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
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
|
/* Copyright (C) 2018-2022 Artifex Software, Inc.
All Rights Reserved.
This software is provided AS-IS with no warranty, either express or
implied.
This software is distributed under license and may not be copied,
modified or distributed except as expressly authorized under the terms
of the license contained in the file LICENSE in this distribution.
Refer to licensing information at http://www.artifex.com or contact
Artifex Software, Inc., 1305 Grant Avenue - Suite 200, Novato,
CA 94945, U.S.A., +1(415)492-9861, for further information.
*/
/* Top level PDF access routines */
#include "ghostpdf.h"
#include "pdf_types.h"
#include "pdf_dict.h"
#include "pdf_array.h"
#include "pdf_int.h"
#include "pdf_misc.h"
#include "pdf_stack.h"
#include "pdf_file.h"
#include "pdf_loop_detect.h"
#include "pdf_trans.h"
#include "pdf_font_types.h"
#include "pdf_gstate.h"
#include "stream.h"
#include "strmio.h"
#include "pdf_colour.h"
#include "pdf_font.h"
#include "pdf_text.h"
#include "pdf_page.h"
#include "pdf_check.h"
#include "pdf_optcontent.h"
#include "pdf_sec.h"
#include "pdf_doc.h"
#include "pdf_repair.h"
#include "pdf_xref.h"
#include "pdf_device.h"
#include "gsstate.h" /* For gs_gstate */
#include "gsicc_manage.h" /* For gsicc_init_iccmanager() */
#if PDFI_LEAK_CHECK
#include "gsmchunk.h"
#endif
extern const char gp_file_name_list_separator;
/*
* Convenience routine to check if a given string exists in a dictionary
* verify its contents and print it in a particular fashion to stdout. This
* is used to display information about the PDF in response to -dPDFINFO
*/
static int dump_info_string(pdf_context *ctx, pdf_dict *source_dict, const char *Key)
{
int code;
pdf_string *s = NULL;
char *Cstr;
code = pdfi_dict_knownget_type(ctx, source_dict, Key, PDF_STRING, (pdf_obj **)&s);
if (code > 0) {
Cstr = (char *)gs_alloc_bytes(ctx->memory, s->length + 1, "Working memory for string dumping");
if (Cstr) {
memcpy(Cstr, s->data, s->length);
Cstr[s->length] = 0x00;
dmprintf2(ctx->memory, "%s: %s\n", Key, Cstr);
gs_free_object(ctx->memory, Cstr, "Working memory for string dumping");
}
code = 0;
}
pdfi_countdown(s);
return code;
}
static int pdfi_output_metadata(pdf_context *ctx)
{
int code = 0;
if (ctx->num_pages > 1)
dmprintf2(ctx->memory, "\n %s has %"PRIi64" pages\n\n", ctx->filename, ctx->num_pages);
else
dmprintf2(ctx->memory, "\n %s has %"PRIi64" page.\n\n", ctx->filename, ctx->num_pages);
if (ctx->Info != NULL) {
pdf_name *n = NULL;
char *Cstr;
code = dump_info_string(ctx, ctx->Info, "Title");
if (code < 0) {
if (ctx->args.pdfstoponerror)
return code;
}
code = dump_info_string(ctx, ctx->Info, "Author");
if (code < 0) {
if (ctx->args.pdfstoponerror)
return code;
}
code = dump_info_string(ctx, ctx->Info, "Subject");
if (code < 0) {
if (ctx->args.pdfstoponerror)
return code;
}
code = dump_info_string(ctx, ctx->Info, "Keywords");
if (code < 0) {
if (ctx->args.pdfstoponerror)
return code;
}
code = dump_info_string(ctx, ctx->Info, "Creator");
if (code < 0) {
if (ctx->args.pdfstoponerror)
return code;
}
code = dump_info_string(ctx, ctx->Info, "Producer");
if (code < 0) {
if (ctx->args.pdfstoponerror)
return code;
}
code = dump_info_string(ctx, ctx->Info, "CreationDate");
if (code < 0) {
if (ctx->args.pdfstoponerror)
return code;
}
code = dump_info_string(ctx, ctx->Info, "ModDate");
if (code < 0) {
if (ctx->args.pdfstoponerror)
return code;
}
code = pdfi_dict_knownget_type(ctx, ctx->Info, "Trapped", PDF_NAME, (pdf_obj **)&n);
if (code > 0) {
Cstr = (char *)gs_alloc_bytes(ctx->memory, n->length + 1, "Working memory for string dumping");
if (Cstr) {
memcpy(Cstr, n->data, n->length);
Cstr[n->length] = 0x00;
dmprintf1(ctx->memory, "Trapped: %s\n\n", Cstr);
gs_free_object(ctx->memory, Cstr, "Working memory for string dumping");
}
code = 0;
}
pdfi_countdown(n);
n = NULL;
}
return code;
}
/*
* Convenience routine to check if a given *Box exists in a page dictionary
* verify its contents and print it in a particular fashion to stdout. This
* is used to display information about the PDF in response to -dPDFINFO
*/
static int pdfi_dump_box(pdf_context *ctx, pdf_dict *page_dict, const char *Key)
{
int code, i;
pdf_array *a = NULL;
double f;
code = pdfi_dict_knownget_type(ctx, page_dict, Key, PDF_ARRAY, (pdf_obj **)&a);
if (code > 0) {
if (pdfi_array_size(a) != 4) {
dmprintf1(ctx->memory, "Error - %s does not contain 4 values.\n", Key);
code = gs_note_error(gs_error_rangecheck);
} else {
dmprintf1(ctx->memory, " %s: [", Key);
for (i = 0; i < pdfi_array_size(a); i++) {
code = pdfi_array_get_number(ctx, a, (uint64_t)i, &f);
if (i != 0)
dmprintf(ctx->memory, " ");
if (code == 0) {
if (a->values[i]->type == PDF_INT)
dmprintf1(ctx->memory, "%"PRIi64"", ((pdf_num *)a->values[i])->value.i);
else
dmprintf1(ctx->memory, "%f", ((pdf_num *)a->values[i])->value.d);
} else {
dmprintf(ctx->memory, "NAN");
}
}
dmprintf(ctx->memory, "]");
}
}
pdfi_countdown(a);
return code;
}
/*
* This routine along with pdfi_output_metadtaa above, dumps certain kinds
* of metadata from the PDF file, and from each page in the PDF file. It is
* intended to duplicate the pdf_info.ps functionality of the PostScript-based
* PDF interpreter in Ghostscript.
*
* It is not yet complete, we don't allow an option for dumping media sizes
* we always emit them, and the switches -dDumpFontsNeeded, -dDumpXML,
* -dDumpFontsUsed and -dShowEmbeddedFonts are not implemented at all yet.
*/
static int pdfi_output_page_info(pdf_context *ctx, uint64_t page_num)
{
int code;
bool known = false;
double f;
pdf_dict *page_dict = NULL;
code = pdfi_page_get_dict(ctx, page_num, &page_dict);
if (code < 0)
return code;
dmprintf1(ctx->memory, "Page %"PRIi64"", page_num + 1);
code = pdfi_dict_knownget_number(ctx, page_dict, "UserUnit", &f);
if (code > 0)
dmprintf1(ctx->memory, " UserUnit: %f ", f);
if (code < 0) {
pdfi_countdown(page_dict);
return code;
}
code = pdfi_dump_box(ctx, page_dict, "MediaBox");
if (code < 0) {
if (code != gs_error_undefined && ctx->args.pdfstoponerror) {
pdfi_countdown(page_dict);
return code;
}
}
code = pdfi_dump_box(ctx, page_dict, "CropBox");
if (code < 0) {
if (code != gs_error_undefined && ctx->args.pdfstoponerror) {
pdfi_countdown(page_dict);
return code;
}
}
code = pdfi_dump_box(ctx, page_dict, "BleedBox");
if (code < 0) {
if (code != gs_error_undefined && ctx->args.pdfstoponerror) {
pdfi_countdown(page_dict);
return code;
}
}
code = pdfi_dump_box(ctx, page_dict, "TrimBox");
if (code < 0) {
if (code != gs_error_undefined && ctx->args.pdfstoponerror) {
pdfi_countdown(page_dict);
return code;
}
}
code = pdfi_dump_box(ctx, page_dict, "ArtBox");
if (code < 0) {
if (code != gs_error_undefined && ctx->args.pdfstoponerror) {
pdfi_countdown(page_dict);
return code;
}
}
code = pdfi_dict_knownget_number(ctx, page_dict, "Rotate", &f);
if (code > 0)
dmprintf1(ctx->memory, " Rotate = %d ", (int)f);
if (code < 0) {
pdfi_countdown(page_dict);
return code;
}
code = pdfi_check_page(ctx, page_dict, false);
if (code < 0) {
if (ctx->args.pdfstoponerror)
return code;
} else {
if (ctx->page.has_transparency)
dmprintf(ctx->memory, " Page uses transparency features");
}
code = pdfi_dict_known(ctx, page_dict, "Annots", &known);
if (code < 0) {
if (code != gs_error_undefined && ctx->args.pdfstoponerror)
return code;
} else {
if (known == true)
dmprintf(ctx->memory, " Page contains Annotations");
}
dmprintf(ctx->memory, "\n\n");
pdfi_countdown(page_dict);
return 0;
}
/* Error and warning string tables. There should be a string for each error and warning
* defined in the error (pdf_error_e) and warning (pdf_warning_e) enumerators. Having
* more strings is harmless, having too few may cause crashes. These need to be kept in sync.
*
* The Ghostscript graphics library errors should be kept up to date, but this is less critical
* if the error code is greater than the last error we know about we just print a generic
* 'unknown' message.
*/
const char *pdf_error_strings[] = {
#define PARAM(A,B) B
#include "pdf_errors.h"
"" /* last error, should not be used */
};
const char *pdf_warning_strings[] = {
#define PARAM(A,B) B
#include "pdf_warnings.h"
"" /* Last warning should not be used */
};
const char *gs_error_strings[] = {
"no error",
"unknownerror",
"dictfull",
"dictstackoverflow",
"dictstackunderflow",
"execstackoverflow",
"interrupt",
"invalidaccess",
"invalidexit",
"invalidfileaccess",
"invalidfont",
"invalidrestore",
"ioerror",
"limitcheck",
"nocurrentpoint",
"rangecheck",
"stackoverflow",
"stackunderflow",
"syntaxerror",
"timeout",
"typecheck",
"undefined",
"undefinedfilename",
"undefinedresult",
"unmatchedmark",
"VMerror",
"configurationerror",
"undefinedresource",
"unregistered",
"invalidcontext",
"invalidid",
};
const char *gs_internal_error_strings[] = {
"error hit",
"fatal error",
"quit",
"interpreter exit",
"remap color",
"exec stack underflow",
"VMreclaim",
"Need input",
"No defined error",
"No defined error (2)",
"need file",
"error info",
"handled",
"circular reference"
};
#define LASTNORMALGSERROR gs_error_invalidid * -1
#define FIRSTINTERNALERROR gs_error_hit_detected * -1
#define LASTGSERROR gs_error_circular_reference * -1
void pdfi_verbose_error(pdf_context *ctx, int gs_error, const char *gs_lib_function, int pdfi_error, const char *pdfi_function_name, const char *extra_info)
{
char fallback[] = "unknown graphics library error";
if (ctx->args.verbose_errors && !ctx->args.QUIET) {
if (gs_error != 0) {
char *error_string;
unsigned int code = gs_error * -1;
if (code > LASTGSERROR)
error_string = fallback;
else {
if (code > LASTNORMALGSERROR) {
if (code < FIRSTINTERNALERROR)
error_string = fallback;
else
error_string = (char *)gs_internal_error_strings[code - FIRSTINTERNALERROR];
} else
error_string = (char *)gs_error_strings[code];
}
errprintf(ctx->memory, "Graphics library error %d (%s) in function '%s'", gs_error, error_string, pdfi_function_name);
if (gs_lib_function != NULL)
errprintf(ctx->memory, " from lib routine '%s'.\n", gs_lib_function);
else
errprintf(ctx->memory, ".\n");
if (pdfi_error != 0)
errprintf(ctx->memory, "\tSetting pdfi error %d - %s.\n", pdfi_error, pdf_error_strings[pdfi_error]);
if (extra_info != NULL)
errprintf(ctx->memory, "\t%s\n", extra_info);
} else {
if (pdfi_error != 0) {
errprintf(ctx->memory, "Function '%s' set pdfi error %d - %s.\n", pdfi_function_name, pdfi_error, pdf_error_strings[pdfi_error]);
if (extra_info != NULL)
errprintf(ctx->memory, "\t%s\n", extra_info);
} else {
if (extra_info != NULL)
errprintf(ctx->memory, "%s\n", extra_info);
}
}
}
}
void pdfi_verbose_warning(pdf_context *ctx, int gs_error, const char *gs_lib_function, int pdfi_warning, const char *pdfi_function_name, const char *extra_info)
{
char fallback[] = "unknown graphics library error";
if (ctx->args.verbose_warnings && !ctx->args.QUIET) {
if (gs_error != 0) {
char *error_string;
unsigned int code = gs_error * -1;
if (code > LASTGSERROR)
error_string = fallback;
else {
if (code > LASTNORMALGSERROR) {
if (code < FIRSTINTERNALERROR)
error_string = fallback;
else
error_string = (char *)gs_internal_error_strings[code - FIRSTINTERNALERROR];
} else
error_string = (char *)gs_error_strings[code];
}
outprintf(ctx->memory, "Graphics library error %d (%s) in function '%s'", gs_error, error_string, pdfi_function_name);
if (gs_lib_function != NULL)
outprintf(ctx->memory, " from lib routine '%s'.\n", gs_lib_function);
else
outprintf(ctx->memory, ".\n");
if (pdfi_warning != 0)
outprintf(ctx->memory, "\tsetting pdfi warning %d - %s.\n", pdfi_warning, pdf_warning_strings[pdfi_warning]);
if (extra_info != NULL)
outprintf(ctx->memory, "\t%s\n", extra_info);
} else {
if (pdfi_warning != 0) {
outprintf(ctx->memory, "Function '%s' set pdfi warning %d - %s.\n", pdfi_function_name, pdfi_warning, pdf_warning_strings[pdfi_warning]);
if (extra_info != NULL)
errprintf(ctx->memory, "\t%s\n", extra_info);
} else {
if (extra_info != NULL)
errprintf(ctx->memory, "\t%s\n", extra_info);
}
}
}
}
void pdfi_set_error_var(pdf_context *ctx, int gs_error, const char *gs_lib_function, pdf_error pdfi_error, const char *pdfi_function_name, const char *fmt, ...)
{
if (pdfi_error != 0)
ctx->pdf_errors[pdfi_error / (sizeof(char) * 8)] |= 1 << pdfi_error % (sizeof(char) * 8);
if (ctx->args.verbose_errors) {
char extra_info[gp_file_name_sizeof];
va_list args;
va_start(args, fmt);
(void)vsnprintf(extra_info, sizeof(extra_info), fmt, args);
va_end(args);
pdfi_verbose_error(ctx, gs_error, gs_lib_function, pdfi_error, pdfi_function_name, extra_info);
}
}
void pdfi_set_warning_var(pdf_context *ctx, int gs_error, const char *gs_lib_function, pdf_warning pdfi_warning, const char *pdfi_function_name, const char *fmt, ...)
{
ctx->pdf_warnings[pdfi_warning / (sizeof(char) * 8)] |= 1 << pdfi_warning % (sizeof(char) * 8);
if (ctx->args.verbose_warnings) {
char extra_info[gp_file_name_sizeof];
va_list args;
va_start(args, fmt);
(void)vsnprintf(extra_info, sizeof(extra_info), fmt, args);
va_end(args);
pdfi_verbose_warning(ctx, gs_error, gs_lib_function, pdfi_warning, pdfi_function_name, extra_info);
}
}
void pdfi_log_info(pdf_context *ctx, const char *pdfi_function, const char *info)
{
#ifdef DEBUG
if (!ctx->args.QUIET)
outprintf(ctx->memory, "%s", info);
#endif
}
void
pdfi_report_errors(pdf_context *ctx)
{
int code, i, j;
bool warnings_exist = false, errors_exist = false;
if (ctx->args.QUIET)
return;
for (i = 0; i < PDF_ERROR_BYTE_SIZE; i++) {
if (ctx->pdf_errors[i] != 0)
errors_exist = true;
}
for (i = 0; i < PDF_WARNING_BYTE_SIZE; i++) {
if (ctx->pdf_warnings[i] != 0)
warnings_exist = true;
}
if (!errors_exist && !warnings_exist)
return;
if (errors_exist)
{
dmprintf(ctx->memory, "\nThe following errors were encountered at least once while processing this file:\n");
for (i = 0; i < PDF_ERROR_BYTE_SIZE; i++) {
if (ctx->pdf_errors[i] != 0) {
for (j=0;j < sizeof(char) * 8; j++) {
if (ctx->pdf_errors[i] & 1 << j) {
int error_num = (i * sizeof(char) * 8) + j;
errprintf(ctx->memory, "\t%s\n", pdf_error_strings[error_num]);
}
}
}
}
}
if (warnings_exist)
{
dmprintf(ctx->memory, "\nThe following warnings were encountered at least once while processing this file:\n");
for (i = 0; i < PDF_WARNING_BYTE_SIZE; i++) {
if (ctx->pdf_warnings[i] != 0) {
for (j=0;j < sizeof(char) * 8; j++) {
if (ctx->pdf_warnings[i] & 1 << j) {
int warning_num = (i * sizeof(char) * 8) + j;
outprintf(ctx->memory, "\t%s\n", pdf_warning_strings[warning_num]);
}
}
}
}
}
dmprintf(ctx->memory, "\n **** This file had errors that were repaired or ignored.\n");
if (ctx->Info) {
pdf_string *s = NULL;
code = pdfi_dict_knownget_type(ctx, ctx->Info, "Producer", PDF_STRING, (pdf_obj **)&s);
if (code > 0) {
char *cs;
cs = (char *)gs_alloc_bytes(ctx->memory, s->length + 1, "temporary string for error report");
memcpy(cs, s->data, s->length);
cs[s->length] = 0x00;
dmprintf1(ctx->memory, " **** The file was produced by: \n **** >>>> %s <<<<\n", cs);
gs_free_object(ctx->memory, cs, "temporary string for error report");
}
pdfi_countdown(s);
}
dmprintf(ctx->memory, " **** Please notify the author of the software that produced this\n");
dmprintf(ctx->memory, " **** file that it does not conform to Adobe's published PDF\n");
dmprintf(ctx->memory, " **** specification.\n\n");
}
/* Name table
* I've been trying to avoid this for as long as possible, but it seems it cannot
* be evaded. We need functions to get an index for a given string (which will
* add the string to the table if its not present) and to cleear up the table
* on finishing a PDF file.
*/
int pdfi_get_name_index(pdf_context *ctx, char *name, int len, unsigned int *returned)
{
pdfi_name_entry_t *e = NULL, *last_entry = NULL, *new_entry = NULL;
int index = 0;
if (ctx->name_table == NULL) {
e = NULL;
} else {
e = ctx->name_table;
}
while(e != NULL) {
if (e->len == len) {
if (memcmp(e->name, name, e->len) == 0) {
*returned = e->index;
return 0;
}
}
last_entry = e;
index = e->index;
e = e->next;
}
new_entry = (pdfi_name_entry_t *)gs_alloc_bytes(ctx->memory, sizeof(pdfi_name_entry_t), "Alloc name table entry");
if (new_entry == NULL)
return_error(gs_error_VMerror);
memset(new_entry, 0x00, sizeof(pdfi_name_entry_t));
new_entry->name = (char *)gs_alloc_bytes(ctx->memory, len+1, "Alloc name table name");
if (new_entry->name == NULL) {
gs_free_object(ctx->memory, new_entry, "Failed to allocate name entry");
return_error(gs_error_VMerror);
}
memset(new_entry->name, 0x00, len+1);
memcpy(new_entry->name, name, len);
new_entry->len = len;
new_entry->index = ++index;
if (last_entry)
last_entry->next = new_entry;
else
ctx->name_table = new_entry;
*returned = new_entry->index;
return 0;
}
static int pdfi_free_name_table(pdf_context *ctx)
{
if (ctx->name_table) {
pdfi_name_entry_t *next = NULL, *e = (pdfi_name_entry_t *)ctx->name_table;
while (e != NULL) {
next = (pdfi_name_entry_t *)e->next;
gs_free_object(ctx->memory, e->name, "free name table entries");
gs_free_object(ctx->memory, e, "free name table entries");
e = next;
}
}
ctx->name_table = NULL;
return 0;
}
int pdfi_name_from_index(pdf_context *ctx, int index, unsigned char **name, unsigned int *len)
{
pdfi_name_entry_t *e = (pdfi_name_entry_t *)ctx->name_table;
while (e != NULL) {
if (e->index == index) {
*name = (unsigned char *)e->name;
*len = e->len;
return 0;
}
e = e->next;
}
return_error(gs_error_undefined);
}
int pdfi_separation_name_from_index(gs_gstate *pgs, gs_separation_name index, unsigned char **name, unsigned int *len)
{
pdfi_int_gstate *igs = (pdfi_int_gstate *)pgs->client_data;
pdf_context *ctx = NULL;
pdfi_name_entry_t *e = NULL;
if (igs == NULL)
return_error(gs_error_undefined);
ctx = igs->ctx;
if (ctx == NULL)
return_error(gs_error_undefined);
e = (pdfi_name_entry_t *)ctx->name_table;
while (e != NULL) {
if (e->index == index) {
*name = (unsigned char *)e->name;
*len = e->len;
return 0;
}
e = e->next;
}
return_error(gs_error_undefined);
}
/* These functions are used by the 'PL' implementation, eventually we will */
/* need to have custom PostScript operators to process the file or at */
/* (least pages from it). */
int pdfi_close_pdf_file(pdf_context *ctx)
{
if (ctx->main_stream) {
if (ctx->main_stream->s) {
sfclose(ctx->main_stream->s);
}
gs_free_object(ctx->memory, ctx->main_stream, "Closing main PDF file");
ctx->main_stream = NULL;
}
ctx->main_stream_length = 0;
if (ctx->filename) {
gs_free_object(ctx->memory, ctx->filename, "pdfi_close_pdf_file, free copy of filename");
ctx->filename = NULL;
}
pdfi_clear_context(ctx);
return 0;
}
static int pdfi_process(pdf_context *ctx)
{
int code = 0, i;
/* Loop over each page and either render it or output the
* required information.
*/
for (i=0;i < ctx->num_pages;i++) {
if (ctx->args.first_page != 0) {
if (i < ctx->args.first_page - 1)
continue;
}
if (ctx->args.last_page != 0) {
if (i > ctx->args.last_page - 1)
break;;
}
if (ctx->args.pdfinfo)
code = pdfi_output_page_info(ctx, i);
else
code = pdfi_page_render(ctx, i, true);
if (code < 0 && ctx->args.pdfstoponerror)
goto exit;
code = 0;
}
exit:
pdfi_report_errors(ctx);
return code;
}
/* This works by reading each embedded file referenced by the collection. If it
* has a MIME type indicating it's a PDF file, or somewhere in the first 2KB it
* has the PDF header (%PDF-) then we treat it as a PDF file. We read the contents
* of the refrenced stream and write them to disk in a scratch file.
*
* We then process each scratch file in turn. Note that we actually return an
* array of strings; the first string is the temporary filename, the second is
* the entry from the names tree. Since this can be in UTF16-BE format, it can
* contain embedded single byte NULL characters, so we can't use a regular C
* string. Instead we use a triple byte NULL termination.
*
* It ought to be possible to do all the processing without creating scratch files, by saving the
* current file state, and opening a new 'file' on the stream in the original PDF
* file. But I couldn't immediately get that to work.
* So this is a FIXME future enhancement.
*/
int pdfi_prep_collection(pdf_context *ctx, uint64_t *TotalFiles, char ***names_array)
{
int code = 0, i, NumEmbeddedFiles = 0;
pdf_obj *Names = NULL, *EmbeddedFiles = NULL;
pdf_array *FileNames = NULL;
pdf_obj *EF = NULL, *F = NULL;
char **working_array = NULL;
if (pdfi_dict_knownget_type(ctx, ctx->Root, "Names", PDF_DICT, &Names)) {
if(pdfi_dict_knownget_type(ctx, (pdf_dict *)Names, "EmbeddedFiles", PDF_DICT, &EmbeddedFiles)) {
if (pdfi_dict_knownget_type(ctx, (pdf_dict *)EmbeddedFiles, "Names", PDF_ARRAY, (pdf_obj **)&FileNames)) {
int ix = 0, index = 0;
gp_file *scratch_file = NULL;
char scratch_name[gp_file_name_sizeof];
NumEmbeddedFiles = pdfi_array_size(FileNames) / 2;
working_array = (char **)gs_alloc_bytes(ctx->memory, NumEmbeddedFiles * 2 * sizeof(char *), "Collection file working names array");
if (working_array == NULL) {
code = gs_note_error(gs_error_VMerror);
goto exit;
}
memset(working_array, 0x00, NumEmbeddedFiles * 2 * sizeof(char *));
for (ix = 0;ix < NumEmbeddedFiles;ix++) {
pdf_obj *File = NULL;
pdf_obj *Subtype = NULL;
code = pdfi_array_get(ctx, FileNames, (ix * 2) + 1, &File);
if (code < 0)
goto exit;
if (File->type == PDF_DICT) {
if (pdfi_dict_knownget_type(ctx, (pdf_dict *)File, "EF", PDF_DICT, &EF)) {
if (pdfi_dict_knownget_type(ctx, (pdf_dict *)EF, "F", PDF_STREAM, &F)) {
pdf_dict *stream_dict = NULL;
pdf_c_stream *s = NULL;
/* pdfi_dict_from_object does not increment the reference count of the stream dictionary
* so we do not need to count it down later.
*/
code = pdfi_dict_from_obj(ctx, F, &stream_dict);
if (code >= 0) {
if (!pdfi_dict_knownget_type(ctx, stream_dict, "Subtype", PDF_NAME, &Subtype)) {
/* No Subtype, (or not a name) we can't check the Mime type, so try to read the first 2Kb
* and look for a %PDF- in that. If not present, assume its not a PDF
*/
code = pdfi_seek(ctx, ctx->main_stream, pdfi_stream_offset(ctx, (pdf_stream *)F), SEEK_SET);
if (code >= 0) {
code = pdfi_filter(ctx, (pdf_stream *)F, ctx->main_stream, &s, false);
if (code >= 0) {
char Buffer[2048];
int bytes;
bytes = pdfi_read_bytes(ctx, (byte *)Buffer, 1, 2048, s);
pdfi_close_file(ctx, s);
s = NULL;
/* Assertion; the smallest real PDF file is at least 400 bytes */
if (bytes >= 400) {
if (strstr(Buffer, "%PDF-") == NULL)
code = -1;
} else
code = -1;
}
}
} else {
if (!pdfi_name_is((const pdf_name *)Subtype, "application/pdf"))
code = -1;
}
if (code >= 0) {
/* Appears to be a PDF file. Create a scratch file to hold it, and then
* read the file from the PDF, and write it to the scratch file. Record
* the scratch filename in the working_array for later processing.
*/
scratch_file = gp_open_scratch_file(ctx->memory, "gpdf-collection-", scratch_name, "wb");
if (scratch_file != NULL) {
code = pdfi_seek(ctx, ctx->main_stream, pdfi_stream_offset(ctx, (pdf_stream *)F), SEEK_SET);
if (code >= 0) {
double L;
pdf_c_stream *SubFile_stream = NULL;
/* Start by setting up the file to be read. Apply a SubFileDecode so that, if the input stream
* is not compressed we will stop reading when we get to the end of the stream.
*/
if (pdfi_dict_knownget_number(ctx, stream_dict, "Length", &L) > 0) {
code = pdfi_apply_SubFileDecode_filter(ctx, (int)L, NULL, ctx->main_stream, &SubFile_stream, false);
if (code >= 0)
code = pdfi_filter(ctx, (pdf_stream *)F, SubFile_stream, &s, false);
} else
code = pdfi_filter(ctx, (pdf_stream *)F, ctx->main_stream, &s, false);
if (code >= 0) {
char Buffer[2048];
int bytes;
pdf_string *Name = NULL;
/* Read the stream contents and write them to the scratch file */
do {
bytes = pdfi_read_bytes(ctx, (byte *)Buffer, 1, 2048, s);
(void)gp_fwrite(Buffer, 1, bytes, scratch_file);
} while (bytes > 0);
/* Create an entry for the Description in the names array */
code = pdfi_array_get(ctx, FileNames, ix * 2, (pdf_obj **)&Name);
if (code >= 0) {
if (Name->type == PDF_STRING) {
working_array[(index * 2) + 1] = (char *)gs_alloc_bytes(ctx->memory, Name->length + 3, "Collection file names array entry");
if (working_array[(index * 2) + 1] != NULL) {
memset(working_array[(index * 2) + 1], 0x00, Name->length + 3);
memcpy(working_array[(index * 2) + 1], Name->data, Name->length);
}
}
pdfi_countdown(Name);
Name = NULL;
}
/* And now the scratch file name */
working_array[index * 2] = (char *)gs_alloc_bytes(ctx->memory, strlen(scratch_name) + 3, "Collection file names array entry");
if (working_array[index * 2] != NULL) {
memset(working_array[index * 2], 0x00, strlen(scratch_name) + 3);
strcpy(working_array[index * 2], scratch_name);
}
index++;
(*TotalFiles)++;
pdfi_close_file(ctx, s);
s = NULL;
}
if (SubFile_stream != NULL)
pdfi_close_file(ctx, SubFile_stream);
SubFile_stream = NULL;
}
gp_fclose(scratch_file);
} else
dmprintf(ctx->memory, "\n **** Warning: Failed to open a scratch file.\n");
}
}
}
}
}
pdfi_countdown(Subtype);
Subtype = NULL;
pdfi_countdown(F);
F = NULL;
pdfi_countdown(EF);
EF = NULL;
pdfi_countdown(File);
File = NULL;
}
} else {
dmprintf(ctx->memory, "\n **** Warning: Failed to read EmbeededFiles Names tree.\n");
}
} else {
dmprintf(ctx->memory, "\n **** Warning: Failed to read EmbeddedFiles.\n");
}
} else {
dmprintf(ctx->memory, "\n **** Warning: Failed to find Names tree.\n");
}
code = 0;
exit:
if (code >= 0) {
uint64_t ix = 0;
(*names_array) = (char **)gs_alloc_bytes(ctx->memory, *TotalFiles * 2 * sizeof(char *), "Collection file namesarray");
for (i = 0; i < NumEmbeddedFiles;i++) {
if (working_array[i * 2] != NULL && working_array[(i * 2) + 1] != NULL) {
(*names_array)[ix * 2] = working_array[i * 2];
working_array[i * 2] = NULL;
(*names_array)[(ix * 2) + 1] = working_array[(i * 2) + 1];
working_array[(i * 2) + 1] = NULL;
ix++;
}
}
}
if (working_array != NULL) {
for (i = 0; i < NumEmbeddedFiles;i++)
gs_free_object(ctx->memory, working_array[i], "free collection temporary filenames");
gs_free_object(ctx->memory, working_array, "free collection working array");
}
pdfi_countdown(F);
pdfi_countdown(EF);
pdfi_countdown(FileNames);
pdfi_countdown(EmbeddedFiles);
pdfi_countdown(Names);
return code;
}
static int pdfi_process_collection(pdf_context *ctx)
{
int code, i;
uint64_t TotalFiles = 0, ix = 0;
char **names_array = NULL;
code = pdfi_prep_collection(ctx, &TotalFiles, &names_array);
if (code >= 0 && TotalFiles > 0)
{
/* names_array is full of pointers to the scratch file names containing PDF files.
* Now we need to run each PDF file. First we close down the current file.
*/
(void)pdfi_close_pdf_file(ctx);
for (ix = 0;ix < TotalFiles * 2;ix+=2) {
if (names_array[ix] != NULL) {
(void)pdfi_process_pdf_file(ctx, names_array[ix]);
(void)pdfi_close_pdf_file(ctx);
}
}
} else
/* We didn't find any PDF files in the Embedded Files. So just run the
* pages in the container file (the original PDF file)
*/
pdfi_process(ctx);
for (i = 0; i < TotalFiles * 2;i++)
gs_free_object(ctx->memory, names_array[i], "free collection temporary filenames");
gs_free_object(ctx->memory, names_array, "free collection names array");
return 0;
}
int pdfi_process_pdf_file(pdf_context *ctx, char *filename)
{
int code = 0;
code = pdfi_open_pdf_file(ctx, filename);
if (code < 0) {
pdfi_report_errors(ctx);
return code;
}
/* Need to do this here so that ctx->writepdfmarks will be setup
* It is also called in pdfi_page_render()
* TODO: Should probably look into that..
*/
pdfi_device_set_flags(ctx);
/* Do any custom device configuration */
pdfi_device_misc_config(ctx);
if (ctx->Collection != NULL)
code = pdfi_process_collection(ctx);
else
code = pdfi_process(ctx);
pdfi_close_pdf_file(ctx);
return code;
}
static int pdfi_init_file(pdf_context *ctx)
{
int code = 0;
pdf_obj *o = NULL;
code = pdfi_read_xref(ctx);
if (code < 0) {
if (ctx->is_hybrid) {
/* If its a hybrid file, and we failed to read the XrefStm, try
* again, but this time read the xref table instead.
*/
pdfi_set_error(ctx, 0, NULL, E_PDF_BADXREFSTREAM, "pdfi_init_file", NULL);
pdfi_countdown(ctx->xref_table);
ctx->xref_table = NULL;
ctx->prefer_xrefstm = false;
code = pdfi_read_xref(ctx);
if (code < 0)
goto exit;
} else {
pdfi_set_error(ctx, code, NULL, E_PDF_BADXREFSTREAM, "pdfi_init_file", NULL);
goto exit;
}
}
if (ctx->Trailer) {
/* See comment in pdfi_read_Root() (pdf_doc.c) for details */
pdf_dict *d = ctx->Trailer;
pdfi_countup(d);
code = pdfi_dict_get(ctx, d, "Encrypt", &o);
pdfi_countdown(d);
if (code < 0 && code != gs_error_undefined)
goto exit;
if (code == 0) {
code = pdfi_initialise_Decryption(ctx);
if (code < 0)
goto exit;
}
}
read_root:
if (ctx->Trailer) {
code = pdfi_read_Root(ctx);
if (code < 0) {
/* If we couldn#'t find the Root object, and we were using the XrefStm
* from a hybrid file, then try again, but this time use the xref table
*/
if (code == gs_error_undefined && ctx->is_hybrid && ctx->prefer_xrefstm) {
pdfi_set_error(ctx, 0, NULL, E_PDF_BADXREFSTREAM, "pdfi_init_file", NULL);
pdfi_countdown(ctx->xref_table);
ctx->xref_table = NULL;
ctx->prefer_xrefstm = false;
code = pdfi_read_xref(ctx);
if (code < 0) {
pdfi_set_error(ctx, 0, NULL, E_PDF_BADXREF, "pdfi_init_file", NULL);
goto exit;
}
code = pdfi_read_Root(ctx);
if (code < 0)
goto exit;
} else {
int code1 = pdfi_repair_file(ctx);
if (code1 < 0)
goto exit;
goto read_root;
}
}
}
if (ctx->Trailer) {
code = pdfi_read_Info(ctx);
if (code < 0 && code != gs_error_undefined) {
if (ctx->args.pdfstoponerror)
goto exit;
pdfi_clearstack(ctx);
}
}
if (!ctx->Root) {
dmprintf(ctx->memory, "Catalog dictionary not located in file, unable to proceed\n");
return_error(gs_error_syntaxerror);
}
code = pdfi_read_Pages(ctx);
if (code < 0)
goto exit;
code = pdfi_doc_page_array_init(ctx);
if (code < 0)
goto exit;
if (ctx->num_pages == 0)
dmprintf(ctx->memory, "\n **** Warning: PDF document has no pages.\n");
code = pdfi_doc_trailer(ctx);
if (code < 0)
goto exit;
pdfi_read_OptionalRoot(ctx);
if (ctx->args.pdfinfo) {
code = pdfi_output_metadata(ctx);
if (code < 0 && ctx->args.pdfstoponerror)
goto exit;
}
exit:
if (code < 0)
pdfi_set_error(ctx, code, NULL, 0, "pdfi_init_file", NULL);
pdfi_countdown(o);
return code;
}
int pdfi_set_input_stream(pdf_context *ctx, stream *stm)
{
byte *Buffer = NULL;
char *s = NULL;
float version = 0.0;
gs_offset_t Offset = 0;
int64_t bytes = 0, leftover = 0;
bool found = false;
int code;
/* In case of broken PDF files, the repair could run off the end of the
* file, so make sure that doing so does *not* automagically close the file
*/
stm->close_at_eod = false;
ctx->main_stream = (pdf_c_stream *)gs_alloc_bytes(ctx->memory, sizeof(pdf_c_stream), "PDF interpreter allocate main PDF stream");
if (ctx->main_stream == NULL)
return_error(gs_error_VMerror);
memset(ctx->main_stream, 0x00, sizeof(pdf_c_stream));
ctx->main_stream->s = stm;
Buffer = gs_alloc_bytes(ctx->memory, BUF_SIZE, "PDF interpreter - allocate working buffer for file validation");
if (Buffer == NULL) {
code = gs_error_VMerror;
goto error;
}
/* Determine file size */
pdfi_seek(ctx, ctx->main_stream, 0, SEEK_END);
ctx->main_stream_length = pdfi_tell(ctx->main_stream);
Offset = BUF_SIZE;
bytes = BUF_SIZE;
pdfi_seek(ctx, ctx->main_stream, 0, SEEK_SET);
bytes = Offset = min(BUF_SIZE - 1, ctx->main_stream_length);
if (ctx->args.pdfdebug)
dmprintf(ctx->memory, "%% Reading header\n");
bytes = pdfi_read_bytes(ctx, Buffer, 1, Offset, ctx->main_stream);
if (bytes <= 0) {
emprintf(ctx->memory, "Failed to read any bytes from input stream\n");
code = gs_error_ioerror;
goto error;
}
if (bytes < 8) {
emprintf(ctx->memory, "Failed to read enough bytes for a valid PDF header from input stream\n");
code = gs_error_ioerror;
goto error;
}
Buffer[Offset] = 0x00;
/* First check for existence of header */
s = strstr((char *)Buffer, "%PDF");
if (s == NULL) {
char extra_info[gp_file_name_sizeof];
if (ctx->filename)
gs_snprintf(extra_info, sizeof(extra_info), "%% File %s does not appear to be a PDF file (no %%PDF in first 2Kb of file)\n", ctx->filename);
else
gs_snprintf(extra_info, sizeof(extra_info), "%% File does not appear to be a PDF stream (no %%PDF in first 2Kb of stream)\n");
pdfi_set_error(ctx, 0, NULL, E_PDF_NOHEADER, "pdfi_set_input_stream", extra_info);
} else {
/* Now extract header version (may be overridden later) */
if (sscanf(s + 5, "%f", &version) != 1) {
ctx->HeaderVersion = 0;
pdfi_set_error(ctx, 0, NULL, E_PDF_NOHEADERVERSION, "pdfi_set_input_stream", (char *)"%% Unable to read PDF version from header\n");
}
else {
ctx->HeaderVersion = version;
}
if (ctx->args.pdfdebug)
dmprintf1(ctx->memory, "%% Found header, PDF version is %f\n", ctx->HeaderVersion);
}
/* Jump to EOF and scan backwards looking for startxref */
pdfi_seek(ctx, ctx->main_stream, 0, SEEK_END);
if (ctx->args.pdfdebug)
dmprintf(ctx->memory, "%% Searching for 'startxerf' keyword\n");
/* Initially read min(BUF_SIZE, file_length) bytes of data to the buffer */
bytes = Offset;
do {
byte *last_lineend = NULL;
uint32_t read;
if (pdfi_seek(ctx, ctx->main_stream, ctx->main_stream_length - Offset, SEEK_SET) != 0) {
emprintf1(ctx->memory, "File is smaller than %"PRIi64" bytes\n", (int64_t)Offset);
code = gs_error_ioerror;
goto error;
}
read = pdfi_read_bytes(ctx, Buffer, 1, bytes, ctx->main_stream);
if (read <= 0) {
emprintf1(ctx->memory, "Failed to read %"PRIi64" bytes from file\n", (int64_t)bytes);
code = gs_error_ioerror;
goto error;
}
/* When reading backwards, if we ran out of data in the last buffer while looking
* for a 'startxref, but we had found a linefeed, then we preserved everything
* from the beginning of the buffer up to that linefeed, by copying it to the end
* of the buffer and reducing the number of bytes to read so that it should have filled
* in the gap. If we didn't read enough bytes, then we have a gap between the end of
* the data we just read and the leftover data from teh last buffer. Move the preserved
* data down to meet the end of the data we just read.
*/
if (bytes != read && leftover != 0)
memcpy(Buffer + read, Buffer + bytes, leftover);
/* As above, if we had any leftover data from the last buffer then increase the
* number of bytes available by that amount. We increase 'bytes' (the number of bytes
* to read) to the same value, which should mean we read an entire buffer's worth. Of
* course if we have any data left out of this buffer we'll reduce bytes again...
*/
read = bytes = read + leftover;
/* Now search backwards in the buffer for the startxref token */
while(read) {
if (memcmp(Buffer + read - 9, "startxref", 9) == 0) {
found = true;
break;
} else {
if (Buffer[read - 1] == 0x0a || Buffer[read - 1] == 0x0d)
last_lineend = Buffer + read;
}
read--;
}
if (found) {
byte *b = Buffer + read;
/* Success! stop now */
if(sscanf((char *)b, " %"PRIdOFFSET"", &ctx->startxref) != 1) {
dmprintf(ctx->memory, "Unable to read offset of xref from PDF file\n");
}
break;
} else {
/* Our file read could conceivably have read back to the point where we read
* part of the 'startxref' token, but not all of it. So we want to preserve
* the data in the buffer, but not all of it obviously! The 'startxref' should be followed
* by a line ending, so above we keep a note of the last line ending. If we found one, then
* we preserve from the start of the buffer to that point. This could slow us up if the file
* Is broken, or has a load of junk after the EOF, because we could potentially be saving a
* lot of data on each pass, but that's only going to happen with bad files.
* Note we reduce the number of bytes to read so that it just fits into the buffer up to the
* beginning of the data we preserved.
*/
if (last_lineend) {
leftover = last_lineend - Buffer;
memmove(Buffer + bytes - leftover, last_lineend, leftover);
bytes -= leftover;
} else
leftover = 0;
}
Offset += bytes;
} while(Offset < ctx->main_stream_length);
if (!found)
pdfi_set_error(ctx, 0, NULL, E_PDF_NOSTARTXREF, "pdfi_set_input_stream", NULL);
code = pdfi_init_file(ctx);
error:
gs_free_object(ctx->memory, Buffer, "PDF interpreter - allocate working buffer for file validation");
return code;
}
int pdfi_open_pdf_file(pdf_context *ctx, char *filename)
{
stream *s = NULL;
int code;
if (ctx->args.pdfdebug)
dmprintf1(ctx->memory, "%% Attempting to open %s as a PDF file\n", filename);
ctx->filename = (char *)gs_alloc_bytes(ctx->memory, strlen(filename) + 1, "copy of filename");
if (ctx->filename == NULL)
return_error(gs_error_VMerror);
strcpy(ctx->filename, filename);
s = sfopen(filename, "r", ctx->memory);
if (s == NULL) {
emprintf1(ctx->memory, "Failed to open file %s\n", filename);
return_error(gs_error_ioerror);
}
code = pdfi_set_input_stream(ctx, s);
return code;
}
static size_t pdfi_grdir_path_string_match(const byte *str, size_t sl0, byte *pat, size_t pl)
{
bool found = false;
size_t sl = sl0;
while (found == false) {
if (pl > sl)
break;
if (*str == *pat && memcmp(str, pat, pl) == 0)
found = true;
else {
str++;
sl--;
}
}
if (found)
return (sl0 - sl) + pl;
else
return 0;
}
int pdfi_add_paths_to_search_paths(pdf_context *ctx, const char *ppath, int l, bool fontpath)
{
int i, slen, npaths = (l > 0) ? 1 : 0;
const char *p = ppath;
char *ps;
const char *pe = p + l + 1;
int code = 0;
static const char *resstr = "Resource";
const int restrlen = strlen(resstr);
const char *dirsepstr = gp_file_name_directory_separator();
const int dirsepstrlen = strlen(dirsepstr);
char genresstr[64];
for (ps = (char *)p; ps < pe; ps++) {
if (*ps == gp_file_name_list_separator)
npaths++;
}
if (npaths > 0) {
gs_param_string *pathstrings;
int new_npaths = ctx->search_paths.num_resource_paths + npaths;
if (fontpath != true) {
pathstrings = (gs_param_string *)gs_alloc_bytes(ctx->memory, sizeof(gs_param_string) * new_npaths, "array of paths");
if (pathstrings == NULL)
return_error(gs_error_VMerror);
memset(pathstrings, 0x00, sizeof(gs_param_string) * new_npaths);
for (i = 1; i <= ctx->search_paths.num_init_resource_paths; i++) {
pathstrings[new_npaths - i] = ctx->search_paths.resource_paths[ctx->search_paths.num_resource_paths - i];
}
for (i = 0; i < ctx->search_paths.num_resource_paths - ctx->search_paths.num_init_resource_paths; i++) {
pathstrings[i] = ctx->search_paths.resource_paths[i];
}
/* NO NOT CHANGE "i" BETWEEN HERE....... */
gs_free_object(ctx->memory, ctx->search_paths.resource_paths, "old array of paths");
ctx->search_paths.resource_paths = pathstrings;
ctx->search_paths.num_resource_paths += npaths;
/* .....AND HERE */
for (ps = (char *)p; ps < pe; ps++) {
if (*ps == gp_file_name_list_separator || ps == pe - 1) {
if (*p == gp_file_name_list_separator) p++; /* move past the separator */
slen = ps - p;
pathstrings[i].data = (byte *)gs_alloc_bytes(ctx->memory, slen, "path string body");
if (pathstrings[i].data == NULL) {
code = gs_note_error(gs_error_VMerror);
break;
}
memcpy((char *)pathstrings[i].data, p, slen);
pathstrings[i].size = slen;
pathstrings[i].persistent = false;
i++;
p = ps++;
}
}
if ((restrlen + 2 * dirsepstrlen) < 64) {
size_t grdlen;
memcpy(genresstr, resstr, restrlen +1); /* +1 So we get the null terminator */
strncat(genresstr, dirsepstr, dirsepstrlen);
for (i = 0; i < ctx->search_paths.num_resource_paths; i++) {
if ((grdlen = pdfi_grdir_path_string_match(ctx->search_paths.resource_paths[i].data, ctx->search_paths.resource_paths[i].size, (byte *)genresstr, restrlen + dirsepstrlen)) > 0) {
ctx->search_paths.genericresourcedir.data = ctx->search_paths.resource_paths[i].data;
ctx->search_paths.genericresourcedir.size = grdlen;
ctx->search_paths.genericresourcedir.persistent = true;
break;
}
}
}
}
else {
p = ppath;
pathstrings = (gs_param_string *)gs_alloc_bytes(ctx->memory, sizeof(gs_param_string) * (npaths + ctx->search_paths.num_font_paths), "array of font paths");
if (pathstrings == NULL)
return_error(gs_error_VMerror);
memset(pathstrings, 0x00, sizeof(gs_param_string) * (npaths + ctx->search_paths.num_font_paths));
for (i = 0; i < ctx->search_paths.num_font_paths; i++) {
pathstrings[ctx->search_paths.num_font_paths + i] = ctx->search_paths.font_paths[i];
}
gs_free_object(ctx->memory, ctx->search_paths.font_paths, "old array of paths");
ctx->search_paths.font_paths = pathstrings;
ctx->search_paths.num_font_paths += npaths;
i = 0;
for (ps = (char *)p; ps < pe; ps++) {
if (*ps == gp_file_name_list_separator || ps == pe - 1) {
slen = ps - p;
pathstrings[i].data = (byte *)gs_alloc_bytes(ctx->memory, slen, "path string body");
if (pathstrings[i].data == NULL) {
code = gs_note_error(gs_error_VMerror);
break;
}
memcpy((char *)pathstrings[i].data, p, slen);
pathstrings[i].size = slen;
pathstrings[i].persistent = false;
i++;
p = ps++;
}
}
}
}
return code;
}
int pdfi_add_initial_paths_to_search_paths(pdf_context *ctx, const char *ppath, int l)
{
int code;
if (ctx->search_paths.num_resource_paths != 0)
return_error(gs_error_invalidaccess);
code = pdfi_add_paths_to_search_paths(ctx, ppath, l, false);
ctx->search_paths.num_init_resource_paths = ctx->search_paths.num_resource_paths;
return code;
}
static void pdfi_free_search_paths(pdf_context *ctx)
{
int i;
for (i = 0; i < ctx->search_paths.num_resource_paths; i++) {
if (ctx->search_paths.resource_paths[i].persistent == false)
gs_free_object(ctx->memory, (byte *)ctx->search_paths.resource_paths[i].data, "path string body");
}
for (i = 0; i < ctx->search_paths.num_font_paths; i++) {
if (ctx->search_paths.font_paths[i].persistent == false)
gs_free_object(ctx->memory, (byte *)ctx->search_paths.font_paths[i].data, "path string body");
}
gs_free_object(ctx->memory, (byte *)ctx->search_paths.resource_paths, "array of paths");
gs_free_object(ctx->memory, (byte *)ctx->search_paths.font_paths, "array of font paths");
if (ctx->search_paths.genericresourcedir.persistent == false)
gs_free_object(ctx->memory, (byte *)ctx->search_paths.genericresourcedir.data, "generic resource directory");
}
static void pdfi_free_fontmapfiles(pdf_context *ctx)
{
int i;
for (i = 0; i < ctx->num_fontmapfiles; i++) {
gs_free_object(ctx->memory, ctx->fontmapfiles[i].data, "fontmapfiles string body");
}
gs_free_object(ctx->memory, ctx->fontmapfiles, "fontmapfiles array");
}
/* The fontmap file list doesn't extend, later settings in the command line override earlier ones
(Unlike the "-I" search paths above).
*/
int pdfi_add_fontmapfiles(pdf_context *ctx, const char *ppath, int l)
{
int i, nfilenames = (l > 0) ? 1 : 0;
const char *p = ppath;
char *ps;
const char *pe = p + l + 1;
int code = 0;
pdfi_free_fontmapfiles(ctx);
for (ps = (char *)p; ps < pe; ps++) {
if (*ps == gp_file_name_list_separator)
nfilenames++;
}
if (nfilenames > 0) {
ctx->fontmapfiles = (gs_string *)gs_alloc_bytes(ctx->memory, sizeof(gs_string) * nfilenames, "array of fontmap files");
if (ctx->fontmapfiles == NULL) {
return_error(gs_error_VMerror);
}
else {
memset(ctx->fontmapfiles, 0x00, sizeof(gs_string) * nfilenames);
ctx->num_fontmapfiles = nfilenames;
for (i = 0; i < nfilenames; i++) {
for (ps = (char *)p; ps < pe; ps++) {
if (*ps == gp_file_name_list_separator)
break;
}
ctx->fontmapfiles[i].data = gs_alloc_bytes(ctx->memory, ps - p, "fontmap file name body");
if (ctx->fontmapfiles[i].data == NULL) {
code = gs_note_error(gs_error_VMerror);
goto done;
}
memcpy(ctx->fontmapfiles[i].data, p, ps - p);
ctx->fontmapfiles[i].size = ps - p;
p = ps + 1;
}
}
}
done:
return code;
}
/***********************************************************************************/
/* Highest level functions. The context we create here is returned to the 'PL' */
/* implementation, in future we plan to return it to PostScript by wrapping a */
/* gargabe collected object 'ref' around it and returning that to the PostScript */
/* world. custom PostScript operators will then be able to render pages, annots, */
/* AcroForms etc by passing the opaque object back to functions here, allowing */
/* the interpreter access to its context. */
/* We start with routines for creating and destroying the interpreter context */
pdf_context *pdfi_create_context(gs_memory_t *mem)
{
pdf_context *ctx = NULL;
gs_gstate *pgs = NULL;
int code = 0;
gs_memory_t *pmem = mem->non_gc_memory;
#if PDFI_LEAK_CHECK
gs_memory_status_t mstat;
code = gs_memory_chunk_wrap(&pmem, mem->non_gc_memory);
if (code < 0)
return NULL;
gs_memory_status(pmem, &mstat);
#endif
ctx = (pdf_context *) gs_alloc_bytes(pmem, sizeof(pdf_context), "pdf_create_context");
pgs = gs_gstate_alloc(pmem);
if (!ctx || !pgs)
{
if (ctx)
gs_free_object(pmem, ctx, "pdf_create_context");
if (pgs)
gs_gstate_free(pgs);
return NULL;
}
memset(ctx, 0, sizeof(pdf_context));
ctx->memory = pmem;
ctx->type = PDF_CTX;
ctx->flags = 0;
ctx->refcnt = 1;
ctx->ctx = ctx;
#if PDFI_LEAK_CHECK
ctx->memstat = mstat;
#endif
ctx->stack_bot = (pdf_obj **)gs_alloc_bytes(ctx->memory, INITIAL_STACK_SIZE * sizeof (pdf_obj *), "pdf_imp_allocate_interp_stack");
if (ctx->stack_bot == NULL) {
gs_free_object(pmem, ctx, "pdf_create_context");
gs_gstate_free(pgs);
return NULL;
}
ctx->stack_size = INITIAL_STACK_SIZE;
ctx->stack_top = ctx->stack_bot - 1;
code = sizeof(pdf_obj *);
code *= ctx->stack_size;
ctx->stack_limit = ctx->stack_bot + ctx->stack_size;
code = pdfi_init_font_directory(ctx);
if (code < 0) {
gs_free_object(pmem, ctx->stack_bot, "pdf_create_context");
gs_free_object(pmem, ctx, "pdf_create_context");
gs_gstate_free(pgs);
return NULL;
}
code = gsicc_init_iccmanager(pgs);
if (code < 0) {
gs_free_object(ctx->memory, ctx->font_dir, "pdf_create_context");
gs_free_object(pmem, ctx->stack_bot, "pdf_create_context");
gs_free_object(pmem, ctx, "pdf_create_context");
gs_gstate_free(pgs);
return NULL;
}
ctx->pgs = pgs;
code = pdfi_gstate_set_client(ctx, pgs);
if (code < 0) {
gs_free_object(ctx->memory, ctx->font_dir, "pdf_create_context");
gs_free_object(pmem, ctx->stack_bot, "pdf_create_context");
gs_free_object(pmem, ctx, "pdf_create_context");
gs_gstate_free(pgs);
return NULL;
}
/* Some (but not all) path construction operations can either return
* an error or clamp values when out of range. In order to match Ghostscript's
* PDF interpreter written in PostScript, we need to clamp them.
*/
gs_setlimitclamp(pgs, true);
/* Declare PDL client support for high level patterns, for the benefit
* of pdfwrite and other high-level devices
*/
ctx->pgs->have_pattern_streams = true;
ctx->device_state.preserve_tr_mode = 0;
ctx->args.notransparency = false;
ctx->main_stream = NULL;
/* Setup some flags that don't default to 'false' */
ctx->args.showannots = true;
ctx->args.preserveannots = true;
/* NOTE: For testing certain annotations on cluster, might want to set this to false */
ctx->args.printed = true; /* TODO: Should be true if OutputFile is set, false otherwise */
/* Initially, prefer the XrefStm in a hybrid file */
ctx->prefer_xrefstm = true;
/* We decrypt strings from encrypted files until we start a page */
ctx->encryption.decrypt_strings = true;
ctx->get_glyph_name = pdfi_glyph_name;
ctx->get_glyph_index = pdfi_glyph_index;
ctx->job_gstate_level = ctx->pgs->level;
/* Weirdly the graphics library wants us to always have two gstates, the
* initial state and at least one saved state. if we don't then when we
* grestore back to the initial state, it immediately saves another one.
*/
code = gs_gsave(ctx->pgs);
if (code < 0) {
gs_free_object(ctx->memory, ctx->font_dir, "pdf_create_context");
gs_free_object(pmem, ctx->stack_bot, "pdf_create_context");
gs_gstate_free(ctx->pgs);
gs_free_object(pmem, ctx, "pdf_create_context");
return NULL;
}
#if REFCNT_DEBUG
ctx->UID = 1;
#endif
#if CACHE_STATISTICS
ctx->hits = 0;
ctx->misses = 0;
ctx->compressed_hits = 0;
ctx->compressed_misses = 0;
#endif
#ifdef DEBUG
ctx->args.verbose_errors = ctx->args.verbose_warnings = 1;
#endif
return ctx;
}
/* Purge all */
static bool
pdfi_fontdir_purge_all(const gs_memory_t * mem, cached_char * cc, void *dummy)
{
return true;
}
#if DEBUG_CACHE
#if DEBUG_CACHE_FREE
static void
pdfi_print_cache(pdf_context *ctx)
{
pdf_obj_cache_entry *entry = ctx->cache_LRU, *next;
dmprintf1(ctx->memory, "CACHE: #entries=%d\n", ctx->cache_entries);
while(entry) {
next = entry->next;
#if REFCNT_DEBUG
dmprintf5(ctx->memory, "UID:%ld, Object:%d, refcnt:%d, next=%p, prev=%p\n",
entry->o->UID, entry->o->object_num, entry->o->refcnt,
entry->next, entry->previous);
#else
dmprintf4(ctx->memory, "Object:%d, refcnt:%d, next=%p, prev=%p\n",
entry->o->object_num, entry->o->refcnt,
entry->next, entry->previous);
#endif
entry = next;
}
}
#else
static void
pdfi_print_cache(pdf_context *ctx)
{}
#endif
#endif /* DEBUG */
#if PURGE_CACHE_PER_PAGE
void
pdfi_purge_obj_cache(pdf_context *ctx)
{
if (ctx->cache_entries != 0) {
pdf_obj_cache_entry *entry = ctx->cache_LRU, *next;
while(entry) {
next = entry->next;
if (entry->o->object_num != 0) {
ctx->xref_table->xref[entry->o->object_num].cache = NULL;
}
pdfi_countdown(entry->o);
ctx->cache_entries--;
gs_free_object(ctx->memory, entry, "pdfi_clear_context, free LRU");
entry = next;
#if REFCNT_DEBUG
ctx->cache_LRU = entry;
#endif
}
ctx->cache_LRU = ctx->cache_MRU = NULL;
ctx->cache_entries = 0;
}
}
#endif
/* pdfi_clear_context frees all the PDF objects associated with interpreting a given
* PDF file. Once we've called this we can happily run another file. This function is
* called by pdf_free_context (in case of errors during the file leaving state around)
* and by pdfi_close_pdf_file.
*/
int pdfi_clear_context(pdf_context *ctx)
{
#if CACHE_STATISTICS
float compressed_hit_rate = 0.0, hit_rate = 0.0;
if (ctx->compressed_hits > 0 || ctx->compressed_misses > 0)
compressed_hit_rate = (float)ctx->compressed_hits / (float)(ctx->compressed_hits + ctx->compressed_misses);
if (ctx->hits > 0 || ctx->misses > 0)
hit_rate = (float)ctx->hits / (float)(ctx->hits + ctx->misses);
dmprintf1(ctx->memory, "Number of normal object cache hits: %"PRIi64"\n", ctx->hits);
dmprintf1(ctx->memory, "Number of normal object cache misses: %"PRIi64"\n", ctx->misses);
dmprintf1(ctx->memory, "Number of compressed object cache hits: %"PRIi64"\n", ctx->compressed_hits);
dmprintf1(ctx->memory, "Number of compressed object cache misses: %"PRIi64"\n", ctx->compressed_misses);
dmprintf1(ctx->memory, "Normal object cache hit rate: %f\n", hit_rate);
dmprintf1(ctx->memory, "Compressed object cache hit rate: %f\n", compressed_hit_rate);
#endif
if (ctx->args.PageList) {
gs_free_object(ctx->memory, ctx->args.PageList, "pdfi_clear_context");
ctx->args.PageList = NULL;
}
if (ctx->Trailer) {
pdfi_countdown(ctx->Trailer);
ctx->Trailer = NULL;
}
if (ctx->AcroForm) {
pdfi_countdown(ctx->AcroForm);
ctx->AcroForm = NULL;
}
if(ctx->Root) {
pdfi_countdown(ctx->Root);
ctx->Root = NULL;
}
if (ctx->Info) {
pdfi_countdown(ctx->Info);
ctx->Info = NULL;
}
if (ctx->PagesTree) {
pdfi_countdown(ctx->PagesTree);
ctx->PagesTree = NULL;
}
if (ctx->args.cidsubstpath.data != NULL) {
gs_free_object(ctx->memory, ctx->args.cidsubstpath.data, "cidsubstpath.data");
ctx->args.cidsubstpath.data = NULL;
}
if (ctx->args.cidsubstfont.data != NULL) {
gs_free_object(ctx->memory, ctx->args.cidsubstfont.data, "cidsubstpath.data");
ctx->args.cidsubstfont.data = NULL;
}
pdfi_free_cstring_array(ctx, &ctx->args.showannottypes);
pdfi_free_cstring_array(ctx, &ctx->args.preserveannottypes);
pdfi_doc_page_array_free(ctx);
if (ctx->xref_table) {
pdfi_countdown(ctx->xref_table);
ctx->xref_table = NULL;
}
pdfi_free_OptionalRoot(ctx);
if (ctx->stack_bot)
pdfi_clearstack(ctx);
if (ctx->filename) {
/* This should already be closed! */
pdfi_close_pdf_file(ctx);
gs_free_object(ctx->memory, ctx->filename, "pdfi_clear_context, free copy of filename");
ctx->filename = NULL;
}
if (ctx->main_stream) {
gs_free_object(ctx->memory, ctx->main_stream, "pdfi_clear_context, free main PDF stream");
ctx->main_stream = NULL;
}
ctx->main_stream_length = 0;
if(ctx->pgs != NULL) {
gx_pattern_cache_free(ctx->pgs->pattern_cache);
ctx->pgs->pattern_cache = NULL;
if (ctx->pgs->font)
pdfi_countdown_current_font(ctx);
/* We use gs_grestore_only() instead of gs_grestore, because gs_grestore
* will not restore below two gstates and we want to clear the entire
* stack of saved states, back to the initial state.
*/
while (ctx->pgs->level != ctx->job_gstate_level && ctx->pgs->saved)
gs_grestore_only(ctx->pgs);
}
pdfi_free_DefaultQState(ctx);
pdfi_oc_free(ctx);
if(ctx->encryption.EKey) {
pdfi_countdown(ctx->encryption.EKey);
ctx->encryption.EKey = NULL;
}
if (ctx->encryption.Password) {
gs_free_object(ctx->memory, ctx->encryption.Password, "PDF Password from params");
ctx->encryption.Password = NULL;
}
if (ctx->cache_entries != 0) {
pdf_obj_cache_entry *entry = ctx->cache_LRU, *next;
#if DEBUG_CACHE
int count;
bool stop = true;
pdf_obj_cache_entry *prev;
do {
pdfi_print_cache(ctx);
entry = ctx->cache_LRU;
stop = true;
while(entry) {
pdfi_print_cache(ctx);
next = entry->next;
prev = entry->previous;
/* pass through the cache, count down any objects which are only referenced by the cache (refcnt == 1)
* this may cause other objects (referred to by the newly freed object) to decrement their refcnt
* until they are also only pointed at by the cache.
*/
if (entry->o->refcnt == 1) {
stop = false;
pdfi_countdown(entry->o);
if (prev != NULL)
prev->next = next;
else
ctx->cache_LRU = next;
if (next)
next->previous = prev;
ctx->cache_entries--;
gs_free_object(ctx->memory, entry, "pdfi_clear_context, free LRU");
}
entry = next;
}
} while (stop == false);
entry = ctx->cache_LRU;
while(entry) {
next = entry->next;
prev = entry->previous;
count = entry->o->refcnt;
dbgmprintf1(ctx->memory, "CLEANUP cache entry obj %d", entry->o->object_num);
dbgmprintf1(ctx->memory, " has refcnt %d\n", count);
entry = next;
}
#else
while(entry) {
next = entry->next;
pdfi_countdown(entry->o);
ctx->cache_entries--;
gs_free_object(ctx->memory, entry, "pdfi_clear_context, free LRU");
entry = next;
#if REFCNT_DEBUG
ctx->cache_LRU = entry;
#endif
}
#endif
ctx->cache_LRU = ctx->cache_MRU = NULL;
ctx->cache_entries = 0;
}
/* We can't free the font directory before the graphics library fonts fonts are freed, as they reference the font_dir.
* graphics library fonts are refrenced from pdf_font objects, and those may be in the cache, which means they
* won't be freed until we empty the cache. So we can't free 'font_dir' until after the cache has been cleared.
*/
if (ctx->font_dir)
gx_purge_selected_cached_chars(ctx->font_dir, pdfi_fontdir_purge_all, (void *)NULL);
pdfi_countdown(ctx->pdffontmap);
ctx->pdffontmap = NULL;
pdfi_countdown(ctx->pdfnativefontmap);
ctx->pdfnativefontmap = NULL;
return 0;
}
int pdfi_free_context(pdf_context *ctx)
{
#if PDFI_LEAK_CHECK
gs_memory_status_t mstat, ctxmstat = ctx->memstat;
gs_memory_t *mem = ctx->memory;
#endif
pdfi_clear_context(ctx);
gs_free_object(ctx->memory, ctx->stack_bot, "pdfi_free_context");
pdfi_free_name_table(ctx);
/* And here we free the initial graphics state */
while (ctx->pgs->saved)
gs_grestore_only(ctx->pgs);
gs_gstate_free(ctx->pgs);
ctx->pgs = NULL;
if (ctx->font_dir)
gs_free_object(ctx->memory, ctx->font_dir, "pdfi_free_context");
/* Currently this should never happen, but in future it might if we choose
* not to keep freeing and reallocating the array.
*/
if (ctx->loop_detection != NULL) {
dbgmprintf(ctx->memory, "Loop detection array exists at EOJ\n");
gs_free_object(ctx->memory, ctx->loop_detection, "pdfi_free_context");
}
pdfi_free_search_paths(ctx);
pdfi_free_fontmapfiles(ctx);
if (ctx->pdfcidfmap != NULL) {
pdfi_countdown(ctx->pdfcidfmap);
ctx->pdfcidfmap = NULL;
}
if (ctx->pdffontmap != NULL) {
pdfi_countdown(ctx->pdffontmap);
ctx->pdffontmap = NULL;
}
gs_free_object(ctx->memory, ctx, "pdfi_free_context");
#if PDFI_LEAK_CHECK
gs_memory_status(mem, &mstat);
if (mstat.allocated > ctxmstat.allocated)
errprintf(mem, "\nMemory Leak Detected: Pre %d, Post %d\n", (int)ctxmstat.allocated, (int)mstat.allocated);
(void)gs_memory_chunk_unwrap(mem);
#endif
return 0;
}
/* These routines are used from the PostScript interpreter inteerface. It is important that
* the 'interpreter part of the graphics state' should be a pdfi interpreter context while pdfi is running
* but the PostScript itnerpreter context when the PostScript interpreter is running. If we are going
* to inherit the PostScript graphics state for pdfi, then we need to turn it into a 'pdfi'
* graphics state for the duration of the interpretation, and back to a PostScript one when
* we return to the PostScript interpreter.
*
* Bizarrely it appears that the interpreter part of the gstate does not obey grestore, instead we copy
* the 'current' context to the saved context when we do a grestore. This seems wrong to me, but
* it seems to be what happens, so we can't rely on grestore to put back the interpreter context, but must
* do so ourselves.
*
* Hence the 'from_PS' routine fills in pointers with the current context and procs, with the expectation that
* these will be saved and used to restore the data in the 'to_PS' routine.
*/
/* NOTE see the comments in zpdfops.c just under the declaration of the pdfi_switch_t strcuture regarding
* complications with the ICC profile cache.
*/
int pdfi_gstate_from_PS(pdf_context *ctx, gs_gstate *pgs, pdfi_switch_t *i_switch, gsicc_profile_cache_t *profile_cache)
{
int code;
i_switch->pgs = ctx->pgs;
i_switch->procs = pgs->client_procs;
i_switch->client_data = (void *)pgs->client_data;
i_switch->profile_cache = pgs->icc_profile_cache;
code = pdfi_gstate_set_client(ctx, pgs);
if (code < 0)
return code;
i_switch->psfont = pgs->font;
pgs->icc_profile_cache = profile_cache;
rc_increment(pgs->icc_profile_cache);
pgs->font = NULL;
ctx->pgs = pgs;
return code;
}
void pdfi_gstate_to_PS(pdf_context *ctx, gs_gstate *pgs, pdfi_switch_t *i_switch)
{
pgs->client_procs.free(pgs->client_data, pgs->memory, pgs);
pgs->client_data = NULL;
rc_decrement(pgs->icc_profile_cache, "pdfi_gstate_to_PS");
pgs->icc_profile_cache = i_switch->profile_cache;
gs_gstate_set_client(pgs, i_switch->client_data, &i_switch->procs, true);
ctx->pgs->font = NULL;
ctx->pgs = i_switch->pgs;
pgs->font = i_switch->psfont;
}
|