obj.js
57.2 KB
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
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
/* Copyright 2012 Mozilla Foundation
*
* Licensed 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.
*/
'use strict';
(function (root, factory) {
if (typeof define === 'function' && define.amd) {
define('pdfjs/core/obj', ['exports', 'pdfjs/shared/util',
'pdfjs/core/primitives', 'pdfjs/core/crypto', 'pdfjs/core/parser',
'pdfjs/core/chunked_stream', 'pdfjs/core/colorspace'], factory);
} else if (typeof exports !== 'undefined') {
factory(exports, require('../shared/util.js'), require('./primitives.js'),
require('./crypto.js'), require('./parser.js'),
require('./chunked_stream.js'), require('./colorspace.js'));
} else {
factory((root.pdfjsCoreObj = {}), root.pdfjsSharedUtil,
root.pdfjsCorePrimitives, root.pdfjsCoreCrypto, root.pdfjsCoreParser,
root.pdfjsCoreChunkedStream, root.pdfjsCoreColorSpace);
}
}(this, function (exports, sharedUtil, corePrimitives, coreCrypto, coreParser,
coreChunkedStream, coreColorSpace) {
var InvalidPDFException = sharedUtil.InvalidPDFException;
var MissingDataException = sharedUtil.MissingDataException;
var XRefParseException = sharedUtil.XRefParseException;
var assert = sharedUtil.assert;
var bytesToString = sharedUtil.bytesToString;
var createPromiseCapability = sharedUtil.createPromiseCapability;
var error = sharedUtil.error;
var info = sharedUtil.info;
var isArray = sharedUtil.isArray;
var isBool = sharedUtil.isBool;
var isInt = sharedUtil.isInt;
var isString = sharedUtil.isString;
var shadow = sharedUtil.shadow;
var stringToPDFString = sharedUtil.stringToPDFString;
var stringToUTF8String = sharedUtil.stringToUTF8String;
var warn = sharedUtil.warn;
var createValidAbsoluteUrl = sharedUtil.createValidAbsoluteUrl;
var Util = sharedUtil.Util;
var Ref = corePrimitives.Ref;
var RefSet = corePrimitives.RefSet;
var RefSetCache = corePrimitives.RefSetCache;
var isName = corePrimitives.isName;
var isCmd = corePrimitives.isCmd;
var isDict = corePrimitives.isDict;
var isRef = corePrimitives.isRef;
var isRefsEqual = corePrimitives.isRefsEqual;
var isStream = corePrimitives.isStream;
var CipherTransformFactory = coreCrypto.CipherTransformFactory;
var Lexer = coreParser.Lexer;
var Parser = coreParser.Parser;
var ChunkedStream = coreChunkedStream.ChunkedStream;
var ColorSpace = coreColorSpace.ColorSpace;
var Catalog = (function CatalogClosure() {
function Catalog(pdfManager, xref, pageFactory) {
this.pdfManager = pdfManager;
this.xref = xref;
this.catDict = xref.getCatalogObj();
this.fontCache = new RefSetCache();
assert(isDict(this.catDict),
'catalog object is not a dictionary');
// TODO refactor to move getPage() to the PDFDocument.
this.pageFactory = pageFactory;
this.pagePromises = [];
}
Catalog.prototype = {
get metadata() {
var streamRef = this.catDict.getRaw('Metadata');
if (!isRef(streamRef)) {
return shadow(this, 'metadata', null);
}
var encryptMetadata = (!this.xref.encrypt ? false :
this.xref.encrypt.encryptMetadata);
var stream = this.xref.fetch(streamRef, !encryptMetadata);
var metadata;
if (stream && isDict(stream.dict)) {
var type = stream.dict.get('Type');
var subtype = stream.dict.get('Subtype');
if (isName(type, 'Metadata') && isName(subtype, 'XML')) {
// XXX: This should examine the charset the XML document defines,
// however since there are currently no real means to decode
// arbitrary charsets, let's just hope that the author of the PDF
// was reasonable enough to stick with the XML default charset,
// which is UTF-8.
try {
metadata = stringToUTF8String(bytesToString(stream.getBytes()));
} catch (e) {
info('Skipping invalid metadata.');
}
}
}
return shadow(this, 'metadata', metadata);
},
get toplevelPagesDict() {
var pagesObj = this.catDict.get('Pages');
assert(isDict(pagesObj), 'invalid top-level pages dictionary');
// shadow the prototype getter
return shadow(this, 'toplevelPagesDict', pagesObj);
},
get documentOutline() {
var obj = null;
try {
obj = this.readDocumentOutline();
} catch (ex) {
if (ex instanceof MissingDataException) {
throw ex;
}
warn('Unable to read document outline');
}
return shadow(this, 'documentOutline', obj);
},
readDocumentOutline: function Catalog_readDocumentOutline() {
var obj = this.catDict.get('Outlines');
if (!isDict(obj)) {
return null;
}
obj = obj.getRaw('First');
if (!isRef(obj)) {
return null;
}
var root = { items: [] };
var queue = [{obj: obj, parent: root}];
// To avoid recursion, keep track of the already processed items.
var processed = new RefSet();
processed.put(obj);
var xref = this.xref, blackColor = new Uint8Array(3);
while (queue.length > 0) {
var i = queue.shift();
var outlineDict = xref.fetchIfRef(i.obj);
if (outlineDict === null) {
continue;
}
assert(outlineDict.has('Title'), 'Invalid outline item');
var data = { url: null, dest: null, };
Catalog.parseDestDictionary({
destDict: outlineDict,
resultObj: data,
docBaseUrl: this.pdfManager.docBaseUrl,
});
var title = outlineDict.get('Title');
var flags = outlineDict.get('F') || 0;
var color = outlineDict.getArray('C'), rgbColor = blackColor;
// We only need to parse the color when it's valid, and non-default.
if (isArray(color) && color.length === 3 &&
(color[0] !== 0 || color[1] !== 0 || color[2] !== 0)) {
rgbColor = ColorSpace.singletons.rgb.getRgb(color, 0);
}
var outlineItem = {
dest: data.dest,
url: data.url,
unsafeUrl: data.unsafeUrl,
newWindow: data.newWindow,
title: stringToPDFString(title),
color: rgbColor,
count: outlineDict.get('Count'),
bold: !!(flags & 2),
italic: !!(flags & 1),
items: []
};
i.parent.items.push(outlineItem);
obj = outlineDict.getRaw('First');
if (isRef(obj) && !processed.has(obj)) {
queue.push({obj: obj, parent: outlineItem});
processed.put(obj);
}
obj = outlineDict.getRaw('Next');
if (isRef(obj) && !processed.has(obj)) {
queue.push({obj: obj, parent: i.parent});
processed.put(obj);
}
}
return (root.items.length > 0 ? root.items : null);
},
get numPages() {
var obj = this.toplevelPagesDict.get('Count');
assert(
isInt(obj),
'page count in top level pages object is not an integer'
);
// shadow the prototype getter
return shadow(this, 'num', obj);
},
get destinations() {
function fetchDestination(dest) {
return isDict(dest) ? dest.get('D') : dest;
}
var xref = this.xref;
var dests = {}, nameTreeRef, nameDictionaryRef;
var obj = this.catDict.get('Names');
if (obj && obj.has('Dests')) {
nameTreeRef = obj.getRaw('Dests');
} else if (this.catDict.has('Dests')) {
nameDictionaryRef = this.catDict.get('Dests');
}
if (nameDictionaryRef) {
// reading simple destination dictionary
obj = nameDictionaryRef;
obj.forEach(function catalogForEach(key, value) {
if (!value) {
return;
}
dests[key] = fetchDestination(value);
});
}
if (nameTreeRef) {
var nameTree = new NameTree(nameTreeRef, xref);
var names = nameTree.getAll();
for (var name in names) {
dests[name] = fetchDestination(names[name]);
}
}
return shadow(this, 'destinations', dests);
},
getDestination: function Catalog_getDestination(destinationId) {
function fetchDestination(dest) {
return isDict(dest) ? dest.get('D') : dest;
}
var xref = this.xref;
var dest = null, nameTreeRef, nameDictionaryRef;
var obj = this.catDict.get('Names');
if (obj && obj.has('Dests')) {
nameTreeRef = obj.getRaw('Dests');
} else if (this.catDict.has('Dests')) {
nameDictionaryRef = this.catDict.get('Dests');
}
if (nameDictionaryRef) { // Simple destination dictionary.
var value = nameDictionaryRef.get(destinationId);
if (value) {
dest = fetchDestination(value);
}
}
if (nameTreeRef) {
var nameTree = new NameTree(nameTreeRef, xref);
dest = fetchDestination(nameTree.get(destinationId));
}
return dest;
},
get pageLabels() {
var obj = null;
try {
obj = this.readPageLabels();
} catch (ex) {
if (ex instanceof MissingDataException) {
throw ex;
}
warn('Unable to read page labels.');
}
return shadow(this, 'pageLabels', obj);
},
readPageLabels: function Catalog_readPageLabels() {
var obj = this.catDict.getRaw('PageLabels');
if (!obj) {
return null;
}
var pageLabels = new Array(this.numPages);
var style = null;
var prefix = '';
var numberTree = new NumberTree(obj, this.xref);
var nums = numberTree.getAll();
var currentLabel = '', currentIndex = 1;
for (var i = 0, ii = this.numPages; i < ii; i++) {
if (i in nums) {
var labelDict = nums[i];
assert(isDict(labelDict), 'The PageLabel is not a dictionary.');
var type = labelDict.get('Type');
assert(!type || isName(type, 'PageLabel'),
'Invalid type in PageLabel dictionary.');
var s = labelDict.get('S');
assert(!s || isName(s), 'Invalid style in PageLabel dictionary.');
style = s ? s.name : null;
var p = labelDict.get('P');
assert(!p || isString(p), 'Invalid prefix in PageLabel dictionary.');
prefix = p ? stringToPDFString(p) : '';
var st = labelDict.get('St');
assert(!st || (isInt(st) && st >= 1),
'Invalid start in PageLabel dictionary.');
currentIndex = st || 1;
}
switch (style) {
case 'D':
currentLabel = currentIndex;
break;
case 'R':
case 'r':
currentLabel = Util.toRoman(currentIndex, style === 'r');
break;
case 'A':
case 'a':
var LIMIT = 26; // Use only the characters A--Z, or a--z.
var A_UPPER_CASE = 0x41, A_LOWER_CASE = 0x61;
var baseCharCode = (style === 'a' ? A_LOWER_CASE : A_UPPER_CASE);
var letterIndex = currentIndex - 1;
var character = String.fromCharCode(baseCharCode +
(letterIndex % LIMIT));
var charBuf = [];
for (var j = 0, jj = (letterIndex / LIMIT) | 0; j <= jj; j++) {
charBuf.push(character);
}
currentLabel = charBuf.join('');
break;
default:
assert(!style,
'Invalid style "' + style + '" in PageLabel dictionary.');
}
pageLabels[i] = prefix + currentLabel;
currentLabel = '';
currentIndex++;
}
return pageLabels;
},
get attachments() {
var xref = this.xref;
var attachments = null, nameTreeRef;
var obj = this.catDict.get('Names');
if (obj) {
nameTreeRef = obj.getRaw('EmbeddedFiles');
}
if (nameTreeRef) {
var nameTree = new NameTree(nameTreeRef, xref);
var names = nameTree.getAll();
for (var name in names) {
var fs = new FileSpec(names[name], xref);
if (!attachments) {
attachments = Object.create(null);
}
attachments[stringToPDFString(name)] = fs.serializable;
}
}
return shadow(this, 'attachments', attachments);
},
get javaScript() {
var xref = this.xref;
var obj = this.catDict.get('Names');
var javaScript = [];
function appendIfJavaScriptDict(jsDict) {
var type = jsDict.get('S');
if (!isName(type, 'JavaScript')) {
return;
}
var js = jsDict.get('JS');
if (isStream(js)) {
js = bytesToString(js.getBytes());
} else if (!isString(js)) {
return;
}
javaScript.push(stringToPDFString(js));
}
if (obj && obj.has('JavaScript')) {
var nameTree = new NameTree(obj.getRaw('JavaScript'), xref);
var names = nameTree.getAll();
for (var name in names) {
// We don't really use the JavaScript right now. This code is
// defensive so we don't cause errors on document load.
var jsDict = names[name];
if (isDict(jsDict)) {
appendIfJavaScriptDict(jsDict);
}
}
}
// Append OpenAction actions to javaScript array
var openactionDict = this.catDict.get('OpenAction');
if (isDict(openactionDict, 'Action')) {
var actionType = openactionDict.get('S');
if (isName(actionType, 'Named')) {
// The named Print action is not a part of the PDF 1.7 specification,
// but is supported by many PDF readers/writers (including Adobe's).
var action = openactionDict.get('N');
if (isName(action, 'Print')) {
javaScript.push('print({});');
}
} else {
appendIfJavaScriptDict(openactionDict);
}
}
return shadow(this, 'javaScript', javaScript);
},
cleanup: function Catalog_cleanup() {
var promises = [];
this.fontCache.forEach(function (promise) {
promises.push(promise);
});
return Promise.all(promises).then(function (translatedFonts) {
for (var i = 0, ii = translatedFonts.length; i < ii; i++) {
var font = translatedFonts[i].dict;
delete font.translated;
}
this.fontCache.clear();
}.bind(this));
},
getPage: function Catalog_getPage(pageIndex) {
if (!(pageIndex in this.pagePromises)) {
this.pagePromises[pageIndex] = this.getPageDict(pageIndex).then(
function (a) {
var dict = a[0];
var ref = a[1];
return this.pageFactory.createPage(pageIndex, dict, ref,
this.fontCache);
}.bind(this)
);
}
return this.pagePromises[pageIndex];
},
getPageDict: function Catalog_getPageDict(pageIndex) {
var capability = createPromiseCapability();
var nodesToVisit = [this.catDict.getRaw('Pages')];
var currentPageIndex = 0;
var xref = this.xref;
var checkAllKids = false;
function next() {
while (nodesToVisit.length) {
var currentNode = nodesToVisit.pop();
if (isRef(currentNode)) {
xref.fetchAsync(currentNode).then(function (obj) {
if (isDict(obj, 'Page') || (isDict(obj) && !obj.has('Kids'))) {
if (pageIndex === currentPageIndex) {
capability.resolve([obj, currentNode]);
} else {
currentPageIndex++;
next();
}
return;
}
nodesToVisit.push(obj);
next();
}, capability.reject);
return;
}
// Must be a child page dictionary.
assert(
isDict(currentNode),
'page dictionary kid reference points to wrong type of object'
);
var count = currentNode.get('Count');
// If the current node doesn't have any children, avoid getting stuck
// in an empty node further down in the tree (see issue5644.pdf).
if (count === 0) {
checkAllKids = true;
}
// Skip nodes where the page can't be.
if (currentPageIndex + count <= pageIndex) {
currentPageIndex += count;
continue;
}
var kids = currentNode.get('Kids');
assert(isArray(kids), 'page dictionary kids object is not an array');
if (!checkAllKids && count === kids.length) {
// Nodes that don't have the page have been skipped and this is the
// bottom of the tree which means the page requested must be a
// descendant of this pages node. Ideally we would just resolve the
// promise with the page ref here, but there is the case where more
// pages nodes could link to single a page (see issue 3666 pdf). To
// handle this push it back on the queue so if it is a pages node it
// will be descended into.
nodesToVisit = [kids[pageIndex - currentPageIndex]];
currentPageIndex = pageIndex;
continue;
} else {
for (var last = kids.length - 1; last >= 0; last--) {
nodesToVisit.push(kids[last]);
}
}
}
capability.reject('Page index ' + pageIndex + ' not found.');
}
next();
return capability.promise;
},
getPageIndex: function Catalog_getPageIndex(pageRef) {
// The page tree nodes have the count of all the leaves below them. To get
// how many pages are before we just have to walk up the tree and keep
// adding the count of siblings to the left of the node.
var xref = this.xref;
function pagesBeforeRef(kidRef) {
var total = 0;
var parentRef;
return xref.fetchAsync(kidRef).then(function (node) {
if (isRefsEqual(kidRef, pageRef) && !isDict(node, 'Page') &&
!(isDict(node) && !node.has('Type') && node.has('Contents'))) {
throw new Error('The reference does not point to a /Page Dict.');
}
if (!node) {
return null;
}
assert(isDict(node), 'node must be a Dict.');
parentRef = node.getRaw('Parent');
return node.getAsync('Parent');
}).then(function (parent) {
if (!parent) {
return null;
}
assert(isDict(parent), 'parent must be a Dict.');
return parent.getAsync('Kids');
}).then(function (kids) {
if (!kids) {
return null;
}
var kidPromises = [];
var found = false;
for (var i = 0; i < kids.length; i++) {
var kid = kids[i];
assert(isRef(kid), 'kid must be a Ref.');
if (kid.num === kidRef.num) {
found = true;
break;
}
kidPromises.push(xref.fetchAsync(kid).then(function (kid) {
if (kid.has('Count')) {
var count = kid.get('Count');
total += count;
} else { // page leaf node
total++;
}
}));
}
if (!found) {
error('kid ref not found in parents kids');
}
return Promise.all(kidPromises).then(function () {
return [total, parentRef];
});
});
}
var total = 0;
function next(ref) {
return pagesBeforeRef(ref).then(function (args) {
if (!args) {
return total;
}
var count = args[0];
var parentRef = args[1];
total += count;
return next(parentRef);
});
}
return next(pageRef);
}
};
/**
* @typedef ParseDestDictionaryParameters
* @property {Dict} destDict - The dictionary containing the destination.
* @property {Object} resultObj - The object where the parsed destination
* properties will be placed.
* @property {string} docBaseUrl - (optional) The document base URL that is
* used when attempting to recover valid absolute URLs from relative ones.
*/
/**
* Helper function used to parse the contents of destination dictionaries.
* @param {ParseDestDictionaryParameters} params
*/
Catalog.parseDestDictionary = function Catalog_parseDestDictionary(params) {
// Lets URLs beginning with 'www.' default to using the 'http://' protocol.
function addDefaultProtocolToUrl(url) {
if (url.indexOf('www.') === 0) {
return ('http://' + url);
}
return url;
}
// According to ISO 32000-1:2008, section 12.6.4.7, URIs should be encoded
// in 7-bit ASCII. Some bad PDFs use UTF-8 encoding, see Bugzilla 1122280.
function tryConvertUrlEncoding(url) {
try {
return stringToUTF8String(url);
} catch (e) {
return url;
}
}
var destDict = params.destDict;
if (!isDict(destDict)) {
warn('Catalog_parseDestDictionary: "destDict" must be a dictionary.');
return;
}
var resultObj = params.resultObj;
if (typeof resultObj !== 'object') {
warn('Catalog_parseDestDictionary: "resultObj" must be an object.');
return;
}
var docBaseUrl = params.docBaseUrl || null;
var action = destDict.get('A'), url, dest;
if (isDict(action)) {
var linkType = action.get('S').name;
switch (linkType) {
case 'URI':
url = action.get('URI');
if (isName(url)) {
// Some bad PDFs do not put parentheses around relative URLs.
url = '/' + url.name;
} else if (isString(url)) {
url = addDefaultProtocolToUrl(url);
}
// TODO: pdf spec mentions urls can be relative to a Base
// entry in the dictionary.
break;
case 'GoTo':
dest = action.get('D');
break;
case 'Launch':
// We neither want, nor can, support arbitrary 'Launch' actions.
// However, in practice they are mostly used for linking to other PDF
// files, which we thus attempt to support (utilizing `docBaseUrl`).
/* falls through */
case 'GoToR':
var urlDict = action.get('F');
if (isDict(urlDict)) {
// We assume that we found a FileSpec dictionary
// and fetch the URL without checking any further.
url = urlDict.get('F') || null;
} else if (isString(urlDict)) {
url = urlDict;
}
// NOTE: the destination is relative to the *remote* document.
var remoteDest = action.get('D');
if (remoteDest) {
if (isName(remoteDest)) {
remoteDest = remoteDest.name;
}
if (isString(url)) {
var baseUrl = url.split('#')[0];
if (isString(remoteDest)) {
// In practice, a named destination may contain only a number.
// If that happens, use the '#nameddest=' form to avoid the link
// redirecting to a page, instead of the correct destination.
url = baseUrl + '#' +
(/^\d+$/.test(remoteDest) ? 'nameddest=' : '') + remoteDest;
} else if (isArray(remoteDest)) {
url = baseUrl + '#' + JSON.stringify(remoteDest);
}
}
}
// The 'NewWindow' property, equal to `LinkTarget.BLANK`.
var newWindow = action.get('NewWindow');
if (isBool(newWindow)) {
resultObj.newWindow = newWindow;
}
break;
case 'Named':
var namedAction = action.get('N');
if (isName(namedAction)) {
resultObj.action = namedAction.name;
}
break;
case 'JavaScript':
var jsAction = action.get('JS'), js;
if (isStream(jsAction)) {
js = bytesToString(jsAction.getBytes());
} else if (isString(jsAction)) {
js = jsAction;
}
if (js) {
// Attempt to recover valid URLs from 'JS' entries with certain
// white-listed formats, e.g.
// - window.open('http://example.com')
// - app.launchURL('http://example.com', true)
var URL_OPEN_METHODS = [
'app.launchURL',
'window.open'
];
var regex = new RegExp('^(?:' + URL_OPEN_METHODS.join('|') + ')' +
'\\((?:\'|\")(\\S+)(?:\'|\")(?:,|\\))');
var jsUrl = regex.exec(stringToPDFString(js), 'i');
if (jsUrl && jsUrl[1]) {
url = jsUrl[1];
break;
}
}
/* falls through */
default:
warn('Catalog_parseDestDictionary: Unrecognized link type "' +
linkType + '".');
break;
}
} else if (destDict.has('Dest')) { // Simple destination link.
dest = destDict.get('Dest');
}
if (isString(url)) {
url = tryConvertUrlEncoding(url);
var absoluteUrl = createValidAbsoluteUrl(url, docBaseUrl);
if (absoluteUrl) {
resultObj.url = absoluteUrl.href;
}
resultObj.unsafeUrl = url;
}
if (dest) {
if (isName(dest)) {
dest = dest.name;
}
if (isString(dest) || isArray(dest)) {
resultObj.dest = dest;
}
}
};
return Catalog;
})();
var XRef = (function XRefClosure() {
function XRef(stream, pdfManager) {
this.stream = stream;
this.pdfManager = pdfManager;
this.entries = [];
this.xrefstms = Object.create(null);
// prepare the XRef cache
this.cache = [];
this.stats = {
streamTypes: [],
fontTypes: []
};
}
XRef.prototype = {
setStartXRef: function XRef_setStartXRef(startXRef) {
// Store the starting positions of xref tables as we process them
// so we can recover from missing data errors
this.startXRefQueue = [startXRef];
},
parse: function XRef_parse(recoveryMode) {
var trailerDict;
if (!recoveryMode) {
trailerDict = this.readXRef();
} else {
warn('Indexing all PDF objects');
trailerDict = this.indexObjects();
}
trailerDict.assignXref(this);
this.trailer = trailerDict;
var encrypt = trailerDict.get('Encrypt');
if (isDict(encrypt)) {
var ids = trailerDict.get('ID');
var fileId = (ids && ids.length) ? ids[0] : '';
// The 'Encrypt' dictionary itself should not be encrypted, and by
// setting `suppressEncryption` we can prevent an infinite loop inside
// of `XRef_fetchUncompressed` if the dictionary contains indirect
// objects (fixes issue7665.pdf).
encrypt.suppressEncryption = true;
this.encrypt = new CipherTransformFactory(encrypt, fileId,
this.pdfManager.password);
}
// get the root dictionary (catalog) object
if (!(this.root = trailerDict.get('Root'))) {
error('Invalid root reference');
}
},
processXRefTable: function XRef_processXRefTable(parser) {
if (!('tableState' in this)) {
// Stores state of the table as we process it so we can resume
// from middle of table in case of missing data error
this.tableState = {
entryNum: 0,
streamPos: parser.lexer.stream.pos,
parserBuf1: parser.buf1,
parserBuf2: parser.buf2
};
}
var obj = this.readXRefTable(parser);
// Sanity check
if (!isCmd(obj, 'trailer')) {
error('Invalid XRef table: could not find trailer dictionary');
}
// Read trailer dictionary, e.g.
// trailer
// << /Size 22
// /Root 20R
// /Info 10R
// /ID [ <81b14aafa313db63dbd6f981e49f94f4> ]
// >>
// The parser goes through the entire stream << ... >> and provides
// a getter interface for the key-value table
var dict = parser.getObj();
// The pdflib PDF generator can generate a nested trailer dictionary
if (!isDict(dict) && dict.dict) {
dict = dict.dict;
}
if (!isDict(dict)) {
error('Invalid XRef table: could not parse trailer dictionary');
}
delete this.tableState;
return dict;
},
readXRefTable: function XRef_readXRefTable(parser) {
// Example of cross-reference table:
// xref
// 0 1 <-- subsection header (first obj #, obj count)
// 0000000000 65535 f <-- actual object (offset, generation #, f/n)
// 23 2 <-- subsection header ... and so on ...
// 0000025518 00002 n
// 0000025635 00000 n
// trailer
// ...
var stream = parser.lexer.stream;
var tableState = this.tableState;
stream.pos = tableState.streamPos;
parser.buf1 = tableState.parserBuf1;
parser.buf2 = tableState.parserBuf2;
// Outer loop is over subsection headers
var obj;
while (true) {
if (!('firstEntryNum' in tableState) || !('entryCount' in tableState)) {
if (isCmd(obj = parser.getObj(), 'trailer')) {
break;
}
tableState.firstEntryNum = obj;
tableState.entryCount = parser.getObj();
}
var first = tableState.firstEntryNum;
var count = tableState.entryCount;
if (!isInt(first) || !isInt(count)) {
error('Invalid XRef table: wrong types in subsection header');
}
// Inner loop is over objects themselves
for (var i = tableState.entryNum; i < count; i++) {
tableState.streamPos = stream.pos;
tableState.entryNum = i;
tableState.parserBuf1 = parser.buf1;
tableState.parserBuf2 = parser.buf2;
var entry = {};
entry.offset = parser.getObj();
entry.gen = parser.getObj();
var type = parser.getObj();
if (isCmd(type, 'f')) {
entry.free = true;
} else if (isCmd(type, 'n')) {
entry.uncompressed = true;
}
// Validate entry obj
if (!isInt(entry.offset) || !isInt(entry.gen) ||
!(entry.free || entry.uncompressed)) {
error('Invalid entry in XRef subsection: ' + first + ', ' + count);
}
// The first xref table entry, i.e. obj 0, should be free. Attempting
// to adjust an incorrect first obj # (fixes issue 3248 and 7229).
if (i === 0 && entry.free && first === 1) {
first = 0;
}
if (!this.entries[i + first]) {
this.entries[i + first] = entry;
}
}
tableState.entryNum = 0;
tableState.streamPos = stream.pos;
tableState.parserBuf1 = parser.buf1;
tableState.parserBuf2 = parser.buf2;
delete tableState.firstEntryNum;
delete tableState.entryCount;
}
// Sanity check: as per spec, first object must be free
if (this.entries[0] && !this.entries[0].free) {
error('Invalid XRef table: unexpected first object');
}
return obj;
},
processXRefStream: function XRef_processXRefStream(stream) {
if (!('streamState' in this)) {
// Stores state of the stream as we process it so we can resume
// from middle of stream in case of missing data error
var streamParameters = stream.dict;
var byteWidths = streamParameters.get('W');
var range = streamParameters.get('Index');
if (!range) {
range = [0, streamParameters.get('Size')];
}
this.streamState = {
entryRanges: range,
byteWidths: byteWidths,
entryNum: 0,
streamPos: stream.pos
};
}
this.readXRefStream(stream);
delete this.streamState;
return stream.dict;
},
readXRefStream: function XRef_readXRefStream(stream) {
var i, j;
var streamState = this.streamState;
stream.pos = streamState.streamPos;
var byteWidths = streamState.byteWidths;
var typeFieldWidth = byteWidths[0];
var offsetFieldWidth = byteWidths[1];
var generationFieldWidth = byteWidths[2];
var entryRanges = streamState.entryRanges;
while (entryRanges.length > 0) {
var first = entryRanges[0];
var n = entryRanges[1];
if (!isInt(first) || !isInt(n)) {
error('Invalid XRef range fields: ' + first + ', ' + n);
}
if (!isInt(typeFieldWidth) || !isInt(offsetFieldWidth) ||
!isInt(generationFieldWidth)) {
error('Invalid XRef entry fields length: ' + first + ', ' + n);
}
for (i = streamState.entryNum; i < n; ++i) {
streamState.entryNum = i;
streamState.streamPos = stream.pos;
var type = 0, offset = 0, generation = 0;
for (j = 0; j < typeFieldWidth; ++j) {
type = (type << 8) | stream.getByte();
}
// if type field is absent, its default value is 1
if (typeFieldWidth === 0) {
type = 1;
}
for (j = 0; j < offsetFieldWidth; ++j) {
offset = (offset << 8) | stream.getByte();
}
for (j = 0; j < generationFieldWidth; ++j) {
generation = (generation << 8) | stream.getByte();
}
var entry = {};
entry.offset = offset;
entry.gen = generation;
switch (type) {
case 0:
entry.free = true;
break;
case 1:
entry.uncompressed = true;
break;
case 2:
break;
default:
error('Invalid XRef entry type: ' + type);
}
if (!this.entries[first + i]) {
this.entries[first + i] = entry;
}
}
streamState.entryNum = 0;
streamState.streamPos = stream.pos;
entryRanges.splice(0, 2);
}
},
indexObjects: function XRef_indexObjects() {
// Simple scan through the PDF content to find objects,
// trailers and XRef streams.
var TAB = 0x9, LF = 0xA, CR = 0xD, SPACE = 0x20;
var PERCENT = 0x25, LT = 0x3C;
function readToken(data, offset) {
var token = '', ch = data[offset];
while (ch !== LF && ch !== CR && ch !== LT) {
if (++offset >= data.length) {
break;
}
token += String.fromCharCode(ch);
ch = data[offset];
}
return token;
}
function skipUntil(data, offset, what) {
var length = what.length, dataLength = data.length;
var skipped = 0;
// finding byte sequence
while (offset < dataLength) {
var i = 0;
while (i < length && data[offset + i] === what[i]) {
++i;
}
if (i >= length) {
break; // sequence found
}
offset++;
skipped++;
}
return skipped;
}
var objRegExp = /^(\d+)\s+(\d+)\s+obj\b/;
var trailerBytes = new Uint8Array([116, 114, 97, 105, 108, 101, 114]);
var startxrefBytes = new Uint8Array([115, 116, 97, 114, 116, 120, 114,
101, 102]);
var endobjBytes = new Uint8Array([101, 110, 100, 111, 98, 106]);
var xrefBytes = new Uint8Array([47, 88, 82, 101, 102]);
// Clear out any existing entries, since they may be bogus.
this.entries.length = 0;
var stream = this.stream;
stream.pos = 0;
var buffer = stream.getBytes();
var position = stream.start, length = buffer.length;
var trailers = [], xrefStms = [];
while (position < length) {
var ch = buffer[position];
if (ch === TAB || ch === LF || ch === CR || ch === SPACE) {
++position;
continue;
}
if (ch === PERCENT) { // %-comment
do {
++position;
if (position >= length) {
break;
}
ch = buffer[position];
} while (ch !== LF && ch !== CR);
continue;
}
var token = readToken(buffer, position);
var m;
if (token.indexOf('xref') === 0 &&
(token.length === 4 || /\s/.test(token[4]))) {
position += skipUntil(buffer, position, trailerBytes);
trailers.push(position);
position += skipUntil(buffer, position, startxrefBytes);
} else if ((m = objRegExp.exec(token))) {
if (typeof this.entries[m[1]] === 'undefined') {
this.entries[m[1]] = {
offset: position - stream.start,
gen: m[2] | 0,
uncompressed: true
};
}
var contentLength = skipUntil(buffer, position, endobjBytes) + 7;
var content = buffer.subarray(position, position + contentLength);
// checking XRef stream suspect
// (it shall have '/XRef' and next char is not a letter)
var xrefTagOffset = skipUntil(content, 0, xrefBytes);
if (xrefTagOffset < contentLength &&
content[xrefTagOffset + 5] < 64) {
xrefStms.push(position - stream.start);
this.xrefstms[position - stream.start] = 1; // Avoid recursion
}
position += contentLength;
} else if (token.indexOf('trailer') === 0 &&
(token.length === 7 || /\s/.test(token[7]))) {
trailers.push(position);
position += skipUntil(buffer, position, startxrefBytes);
} else {
position += token.length + 1;
}
}
// reading XRef streams
var i, ii;
for (i = 0, ii = xrefStms.length; i < ii; ++i) {
this.startXRefQueue.push(xrefStms[i]);
this.readXRef(/* recoveryMode */ true);
}
// finding main trailer
var dict;
for (i = 0, ii = trailers.length; i < ii; ++i) {
stream.pos = trailers[i];
var parser = new Parser(new Lexer(stream), /* allowStreams = */ true,
/* xref = */ this, /* recoveryMode = */ true);
var obj = parser.getObj();
if (!isCmd(obj, 'trailer')) {
continue;
}
// read the trailer dictionary
dict = parser.getObj();
if (!isDict(dict)) {
continue;
}
// taking the first one with 'ID'
if (dict.has('ID')) {
return dict;
}
}
// no tailer with 'ID', taking last one (if exists)
if (dict) {
return dict;
}
// nothing helps
// calling error() would reject worker with an UnknownErrorException.
throw new InvalidPDFException('Invalid PDF structure');
},
readXRef: function XRef_readXRef(recoveryMode) {
var stream = this.stream;
try {
while (this.startXRefQueue.length) {
var startXRef = this.startXRefQueue[0];
stream.pos = startXRef + stream.start;
var parser = new Parser(new Lexer(stream), true, this);
var obj = parser.getObj();
var dict;
// Get dictionary
if (isCmd(obj, 'xref')) {
// Parse end-of-file XRef
dict = this.processXRefTable(parser);
if (!this.topDict) {
this.topDict = dict;
}
// Recursively get other XRefs 'XRefStm', if any
obj = dict.get('XRefStm');
if (isInt(obj)) {
var pos = obj;
// ignore previously loaded xref streams
// (possible infinite recursion)
if (!(pos in this.xrefstms)) {
this.xrefstms[pos] = 1;
this.startXRefQueue.push(pos);
}
}
} else if (isInt(obj)) {
// Parse in-stream XRef
if (!isInt(parser.getObj()) ||
!isCmd(parser.getObj(), 'obj') ||
!isStream(obj = parser.getObj())) {
error('Invalid XRef stream');
}
dict = this.processXRefStream(obj);
if (!this.topDict) {
this.topDict = dict;
}
if (!dict) {
error('Failed to read XRef stream');
}
} else {
error('Invalid XRef stream header');
}
// Recursively get previous dictionary, if any
obj = dict.get('Prev');
if (isInt(obj)) {
this.startXRefQueue.push(obj);
} else if (isRef(obj)) {
// The spec says Prev must not be a reference, i.e. "/Prev NNN"
// This is a fallback for non-compliant PDFs, i.e. "/Prev NNN 0 R"
this.startXRefQueue.push(obj.num);
}
this.startXRefQueue.shift();
}
return this.topDict;
} catch (e) {
if (e instanceof MissingDataException) {
throw e;
}
info('(while reading XRef): ' + e);
}
if (recoveryMode) {
return;
}
throw new XRefParseException();
},
getEntry: function XRef_getEntry(i) {
var xrefEntry = this.entries[i];
if (xrefEntry && !xrefEntry.free && xrefEntry.offset) {
return xrefEntry;
}
return null;
},
fetchIfRef: function XRef_fetchIfRef(obj, suppressEncryption) {
if (!isRef(obj)) {
return obj;
}
return this.fetch(obj, suppressEncryption);
},
fetch: function XRef_fetch(ref, suppressEncryption) {
assert(isRef(ref), 'ref object is not a reference');
var num = ref.num;
if (num in this.cache) {
var cacheEntry = this.cache[num];
return cacheEntry;
}
var xrefEntry = this.getEntry(num);
// the referenced entry can be free
if (xrefEntry === null) {
return (this.cache[num] = null);
}
if (xrefEntry.uncompressed) {
xrefEntry = this.fetchUncompressed(ref, xrefEntry, suppressEncryption);
} else {
xrefEntry = this.fetchCompressed(xrefEntry, suppressEncryption);
}
if (isDict(xrefEntry)) {
xrefEntry.objId = ref.toString();
} else if (isStream(xrefEntry)) {
xrefEntry.dict.objId = ref.toString();
}
return xrefEntry;
},
fetchUncompressed: function XRef_fetchUncompressed(ref, xrefEntry,
suppressEncryption) {
var gen = ref.gen;
var num = ref.num;
if (xrefEntry.gen !== gen) {
error('inconsistent generation in XRef');
}
var stream = this.stream.makeSubStream(xrefEntry.offset +
this.stream.start);
var parser = new Parser(new Lexer(stream), true, this);
var obj1 = parser.getObj();
var obj2 = parser.getObj();
var obj3 = parser.getObj();
if (!isInt(obj1) || parseInt(obj1, 10) !== num ||
!isInt(obj2) || parseInt(obj2, 10) !== gen ||
!isCmd(obj3)) {
error('bad XRef entry');
}
if (!isCmd(obj3, 'obj')) {
// some bad PDFs use "obj1234" and really mean 1234
if (obj3.cmd.indexOf('obj') === 0) {
num = parseInt(obj3.cmd.substring(3), 10);
if (!isNaN(num)) {
return num;
}
}
error('bad XRef entry');
}
if (this.encrypt && !suppressEncryption) {
xrefEntry = parser.getObj(this.encrypt.createCipherTransform(num, gen));
} else {
xrefEntry = parser.getObj();
}
if (!isStream(xrefEntry)) {
this.cache[num] = xrefEntry;
}
return xrefEntry;
},
fetchCompressed: function XRef_fetchCompressed(xrefEntry,
suppressEncryption) {
var tableOffset = xrefEntry.offset;
var stream = this.fetch(new Ref(tableOffset, 0));
if (!isStream(stream)) {
error('bad ObjStm stream');
}
var first = stream.dict.get('First');
var n = stream.dict.get('N');
if (!isInt(first) || !isInt(n)) {
error('invalid first and n parameters for ObjStm stream');
}
var parser = new Parser(new Lexer(stream), false, this);
parser.allowStreams = true;
var i, entries = [], num, nums = [];
// read the object numbers to populate cache
for (i = 0; i < n; ++i) {
num = parser.getObj();
if (!isInt(num)) {
error('invalid object number in the ObjStm stream: ' + num);
}
nums.push(num);
var offset = parser.getObj();
if (!isInt(offset)) {
error('invalid object offset in the ObjStm stream: ' + offset);
}
}
// read stream objects for cache
for (i = 0; i < n; ++i) {
entries.push(parser.getObj());
// The ObjStm should not contain 'endobj'. If it's present, skip over it
// to support corrupt PDFs (fixes issue 5241, bug 898610, bug 1037816).
if (isCmd(parser.buf1, 'endobj')) {
parser.shift();
}
num = nums[i];
var entry = this.entries[num];
if (entry && entry.offset === tableOffset && entry.gen === i) {
this.cache[num] = entries[i];
}
}
xrefEntry = entries[xrefEntry.gen];
if (xrefEntry === undefined) {
error('bad XRef entry for compressed object');
}
return xrefEntry;
},
fetchIfRefAsync: function XRef_fetchIfRefAsync(obj, suppressEncryption) {
if (!isRef(obj)) {
return Promise.resolve(obj);
}
return this.fetchAsync(obj, suppressEncryption);
},
fetchAsync: function XRef_fetchAsync(ref, suppressEncryption) {
var streamManager = this.stream.manager;
var xref = this;
return new Promise(function tryFetch(resolve, reject) {
try {
resolve(xref.fetch(ref, suppressEncryption));
} catch (e) {
if (e instanceof MissingDataException) {
streamManager.requestRange(e.begin, e.end).then(function () {
tryFetch(resolve, reject);
}, reject);
return;
}
reject(e);
}
});
},
getCatalogObj: function XRef_getCatalogObj() {
return this.root;
}
};
return XRef;
})();
/**
* A NameTree/NumberTree is like a Dict but has some advantageous properties,
* see the specification (7.9.6 and 7.9.7) for additional details.
* TODO: implement all the Dict functions and make this more efficient.
*/
var NameOrNumberTree = (function NameOrNumberTreeClosure() {
function NameOrNumberTree(root, xref) {
throw new Error('Cannot initialize NameOrNumberTree.');
}
NameOrNumberTree.prototype = {
getAll: function NameOrNumberTree_getAll() {
var dict = Object.create(null);
if (!this.root) {
return dict;
}
var xref = this.xref;
// Reading Name/Number tree.
var processed = new RefSet();
processed.put(this.root);
var queue = [this.root];
while (queue.length > 0) {
var i, n;
var obj = xref.fetchIfRef(queue.shift());
if (!isDict(obj)) {
continue;
}
if (obj.has('Kids')) {
var kids = obj.get('Kids');
for (i = 0, n = kids.length; i < n; i++) {
var kid = kids[i];
assert(!processed.has(kid),
'Duplicate entry in "' + this._type + '" tree.');
queue.push(kid);
processed.put(kid);
}
continue;
}
var entries = obj.get(this._type);
if (isArray(entries)) {
for (i = 0, n = entries.length; i < n; i += 2) {
dict[xref.fetchIfRef(entries[i])] = xref.fetchIfRef(entries[i + 1]);
}
}
}
return dict;
},
get: function NameOrNumberTree_get(key) {
if (!this.root) {
return null;
}
var xref = this.xref;
var kidsOrEntries = xref.fetchIfRef(this.root);
var loopCount = 0;
var MAX_LEVELS = 10;
var l, r, m;
// Perform a binary search to quickly find the entry that
// contains the key we are looking for.
while (kidsOrEntries.has('Kids')) {
if (++loopCount > MAX_LEVELS) {
warn('Search depth limit reached for "' + this._type + '" tree.');
return null;
}
var kids = kidsOrEntries.get('Kids');
if (!isArray(kids)) {
return null;
}
l = 0;
r = kids.length - 1;
while (l <= r) {
m = (l + r) >> 1;
var kid = xref.fetchIfRef(kids[m]);
var limits = kid.get('Limits');
if (key < xref.fetchIfRef(limits[0])) {
r = m - 1;
} else if (key > xref.fetchIfRef(limits[1])) {
l = m + 1;
} else {
kidsOrEntries = xref.fetchIfRef(kids[m]);
break;
}
}
if (l > r) {
return null;
}
}
// If we get here, then we have found the right entry. Now go through the
// entries in the dictionary until we find the key we're looking for.
var entries = kidsOrEntries.get(this._type);
if (isArray(entries)) {
// Perform a binary search to reduce the lookup time.
l = 0;
r = entries.length - 2;
while (l <= r) {
// Check only even indices (0, 2, 4, ...) because the
// odd indices contain the actual data.
m = (l + r) & ~1;
var currentKey = xref.fetchIfRef(entries[m]);
if (key < currentKey) {
r = m - 2;
} else if (key > currentKey) {
l = m + 2;
} else {
return xref.fetchIfRef(entries[m + 1]);
}
}
}
return null;
}
};
return NameOrNumberTree;
})();
var NameTree = (function NameTreeClosure() {
function NameTree(root, xref) {
this.root = root;
this.xref = xref;
this._type = 'Names';
}
Util.inherit(NameTree, NameOrNumberTree, {});
return NameTree;
})();
var NumberTree = (function NumberTreeClosure() {
function NumberTree(root, xref) {
this.root = root;
this.xref = xref;
this._type = 'Nums';
}
Util.inherit(NumberTree, NameOrNumberTree, {});
return NumberTree;
})();
/**
* "A PDF file can refer to the contents of another file by using a File
* Specification (PDF 1.1)", see the spec (7.11) for more details.
* NOTE: Only embedded files are supported (as part of the attachments support)
* TODO: support the 'URL' file system (with caching if !/V), portable
* collections attributes and related files (/RF)
*/
var FileSpec = (function FileSpecClosure() {
function FileSpec(root, xref) {
if (!root || !isDict(root)) {
return;
}
this.xref = xref;
this.root = root;
if (root.has('FS')) {
this.fs = root.get('FS');
}
this.description = root.has('Desc') ?
stringToPDFString(root.get('Desc')) :
'';
if (root.has('RF')) {
warn('Related file specifications are not supported');
}
this.contentAvailable = true;
if (!root.has('EF')) {
this.contentAvailable = false;
warn('Non-embedded file specifications are not supported');
}
}
function pickPlatformItem(dict) {
// Look for the filename in this order:
// UF, F, Unix, Mac, DOS
if (dict.has('UF')) {
return dict.get('UF');
} else if (dict.has('F')) {
return dict.get('F');
} else if (dict.has('Unix')) {
return dict.get('Unix');
} else if (dict.has('Mac')) {
return dict.get('Mac');
} else if (dict.has('DOS')) {
return dict.get('DOS');
} else {
return null;
}
}
FileSpec.prototype = {
get filename() {
if (!this._filename && this.root) {
var filename = pickPlatformItem(this.root) || 'unnamed';
this._filename = stringToPDFString(filename).
replace(/\\\\/g, '\\').
replace(/\\\//g, '/').
replace(/\\/g, '/');
}
return this._filename;
},
get content() {
if (!this.contentAvailable) {
return null;
}
if (!this.contentRef && this.root) {
this.contentRef = pickPlatformItem(this.root.get('EF'));
}
var content = null;
if (this.contentRef) {
var xref = this.xref;
var fileObj = xref.fetchIfRef(this.contentRef);
if (fileObj && isStream(fileObj)) {
content = fileObj.getBytes();
} else {
warn('Embedded file specification points to non-existing/invalid ' +
'content');
}
} else {
warn('Embedded file specification does not have a content');
}
return content;
},
get serializable() {
return {
filename: this.filename,
content: this.content
};
}
};
return FileSpec;
})();
/**
* A helper for loading missing data in object graphs. It traverses the graph
* depth first and queues up any objects that have missing data. Once it has
* has traversed as many objects that are available it attempts to bundle the
* missing data requests and then resume from the nodes that weren't ready.
*
* NOTE: It provides protection from circular references by keeping track of
* of loaded references. However, you must be careful not to load any graphs
* that have references to the catalog or other pages since that will cause the
* entire PDF document object graph to be traversed.
*/
var ObjectLoader = (function() {
function mayHaveChildren(value) {
return isRef(value) || isDict(value) || isArray(value) || isStream(value);
}
function addChildren(node, nodesToVisit) {
var value;
if (isDict(node) || isStream(node)) {
var map;
if (isDict(node)) {
map = node.map;
} else {
map = node.dict.map;
}
for (var key in map) {
value = map[key];
if (mayHaveChildren(value)) {
nodesToVisit.push(value);
}
}
} else if (isArray(node)) {
for (var i = 0, ii = node.length; i < ii; i++) {
value = node[i];
if (mayHaveChildren(value)) {
nodesToVisit.push(value);
}
}
}
}
function ObjectLoader(obj, keys, xref) {
this.obj = obj;
this.keys = keys;
this.xref = xref;
this.refSet = null;
this.capability = null;
}
ObjectLoader.prototype = {
load: function ObjectLoader_load() {
var keys = this.keys;
this.capability = createPromiseCapability();
// Don't walk the graph if all the data is already loaded.
if (!(this.xref.stream instanceof ChunkedStream) ||
this.xref.stream.getMissingChunks().length === 0) {
this.capability.resolve();
return this.capability.promise;
}
this.refSet = new RefSet();
// Setup the initial nodes to visit.
var nodesToVisit = [];
for (var i = 0; i < keys.length; i++) {
nodesToVisit.push(this.obj[keys[i]]);
}
this._walk(nodesToVisit);
return this.capability.promise;
},
_walk: function ObjectLoader_walk(nodesToVisit) {
var nodesToRevisit = [];
var pendingRequests = [];
// DFS walk of the object graph.
while (nodesToVisit.length) {
var currentNode = nodesToVisit.pop();
// Only references or chunked streams can cause missing data exceptions.
if (isRef(currentNode)) {
// Skip nodes that have already been visited.
if (this.refSet.has(currentNode)) {
continue;
}
try {
var ref = currentNode;
this.refSet.put(ref);
currentNode = this.xref.fetch(currentNode);
} catch (e) {
if (!(e instanceof MissingDataException)) {
throw e;
}
nodesToRevisit.push(currentNode);
pendingRequests.push({ begin: e.begin, end: e.end });
}
}
if (currentNode && currentNode.getBaseStreams) {
var baseStreams = currentNode.getBaseStreams();
var foundMissingData = false;
for (var i = 0; i < baseStreams.length; i++) {
var stream = baseStreams[i];
if (stream.getMissingChunks && stream.getMissingChunks().length) {
foundMissingData = true;
pendingRequests.push({
begin: stream.start,
end: stream.end
});
}
}
if (foundMissingData) {
nodesToRevisit.push(currentNode);
}
}
addChildren(currentNode, nodesToVisit);
}
if (pendingRequests.length) {
this.xref.stream.manager.requestRanges(pendingRequests).then(
function pendingRequestCallback() {
nodesToVisit = nodesToRevisit;
for (var i = 0; i < nodesToRevisit.length; i++) {
var node = nodesToRevisit[i];
// Remove any reference nodes from the currrent refset so they
// aren't skipped when we revist them.
if (isRef(node)) {
this.refSet.remove(node);
}
}
this._walk(nodesToVisit);
}.bind(this), this.capability.reject);
return;
}
// Everything is loaded.
this.refSet = null;
this.capability.resolve();
}
};
return ObjectLoader;
})();
exports.Catalog = Catalog;
exports.ObjectLoader = ObjectLoader;
exports.XRef = XRef;
exports.FileSpec = FileSpec;
}));