characters */
private boolean charactersAdded = false;
private char lastChar;
/** Whether a flush should occur after writing a document */
private boolean autoFlush;
/** Lexical handler we should delegate to */
private LexicalHandler lexicalHandler;
/** Whether comments should appear inside DTD declarations - defaults to false */
private boolean showCommentsInDTDs;
/** Is the writer curerntly inside a DTD definition? */
private boolean inDTD;
/** The namespaces used for the current element when consuming SAX events */
private Map namespacesMap;
/**
* what is the maximum allowed character code
* such as 127 in US-ASCII (7 bit) or 255 in ISO-* (8 bit)
* or -1 to not escape any characters (other than the special XML characters like < > &)
*/
private int maximumAllowedCharacter;
public XMLWriter(Writer writer) {
this( writer, DEFAULT_FORMAT );
}
public XMLWriter(Writer writer, OutputFormat format) {
this.writer = writer;
this.format = format;
namespaceStack.push(Namespace.NO_NAMESPACE);
}
public XMLWriter() {
this.format = DEFAULT_FORMAT;
this.writer = new BufferedWriter( new OutputStreamWriter( System.out ) );
this.autoFlush = true;
namespaceStack.push(Namespace.NO_NAMESPACE);
}
public XMLWriter(OutputStream out) throws UnsupportedEncodingException {
this.format = DEFAULT_FORMAT;
this.writer = createWriter(out, format.getEncoding());
this.autoFlush = true;
namespaceStack.push(Namespace.NO_NAMESPACE);
}
public XMLWriter(OutputStream out, OutputFormat format) throws UnsupportedEncodingException {
this.format = format;
this.writer = createWriter(out, format.getEncoding());
this.autoFlush = true;
namespaceStack.push(Namespace.NO_NAMESPACE);
}
public XMLWriter(OutputFormat format) throws UnsupportedEncodingException {
this.format = format;
this.writer = createWriter( System.out, format.getEncoding() );
this.autoFlush = true;
namespaceStack.push(Namespace.NO_NAMESPACE);
}
public void setWriter(Writer writer) {
this.writer = writer;
this.autoFlush = false;
}
public void setOutputStream(OutputStream out) throws UnsupportedEncodingException {
this.writer = createWriter(out, format.getEncoding());
this.autoFlush = true;
}
/**
* @return true if text thats output should be escaped.
* This is enabled by default. It could be disabled if
* the output format is textual, like in XSLT where we can have
* xml, html or text output.
*/
public boolean isEscapeText() {
return escapeText;
}
/**
* Sets whether text output should be escaped or not.
* This is enabled by default. It could be disabled if
* the output format is textual, like in XSLT where we can have
* xml, html or text output.
*/
public void setEscapeText(boolean escapeText) {
this.escapeText = escapeText;
}
/** Set the initial indentation level. This can be used to output
* a document (or, more likely, an element) starting at a given
* indent level, so it's not always flush against the left margin.
* Default: 0
*
* @param indentLevel the number of indents to start with
*/
public void setIndentLevel(int indentLevel) {
this.indentLevel = indentLevel;
}
/**
* Returns the maximum allowed character code that should be allowed
* unescaped which defaults to 127 in US-ASCII (7 bit) or
* 255 in ISO-* (8 bit).
*/
public int getMaximumAllowedCharacter() {
if (maximumAllowedCharacter == 0) {
maximumAllowedCharacter = defaultMaximumAllowedCharacter();
}
return maximumAllowedCharacter;
}
/**
* Sets the maximum allowed character code that should be allowed
* unescaped
* such as 127 in US-ASCII (7 bit) or 255 in ISO-* (8 bit)
* or -1 to not escape any characters (other than the special XML characters like < > &)
*
* If this is not explicitly set then it is defaulted from the encoding.
*
* @param maximumAllowedCharacter The maximumAllowedCharacter to set
*/
public void setMaximumAllowedCharacter(int maximumAllowedCharacter) {
this.maximumAllowedCharacter = maximumAllowedCharacter;
}
/** Flushes the underlying Writer */
public void flush() throws IOException {
writer.flush();
}
/** Closes the underlying Writer */
public void close() throws IOException {
writer.close();
}
/** Writes the new line text to the underlying Writer */
public void println() throws IOException {
writer.write( format.getLineSeparator() );
}
/** Writes the given {@link org.dom4j.Attribute}.
*
* @param attribute <code>Attribute</code> to output.
*/
public void write(Attribute attribute) throws IOException {
writeAttribute(attribute);
if ( autoFlush ) {
flush();
}
}
/** <p>This will print the <code>Document</code> to the current Writer.</p>
*
* <p> Warning: using your own Writer may cause the writer's
* preferred character encoding to be ignored. If you use
* encodings other than UTF8, we recommend using the method that
* takes an OutputStream instead. </p>
*
* <p>Note: as with all Writers, you may need to flush() yours
* after this method returns.</p>
*
* @param doc <code>Document</code> to format.
* @throws IOException - if there's any problem writing.
**/
public void write(Document doc) throws IOException {
writeDeclaration();
if (doc.getDocType() != null) {
indent();
writeDocType(doc.getDocType());
}
for ( int i = 0, size = doc.nodeCount(); i < size; i++ ) {
Node node = doc.node(i);
writeNode( node );
}
writePrintln();
if ( autoFlush ) {
flush();
}
}
/** <p>Writes the <code>{@link org.dom4j.Element}</code>, including
* its <code>{@link Attribute}</code>s, and its value, and all
* its content (child nodes) to the current Writer.</p>
*
* @param element <code>Element</code> to output.
*/
public void write(Element element) throws IOException {
writeElement(element);
if ( autoFlush ) {
flush();
}
}
/** Writes the given {@link CDATA}.
*
* @param cdata <code>CDATA</code> to output.
*/
public void write(CDATA cdata) throws IOException {
writeCDATA( cdata.getText() );
if ( autoFlush ) {
flush();
}
}
/** Writes the given {@link Comment}.
*
* @param comment <code>Comment</code> to output.
*/
public void write(Comment comment) throws IOException {
writeComment( comment.getText() );
if ( autoFlush ) {
flush();
}
}
/** Writes the given {@link DocumentType}.
*
* @param docType <code>DocumentType</code> to output.
*/
public void write(DocumentType docType) throws IOException {
writeDocType(docType);
if ( autoFlush ) {
flush();
}
}
/** Writes the given {@link Entity}.
*
* @param entity <code>Entity</code> to output.
*/
public void write(Entity entity) throws IOException {
writeEntity( entity );
if ( autoFlush ) {
flush();
}
}
/** Writes the given {@link Namespace}.
*
* @param namespace <code>Namespace</code> to output.
*/
public void write(Namespace namespace) throws IOException {
writeNamespace(namespace);
if ( autoFlush ) {
flush();
}
}
/** Writes the given {@link ProcessingInstruction}.
*
* @param processingInstruction <code>ProcessingInstruction</code> to output.
*/
public void write(ProcessingInstruction processingInstruction) throws IOException {
writeProcessingInstruction(processingInstruction);
if ( autoFlush ) {
flush();
}
}
/** <p>Print out a {@link String}, Perfoms
* the necessary entity escaping and whitespace stripping.</p>
*
* @param text is the text to output
*/
public void write(String text) throws IOException {
writeString(text);
if ( autoFlush ) {
flush();
}
}
/** Writes the given {@link Text}.
*
* @param text <code>Text</code> to output.
*/
public void write(Text text) throws IOException {
writeString(text.getText());
if ( autoFlush ) {
flush();
}
}
/** Writes the given {@link Node}.
*
* @param node <code>Node</code> to output.
*/
public void write(Node node) throws IOException {
writeNode(node);
if ( autoFlush ) {
flush();
}
}
/** Writes the given object which should be a String, a Node or a List
* of Nodes.
*
* @param object is the object to output.
*/
public void write(Object object) throws IOException {
if (object instanceof Node) {
write((Node) object);
}
else if (object instanceof String) {
write((String) object);
}
else if (object instanceof List) {
List list = (List) object;
for ( int i = 0, size = list.size(); i < size; i++ ) {
write( list.get(i) );
}
}
else if (object != null) {
throw new IOException( "Invalid object: " + object );
}
}
/** <p>Writes the opening tag of an {@link Element},
* including its {@link Attribute}s
* but without its content.</p>
*
* @param element <code>Element</code> to output.
*/
public void writeOpen(Element element) throws IOException {
writer.write("<");
writer.write( element.getQualifiedName() );
writeAttributes(element);
writer.write(">");
}
/** <p>Writes the closing tag of an {@link Element}</p>
*
* @param element <code>Element</code> to output.
*/
public void writeClose(Element element) throws IOException {
writeClose( element.getQualifiedName() );
}
// XMLFilterImpl methods
//-------------------------------------------------------------------------
public void parse(InputSource source) throws IOException, SAXException {
installLexicalHandler();
super.parse(source);
}
public void setProperty(String name, Object value) throws SAXNotRecognizedException, SAXNotSupportedException {
for (int i = 0; i < LEXICAL_HANDLER_NAMES.length; i++) {
if (LEXICAL_HANDLER_NAMES[i].equals(name)) {
setLexicalHandler((LexicalHandler) value);
return;
}
}
super.setProperty(name, value);
}
public Object getProperty(String name) throws SAXNotRecognizedException, SAXNotSupportedException {
for (int i = 0; i < LEXICAL_HANDLER_NAMES.length; i++) {
if (LEXICAL_HANDLER_NAMES[i].equals(name)) {
return getLexicalHandler();
}
}
return super.getProperty(name);
}
public void setLexicalHandler (LexicalHandler handler) {
if (handler == null) {
throw new NullPointerException("Null lexical handler");
}
else {
this.lexicalHandler = handler;
}
}
public LexicalHandler getLexicalHandler(){
return lexicalHandler;
}
// ContentHandler interface
//-------------------------------------------------------------------------
public void setDocumentLocator(Locator locator) {
super.setDocumentLocator(locator);
}
public void startDocument() throws SAXException {
try {
writeDeclaration();
super.startDocument();
}
catch (IOException e) {
handleException(e);
}
}
public void endDocument() throws SAXException {
super.endDocument();
if ( autoFlush ) {
try {
flush();
} catch ( IOException e) {}
}
}
public void startPrefixMapping(String prefix, String uri) throws SAXException {
if ( namespacesMap == null ) {
namespacesMap = new HashMap();
}
namespacesMap.put(prefix, uri);
super.startPrefixMapping(prefix, uri);
}
public void endPrefixMapping(String prefix) throws SAXException {
super.endPrefixMapping(prefix);
}
public void startElement(String namespaceURI, String localName, String qName, Attributes attributes) throws SAXException {
try {
charactersAdded = false;
writePrintln();
indent();
writer.write("<");
writer.write(qName);
writeNamespaces();
writeAttributes( attributes );
writer.write(">");
++indentLevel;
lastOutputNodeType = Node.ELEMENT_NODE;
super.startElement( namespaceURI, localName, qName, attributes );
}
catch (IOException e) {
handleException(e);
}
}
public void endElement(String namespaceURI, String localName, String qName) throws SAXException {
try {
charactersAdded = false;
--indentLevel;
if ( lastOutputNodeType == Node.ELEMENT_NODE ) {
writePrintln();
indent();
}
// XXXX: need to determine this using a stack and checking for
// content / children
boolean hadContent = true;
if ( hadContent ) {
writeClose(qName);
}
else {
writeEmptyElementClose(qName);
}
lastOutputNodeType = Node.ELEMENT_NODE;
super.endElement( namespaceURI, localName, qName );
}
catch (IOException e) {
handleException(e);
}
}
public void characters(char[] ch, int start, int length) throws SAXException {
if (ch == null || ch.length == 0 || length <= 0) {
return;
}
try {
/*
* we can't use the writeString method here because it's possible
* we don't receive all characters at once and calling writeString
* would cause unwanted spaces to be added in between these chunks
* of character arrays.
*/
String string = new String(ch, start, length);
if (escapeText) {
string = escapeElementEntities(string);
}
if (format.isTrimText()) {
if ((lastOutputNodeType == Node.TEXT_NODE) && !charactersAdded) {
writer.write(" ");
} else if (charactersAdded && Character.isWhitespace(lastChar)) {
writer.write(lastChar);
}
String delim = "";
StringTokenizer tokens = new StringTokenizer(string);
while (tokens.hasMoreTokens()) {
writer.write(delim);
writer.write(tokens.nextToken());
delim = " ";
}
} else {
writer.write(string);
}
charactersAdded = true;
lastChar = ch[start + length - 1];
lastOutputNodeType = Node.TEXT_NODE;
super.characters(ch, start, length);
}
catch (IOException e) {
handleException(e);
}
}
public void ignorableWhitespace(char[] ch, int start, int length) throws SAXException {
super.ignorableWhitespace(ch, start, length);
}
public void processingInstruction(String target, String data) throws SAXException {
try {
indent();
writer.write("<?");
writer.write(target);
writer.write(" ");
writer.write(data);
writer.write("?>");
writePrintln();
lastOutputNodeType = Node.PROCESSING_INSTRUCTION_NODE;
super.processingInstruction(target, data);
}
catch (IOException e) {
handleException(e);
}
}
// DTDHandler interface
//-------------------------------------------------------------------------
public void notationDecl(String name, String publicID, String systemID) throws SAXException {
super.notationDecl(name, publicID, systemID);
}
public void unparsedEntityDecl(String name, String publicID, String systemID, String notationName) throws SAXException {
super.unparsedEntityDecl(name, publicID, systemID, notationName);
}
// LexicalHandler interface
//-------------------------------------------------------------------------
public void startDTD(String name, String publicID, String systemID) throws SAXException {
inDTD = true;
try {
writeDocType(name, publicID, systemID);
}
catch (IOException e) {
handleException(e);
}
if (lexicalHandler != null) {
lexicalHandler.startDTD(name, publicID, systemID);
}
}
public void endDTD() throws SAXException {
inDTD = false;
if (lexicalHandler != null) {
lexicalHandler.endDTD();
}
}
public void startCDATA() throws SAXException {
try {
writer.write( "<![CDATA[" );
}
catch (IOException e) {
handleException(e);
}
if (lexicalHandler != null) {
lexicalHandler.startCDATA();
}
}
public void endCDATA() throws SAXException {
try {
writer.write( "]]>" );
}
catch (IOException e) {
handleException(e);
}
if (lexicalHandler != null) {
lexicalHandler.endCDATA();
}
}
public void startEntity(String name) throws SAXException {
try {
writeEntityRef(name);
}
catch (IOException e) {
handleException(e);
}
if (lexicalHandler != null) {
lexicalHandler.startEntity(name);
}
}
public void endEntity(String name) throws SAXException {
if (lexicalHandler != null) {
lexicalHandler.endEntity(name);
}
}
public void comment(char[] ch, int start, int length) throws SAXException {
if ( showCommentsInDTDs || ! inDTD ) {
try {
charactersAdded = false;
writeComment( new String(ch, start, length) );
}
catch (IOException e) {
handleException(e);
}
}
if (lexicalHandler != null) {
lexicalHandler.comment(ch, start, length);
}
}
// Implementation methods
//-------------------------------------------------------------------------
protected void writeElement(Element element) throws IOException {
int size = element.nodeCount();
String qualifiedName = element.getQualifiedName();
writePrintln();
indent();
writer.write("<");
writer.write(qualifiedName);
int previouslyDeclaredNamespaces = namespaceStack.size();
Namespace ns = element.getNamespace();
if (isNamespaceDeclaration( ns ) ) {
namespaceStack.push(ns);
writeNamespace(ns);
}
// Print out additional namespace declarations
boolean textOnly = true;
for ( int i = 0; i < size; i++ ) {
Node node = element.node(i);
if ( node instanceof Namespace ) {
Namespace additional = (Namespace) node;
if (isNamespaceDeclaration( additional ) ) {
namespaceStack.push(additional);
writeNamespace(additional);
}
}
else if ( node instanceof Element) {
textOnly = false;
}
else if ( node instanceof Comment) {
textOnly = false;
}
}
writeAttributes(element);
lastOutputNodeType = Node.ELEMENT_NODE;
if ( size <= 0 ) {
writeEmptyElementClose(qualifiedName);
}
else {
writer.write(">");
if ( textOnly ) {
// we have at least one text node so lets assume
// that its non-empty
writeElementContent(element);
}
else {
// we know it's not null or empty from above
++indentLevel;
writeElementContent(element);
--indentLevel;
writePrintln();
indent();
}
writer.write("</");
writer.write(qualifiedName);
writer.write(">");
}
// remove declared namespaceStack from stack
while (namespaceStack.size() > previouslyDeclaredNamespaces) {
namespaceStack.pop();
}
lastOutputNodeType = Node.ELEMENT_NODE;
}
/**
* Determines if element is a special case of XML elements
* where it contains an xml:space attribute of "preserve".
* If it does, then retain whitespace.
*/
protected final boolean isElementSpacePreserved(Element element) {
final Attribute attr = (Attribute)element.attribute("space");
boolean preserveFound=preserve; //default to global state
if (attr!=null) {
if ("xml".equals(attr.getNamespacePrefix()) &&
"preserve".equals(attr.getText())) {
preserveFound = true;
}
else {
preserveFound = false;
}
}
return preserveFound;
}
/** Outputs the content of the given element. If whitespace trimming is
* enabled then all adjacent text nodes are appended together before
* the whitespace trimming occurs to avoid problems with multiple
* text nodes being created due to text content that spans parser buffers
* in a SAX parser.
*/
protected void writeElementContent(Element element) throws IOException {
boolean trim = format.isTrimText();
boolean oldPreserve=preserve;
if (trim) { //verify we have to before more expensive test
preserve=isElementSpacePreserved(element);
trim = !preserve;
}
if (trim) {
// concatenate adjacent text nodes together
// so that whitespace trimming works properly
Text lastTextNode = null;
StringBuilder buffer = null;
boolean textOnly = true;
for ( int i = 0, size = element.nodeCount(); i < size; i++ ) {
Node node = element.node(i);
if ( node instanceof Text ) {
if ( lastTextNode == null ) {
lastTextNode = (Text) node;
}
else {
if (buffer == null) {
buffer = new StringBuilder( lastTextNode.getText() );
}
buffer.append( ((Text) node).getText() );
}
}
else {
if (!textOnly && format.isPadText()) {
writer.write(PAD_TEXT);
}
textOnly = false;
if ( lastTextNode != null ) {
if ( buffer != null ) {
writeString( buffer.toString() );
buffer = null;
}
else {
writeString( lastTextNode.getText() );
}
lastTextNode = null;
if (format.isPadText()) {
writer.write(PAD_TEXT);
}
}
writeNode(node);
}
}
if ( lastTextNode != null ) {
if (!textOnly && format.isPadText()) {
writer.write(PAD_TEXT);
}
if ( buffer != null ) {
writeString( buffer.toString() );
buffer = null;
}
else {
writeString( lastTextNode.getText() );
}
lastTextNode = null;
}
}
else {
Node lastTextNode = null;
for ( int i = 0, size = element.nodeCount(); i < size; i++ ) {
Node node = element.node(i);
if (node instanceof Text) {
writeNode(node);
lastTextNode = node;
} else {
if ((lastTextNode != null) && format.isPadText()) {
writer.write(PAD_TEXT);
}
writeNode(node);
if ((lastTextNode != null) && format.isPadText()) {
writer.write(PAD_TEXT);
}
lastTextNode = null;
}
}
}
preserve=oldPreserve;
}
protected void writeCDATA(String text) throws IOException {
writer.write( "<![CDATA[" );
if (text != null) {
writer.write( text );
}
writer.write( "]]>" );
lastOutputNodeType = Node.CDATA_SECTION_NODE;
}
protected void writeDocType(DocumentType docType) throws IOException {
if (docType != null) {
docType.write( writer );
//writeDocType( docType.getElementName(), docType.getPublicID(), docType.getSystemID() );
writePrintln();
}
}
protected void writeNamespace(Namespace namespace) throws IOException {
if ( namespace != null ) {
writeNamespace(namespace.getPrefix(), namespace.getURI());
}
}
/**
* Writes the SAX namepsaces
*/
protected void writeNamespaces() throws IOException {
if ( namespacesMap != null ) {
for ( Iterator iter = namespacesMap.entrySet().iterator(); iter.hasNext(); ) {
Map.Entry entry = (Map.Entry) iter.next();
String prefix = (String) entry.getKey();
String uri = (String) entry.getValue();
writeNamespace(prefix, uri);
}
namespacesMap = null;
}
}
/**
* Writes the SAX namepsaces
*/
protected void writeNamespace(String prefix, String uri) throws IOException {
if ( prefix != null && prefix.length() > 0 ) {
writer.write(" xmlns:");
writer.write(prefix);
writer.write("=\"");
}
else {
writer.write(" xmlns=\"");
}
writer.write(uri);
writer.write("\"");
}
protected void writeProcessingInstruction(ProcessingInstruction processingInstruction) throws IOException {
//indent();
writer.write( "<?" );
writer.write( processingInstruction.getName() );
writer.write( " " );
writer.write( processingInstruction.getText() );
writer.write( "?>" );
writePrintln();
lastOutputNodeType = Node.PROCESSING_INSTRUCTION_NODE;
}
protected void writeString(String text) throws IOException {
if ( text != null && text.length() > 0 ) {
if ( escapeText ) {
text = escapeElementEntities(text);
}
// if (format.isPadText()) {
// if (lastOutputNodeType == Node.ELEMENT_NODE) {
// writer.write(PAD_TEXT);
// }
// }
if (format.isTrimText()) {
boolean first = true;
StringTokenizer tokenizer = new StringTokenizer(text);
while (tokenizer.hasMoreTokens()) {
String token = tokenizer.nextToken();
if ( first ) {
first = false;
if ( lastOutputNodeType == Node.TEXT_NODE ) {
writer.write(" ");
}
}
else {
writer.write(" ");
}
writer.write(token);
lastOutputNodeType = Node.TEXT_NODE;
}
}
else {
lastOutputNodeType = Node.TEXT_NODE;
writer.write(text);
}
}
}
/**
* This method is used to write out Nodes that contain text
* and still allow for xml:space to be handled properly.
*
*/
protected void writeNodeText(Node node) throws IOException {
String text = node.getText();
if (text != null && text.length() > 0) {
if (escapeText) {
text = escapeElementEntities(text);
}
lastOutputNodeType = Node.TEXT_NODE;
writer.write(text);
}
}
protected void writeNode(Node node) throws IOException {
int nodeType = node.getNodeType();
switch (nodeType) {
case Node.ELEMENT_NODE:
writeElement((Element) node);
break;
case Node.ATTRIBUTE_NODE:
writeAttribute((Attribute) node);
break;
case Node.TEXT_NODE:
writeNodeText(node);
//write((Text) node);
break;
case Node.CDATA_SECTION_NODE:
writeCDATA(node.getText());
break;
case Node.ENTITY_REFERENCE_NODE:
writeEntity((Entity) node);
break;
case Node.PROCESSING_INSTRUCTION_NODE:
writeProcessingInstruction((ProcessingInstruction) node);
break;
case Node.COMMENT_NODE:
writeComment(node.getText());
break;
case Node.DOCUMENT_NODE:
write((Document) node);
break;
case Node.DOCUMENT_TYPE_NODE:
writeDocType((DocumentType) node);
break;
case Node.NAMESPACE_NODE:
// Will be output with attributes
//write((Namespace) node);
break;
default:
throw new IOException( "Invalid node type: " + node );
}
}
protected void installLexicalHandler() {
XMLReader parent = getParent();
if (parent == null) {
throw new NullPointerException("No parent for filter");
}
// try to register for lexical events
for (int i = 0; i < LEXICAL_HANDLER_NAMES.length; i++) {
try {
parent.setProperty(LEXICAL_HANDLER_NAMES[i], this);
break;
}
catch (SAXNotRecognizedException ex) {
// ignore
}
catch (SAXNotSupportedException ex) {
// ignore
}
}
}
protected void writeDocType(String name, String publicID, String systemID) throws IOException {
boolean hasPublic = false;
writer.write("<!DOCTYPE ");
writer.write(name);
if ((publicID != null) && (!publicID.equals(""))) {
writer.write(" PUBLIC \"");
writer.write(publicID);
writer.write("\"");
hasPublic = true;
}
if ((systemID != null) && (!systemID.equals(""))) {
if (!hasPublic) {
writer.write(" SYSTEM");
}
writer.write(" \"");
writer.write(systemID);
writer.write("\"");
}
writer.write(">");
writePrintln();
}
protected void writeEntity(Entity entity) throws IOException {
if (!resolveEntityRefs()) {
writeEntityRef( entity.getName() );
} else {
writer.write(entity.getText());
}
}
protected void writeEntityRef(String name) throws IOException {
writer.write( "&" );
writer.write( name );
writer.write( ";" );
lastOutputNodeType = Node.ENTITY_REFERENCE_NODE;
}
protected void writeComment(String text) throws IOException {
if (format.isNewlines()) {
println();
indent();
}
writer.write( "<!--" );
writer.write( text );
writer.write( "-->" );
lastOutputNodeType = Node.COMMENT_NODE;
}
/** Writes the attributes of the given element
*
*/
protected void writeAttributes( Element element ) throws IOException {
// I do not yet handle the case where the same prefix maps to
// two different URIs. For attributes on the same element
// this is illegal; but as yet we don't throw an exception
// if someone tries to do this
for ( int i = 0, size = element.attributeCount(); i < size; i++ ) {
Attribute attribute = element.attribute(i);
Namespace ns = attribute.getNamespace();
if (ns != null && ns != Namespace.NO_NAMESPACE && ns != Namespace.XML_NAMESPACE) {
String prefix = ns.getPrefix();
String uri = namespaceStack.getURI(prefix);
if (!ns.getURI().equals(uri)) { // output a new namespace declaration
writeNamespace(ns);
namespaceStack.push(ns);
}
}
// If the attribute is a namespace declaration, check if we have already
// written that declaration elsewhere (if that's the case, it must be
// in the namespace stack
String attName = attribute.getName();
if (attName.startsWith("xmlns:")) {
String prefix = attName.substring(6);
if (namespaceStack.getNamespaceForPrefix(prefix) == null) {
String uri = attribute.getValue();
namespaceStack.push(prefix, uri);
writeNamespace(prefix, uri);
}
} else if (attName.equals("xmlns")) {
if (namespaceStack.getDefaultNamespace() == null) {
String uri = attribute.getValue();
namespaceStack.push(null, uri);
writeNamespace(null, uri);
}
} else {
char quote = format.getAttributeQuoteCharacter();
writer.write(" ");
writer.write(attribute.getQualifiedName());
writer.write("=");
writer.write(quote);
writeEscapeAttributeEntities(attribute.getValue());
writer.write(quote);
}
}
}
protected void writeAttribute(Attribute attribute) throws IOException {
writer.write(" ");
writer.write(attribute.getQualifiedName());
writer.write("=");
char quote = format.getAttributeQuoteCharacter();
writer.write(quote);
writeEscapeAttributeEntities(attribute.getValue());
writer.write(quote);
lastOutputNodeType = Node.ATTRIBUTE_NODE;
}
protected void writeAttributes(Attributes attributes) throws IOException {
for (int i = 0, size = attributes.getLength(); i < size; i++) {
writeAttribute( attributes, i );
}
}
protected void writeAttribute(Attributes attributes, int index) throws IOException {
char quote = format.getAttributeQuoteCharacter();
writer.write(" ");
writer.write(attributes.getQName(index));
writer.write("=");
writer.write(quote);
writeEscapeAttributeEntities(attributes.getValue(index));
writer.write(quote);
}
protected void indent() throws IOException {
String indent = format.getIndent();
if ( indent != null && indent.length() > 0 ) {
for ( int i = 0; i < indentLevel; i++ ) {
writer.write(indent);
}
}
}
/**
* <p>
* This will print a new line only if the newlines flag was set to true
* </p>
*/
protected void writePrintln() throws IOException {
if (format.isNewlines()) {
writer.write( format.getLineSeparator() );
}
}
/**
* Get an OutputStreamWriter, use preferred encoding.
*/
protected Writer createWriter(OutputStream outStream, String encoding) throws UnsupportedEncodingException {
return new BufferedWriter(
new OutputStreamWriter( outStream, encoding )
);
}
/**
* <p>
* This will write the declaration to the given Writer.
* Assumes XML version 1.0 since we don't directly know.
* </p>
*/
protected void writeDeclaration() throws IOException {
String encoding = format.getEncoding();
// Only print of declaration is not suppressed
if (! format.isSuppressDeclaration()) {
// Assume 1.0 version
if (encoding.equals("UTF8")) {
writer.write("<?xml version=\"1.0\"");
if (!format.isOmitEncoding()) {
writer.write(" encoding=\"UTF-8\"");
}
writer.write("?>");
} else {
writer.write("<?xml version=\"1.0\"");
if (! format.isOmitEncoding()) {
writer.write(" encoding=\"" + encoding + "\"");
}
writer.write("?>");
}
if (format.isNewLineAfterDeclaration()) {
println();
}
}
}
protected void writeClose(String qualifiedName) throws IOException {
writer.write("</");
writer.write(qualifiedName);
writer.write(">");
}
protected void writeEmptyElementClose(String qualifiedName) throws IOException {
// Simply close up
if (! format.isExpandEmptyElements()) {
writer.write("/>");
} else {
writer.write("></");
writer.write(qualifiedName);
writer.write(">");
}
}
protected boolean isExpandEmptyElements() {
return format.isExpandEmptyElements();
}
/** This will take the pre-defined entities in XML 1.0 and
* convert their character representation to the appropriate
* entity reference, suitable for XML attributes.
*/
protected String escapeElementEntities(String text) {
char[] block = null;
int i, last = 0, size = text.length();
for ( i = 0; i < size; i++ ) {
String entity = null;
char c = text.charAt(i);
switch( c ) {
case '<' :
entity = "<";
break;
case '>' :
entity = ">";
break;
case '&' :
entity = "&";
break;
case '\t': case '\n': case '\r':
// don't encode standard whitespace characters
if (preserve) {
entity=String.valueOf(c);
}
break;
default:
if (c < 32 || shouldEncodeChar(c)) {
entity = "&#" + (int) c + ";";
}
break;
}
if (entity != null) {
if ( block == null ) {
block = text.toCharArray();
}
buffer.append(block, last, i - last);
buffer.append(entity);
last = i + 1;
}
}
if ( last == 0 ) {
return text;
}
if ( last < size ) {
if ( block == null ) {
block = text.toCharArray();
}
buffer.append(block, last, i - last);
}
String answer = buffer.toString();
buffer.setLength(0);
return answer;
}
protected void writeEscapeAttributeEntities(String text) throws IOException {
if ( text != null ) {
String escapedText = escapeAttributeEntities( text );
writer.write( escapedText );
}
}
/** This will take the pre-defined entities in XML 1.0 and
* convert their character representation to the appropriate
* entity reference, suitable for XML attributes.
*/
protected String escapeAttributeEntities(String text) {
char quote = format.getAttributeQuoteCharacter();
char[] block = null;
int i, last = 0, size = text.length();
for ( i = 0; i < size; i++ ) {
String entity = null;
char c = text.charAt(i);
switch( c ) {
case '<' :
entity = "<";
break;
case '>' :
entity = ">";
break;
case '\'' :
if (quote == '\'') {
entity = "'";
}
break;
case '\"' :
if (quote == '\"') {
entity = """;
}
break;
case '&' :
entity = "&";
break;
case '\t': case '\n': case '\r':
// don't encode standard whitespace characters
break;
default:
if (c < 32 || shouldEncodeChar(c)) {
entity = "&#" + (int) c + ";";
}
break;
}
if (entity != null) {
if ( block == null ) {
block = text.toCharArray();
}
buffer.append(block, last, i - last);
buffer.append(entity);
last = i + 1;
}
}
if ( last == 0 ) {
return text;
}
if ( last < size ) {
if ( block == null ) {
block = text.toCharArray();
}
buffer.append(block, last, i - last);
}
String answer = buffer.toString();
buffer.setLength(0);
return answer;
}
/**
* Should the given character be escaped. This depends on the
* encoding of the document.
*
* @return boolean
*/
protected boolean shouldEncodeChar(char c) {
int max = getMaximumAllowedCharacter();
return max > 0 && c > max;
}
/**
* Returns the maximum allowed character code that should be allowed
* unescaped which defaults to 127 in US-ASCII (7 bit) or
* 255 in ISO-* (8 bit).
*/
protected int defaultMaximumAllowedCharacter() {
String encoding = format.getEncoding();
if (encoding != null) {
if (encoding.equals("US-ASCII")) {
return 127;
}
}
// no encoding for things like ISO-*, UTF-8 or UTF-16
return -1;
}
protected boolean isNamespaceDeclaration( Namespace ns ) {
if (ns != null && ns != Namespace.XML_NAMESPACE) {
String uri = ns.getURI();
if ( uri != null ) {
if ( ! namespaceStack.contains( ns ) ) {
return true;
}
}
}
return false;
}
protected void handleException(IOException e) throws SAXException {
throw new SAXException(e);
}
//Laramie Crocker 4/8/2002 10:38AM
/** Lets subclasses get at the current format object, so they can call setTrimText, setNewLines, etc.
* Put in to support the HTMLWriter, in the way
* that it pushes the current newline/trim state onto a stack and overrides
* the state within preformatted tags.
*/
protected OutputFormat getOutputFormat() {
return format;
}
public boolean resolveEntityRefs() {
return resolveEntityRefs;
}
public void setResolveEntityRefs(boolean resolve) {
this.resolveEntityRefs = resolve;
}
}