File: pdftoepdf.cc

package info (click to toggle)
texlive-bin 2016.20160513.41080.dfsg-2+deb9u1
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 155,060 kB
  • sloc: ansic: 702,862; cpp: 222,090; perl: 76,014; sh: 23,402; makefile: 8,078; lex: 4,710; pascal: 3,782; python: 3,614; java: 3,569; yacc: 2,905; exp: 2,031; xml: 800; tcl: 670; ruby: 620; lisp: 397; sed: 351; asm: 140; csh: 48; awk: 30
file content (1108 lines) | stat: -rw-r--r-- 36,077 bytes parent folder | download
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
/*
Copyright 1996-2014 Han The Thanh, <thanh@pdftex.org>

This file is part of pdfTeX.

pdfTeX is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.

pdfTeX is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License along
with this program.  If not, see <http://www.gnu.org/licenses/>.
*/

/* Do this early in order to avoid a conflict between
   MINGW32 <rpcndr.h> defining 'boolean' as 'unsigned char' and
   <kpathsea/types.h> defining Pascal's boolean as 'int'.
*/
#include <w2c/config.h>
#include <kpathsea/lib.h>

#include <stdlib.h>
#include <math.h>
#include <stddef.h>
#include <stdio.h>
#include <string.h>
#include <ctype.h>

#ifdef POPPLER_VERSION
#include <dirent.h>
#include <poppler-config.h>
#include <goo/GooString.h>
#include <goo/gmem.h>
#include <goo/gfile.h>
#define GString GooString
#else
#include <aconf.h>
#include <GString.h>
#include <gmem.h>
#include <gfile.h>
#endif
#include <assert.h>

#include "Object.h"
#include "Stream.h"
#include "Array.h"
#include "Dict.h"
#include "XRef.h"
#include "Catalog.h"
#include "Link.h"
#include "Page.h"
#include "GfxFont.h"
#include "PDFDoc.h"
#include "GlobalParams.h"
#include "Error.h"

// This file is mostly C and not very much C++; it's just used to interface
// the functions of xpdf, which are written in C++.

extern "C" {
#include <pdftexdir/ptexmac.h>
#include <pdftexdir/pdftex-common.h>

// These functions from pdftex.web gets declared in pdftexcoerce.h in the
// usual web2c way, but we cannot include that file here because C++
// does not allow it.
extern int getpdfsuppresswarningpagegroup(void);
extern integer getpdfsuppressptexinfo(void);
extern integer zround(double);
}

// The prefix "PTEX" for the PDF keys is special to pdfTeX;
// this has been registered with Adobe by Hans Hagen.

#define pdfkeyprefix "PTEX"

#define MASK_SUPPRESS_PTEX_FULLBANNER 0x01
#define MASK_SUPPRESS_PTEX_FILENAME   0x02
#define MASK_SUPPRESS_PTEX_PAGENUMBER 0x04
#define MASK_SUPPRESS_PTEX_INFODICT   0x08

// PdfObject encapsulates the xpdf Object type,
// and properly frees its resources on destruction.
// Use obj-> to access members of the Object,
// and &obj to get a pointer to the object.
// It is no longer necessary to call Object::free explicitely.

class PdfObject {
  public:
    PdfObject() {               // nothing
    } ~PdfObject() {
        iObject.free();
    }
    Object *operator->() {
        return &iObject;
    }
    Object *operator&() {
        return &iObject;
    }
  private:                     // no copying or assigning
    PdfObject(const PdfObject &);
    void operator=(const PdfObject &);
  public:
    Object iObject;
};

// When copying the Resources of the selected page, all objects are copied
// recusively top-down. Indirect objects however are not fetched during
// copying, but get a new object number from pdfTeX and then will be
// appended into a linked list. Duplicates are checked and removed from the
// list of indirect objects during appending.

enum InObjType {
    objFont,
    objFontDesc,
    objOther
};

struct InObj {
    Ref ref;                    // ref in original PDF
    InObjType type;             // object type
    InObj *next;                // next entry in list of indirect objects
    int num;                    // new object number in output PDF
    fd_entry *fd;               // pointer to /FontDescriptor object structure
    int enc_objnum;             // Encoding for objFont
    int written;                // has it been written to output PDF?
};

struct UsedEncoding {
    int enc_objnum;
    GfxFont *font;
    UsedEncoding *next;
};

static InObj *inObjList;
static UsedEncoding *encodingList;
static GBool isInit = gFalse;

// --------------------------------------------------------------------
// Maintain list of open embedded PDF files
// --------------------------------------------------------------------

struct PdfDocument {
    char *file_name;
    PDFDoc *doc;
    XRef *xref;
    InObj *inObjList;
    int occurences;             // number of references to the document; the doc can be
    // deleted when this is negative
    PdfDocument *next;
};

static PdfDocument *pdfDocuments = 0;

static XRef *xref = 0;

// Returns pointer to PdfDocument record for PDF file.
// Creates a new record if it doesn't exist yet.
// xref is made current for the document.

static PdfDocument *find_add_document(char *file_name)
{
    PdfDocument *p = pdfDocuments;
    while (p && strcmp(p->file_name, file_name) != 0)
        p = p->next;
    if (p) {
        xref = p->xref;
        (p->occurences)++;
        return p;
    }
    p = new PdfDocument;
    p->file_name = xstrdup(file_name);
    p->xref = xref = 0;
    p->occurences = 0;
    GString *docName = new GString(p->file_name);
    p->doc = new PDFDoc(docName);       // takes ownership of docName
    if (!p->doc->isOk() || !p->doc->okToPrint()) {
        pdftex_fail("xpdf: reading PDF image failed");
    }
    p->inObjList = 0;
    p->next = pdfDocuments;
    pdfDocuments = p;
    return p;
}

// Deallocate a PdfDocument with all its resources

static void delete_document(PdfDocument * pdf_doc)
{
    PdfDocument **p = &pdfDocuments;
    while (*p && *p != pdf_doc)
        p = &((*p)->next);
    // should not happen:
    if (!*p)
        return;
    // unlink from list
    *p = pdf_doc->next;
    // free pdf_doc's resources
    InObj *r, *n;
    for (r = pdf_doc->inObjList; r != 0; r = n) {
        n = r->next;
        delete r;
    }
    xref = pdf_doc->xref;
    delete pdf_doc->doc;
    xfree(pdf_doc->file_name);
    delete pdf_doc;
}

// Replacement for
//      Object *initDict(Dict *dict1){ initObj(objDict); dict = dict1; return this; }

static void initDictFromDict(PdfObject & obj, Dict * dict)
{
    obj->initDict(xref);
    for (int i = 0, l = dict->getLength(); i < l; i++) {
        Object obj1;
        obj->dictAdd(copyString(dict->getKey(i)), dict->getValNF(i, &obj1));
    }
}

// --------------------------------------------------------------------

static int addEncoding(GfxFont * gfont)
{
    UsedEncoding *n;
    n = new UsedEncoding;
    n->next = encodingList;
    encodingList = n;
    n->font = gfont;
    n->enc_objnum = pdfnewobjnum();
    return n->enc_objnum;
}

#define addFont(ref, fd, enc_objnum) \
        addInObj(objFont, ref, fd, enc_objnum)

// addFontDesc is only used to avoid writing the original FontDescriptor
// from the PDF file.

#define addFontDesc(ref, fd) \
        addInObj(objFontDesc, ref, fd, 0)

#define addOther(ref) \
        addInObj(objOther, ref, 0, 0)

static int addInObj(InObjType type, Ref ref, fd_entry * fd, int e)
{
    InObj *p, *q, *n = new InObj;
    if (ref.num == 0)
        pdftex_fail("PDF inclusion: invalid reference");
    n->ref = ref;
    n->type = type;
    n->next = 0;
    n->fd = fd;
    n->enc_objnum = e;
    n->written = 0;
    if (inObjList == 0)
        inObjList = n;
    else {
        for (p = inObjList; p != 0; p = p->next) {
            if (p->ref.num == ref.num && p->ref.gen == ref.gen) {
                delete n;
                return p->num;
            }
            q = p;
        }
        // it is important to add new objects at the end of the list,
        // because new objects are being added while the list is being
        // written out.
        q->next = n;
    }
    if (type == objFontDesc)
        n->num = get_fd_objnum(fd);
    else
        n->num = pdfnewobjnum();
    return n->num;
}

#if 0 /* unusewd */
static int getNewObjectNumber(Ref ref)
{
    InObj *p;
    if (inObjList == 0) {
        pdftex_fail("No objects copied yet");
    } else {
        for (p = inObjList; p != 0; p = p->next) {
            if (p->ref.num == ref.num && p->ref.gen == ref.gen) {
                return p->num;
            }
        }
        pdftex_fail("Object not yet copied: %i %i", ref.num, ref.gen);
    }
#ifdef _MSC_VER
    /* Never reached, but without __attribute__((noreturn)) for pdftex_fail()
       MSVC 5.0 requires an int return value.  */
    return -60000;
#endif
}
#endif

static void copyObject(Object *);

static void copyName(char *s)
{
    pdf_puts("/");
    for (; *s != 0; s++) {
        if (isdigit(*s) || isupper(*s) || islower(*s) || *s == '_' ||
            *s == '.' || *s == '-' || *s == '+')
            pdfout(*s);
        else
            pdf_printf("#%.2X", *s & 0xFF);
    }
}

static void copyDictEntry(Object * obj, int i)
{
    PdfObject obj1;
    copyName(obj->dictGetKey(i));
    pdf_puts(" ");
    obj->dictGetValNF(i, &obj1);
    copyObject(&obj1);
    pdf_puts("\n");
}

static void copyDict(Object * obj)
{
    int i, l;
    if (!obj->isDict())
        pdftex_fail("PDF inclusion: invalid dict type <%s>",
                    obj->getTypeName());
    for (i = 0, l = obj->dictGetLength(); i < l; ++i)
        copyDictEntry(obj, i);
}

static void copyFontDict(Object * obj, InObj * r)
{
    int i, l;
    char *key;
    if (!obj->isDict())
        pdftex_fail("PDF inclusion: invalid dict type <%s>",
                    obj->getTypeName());
    pdf_puts("<<\n");
    assert(r->type == objFont); // FontDescriptor is in fd_tree
    for (i = 0, l = obj->dictGetLength(); i < l; ++i) {
        key = obj->dictGetKey(i);
        if (strncmp("FontDescriptor", key, strlen("FontDescriptor")) == 0
            || strncmp("BaseFont", key, strlen("BaseFont")) == 0
            || strncmp("Encoding", key, strlen("Encoding")) == 0)
            continue;           // skip original values
        copyDictEntry(obj, i);
    }
    // write new FontDescriptor, BaseFont, and Encoding
    pdf_printf("/FontDescriptor %d 0 R\n", get_fd_objnum(r->fd));
    pdf_printf("/BaseFont %d 0 R\n", get_fn_objnum(r->fd));
    pdf_printf("/Encoding %d 0 R\n", r->enc_objnum);
    pdf_puts(">>");
}

static void copyStream(Stream * str)
{
    int c, c2 = 0;
    str->reset();
    while ((c = str->getChar()) != EOF) {
        pdfout(c);
        c2 = c;
    }
    pdflastbyte = c2;
}

static void copyProcSet(Object * obj)
{
    int i, l;
    PdfObject procset;
    if (!obj->isArray())
        pdftex_fail("PDF inclusion: invalid ProcSet array type <%s>",
                    obj->getTypeName());
    pdf_puts("/ProcSet [ ");
    for (i = 0, l = obj->arrayGetLength(); i < l; ++i) {
        obj->arrayGetNF(i, &procset);
        if (!procset->isName())
            pdftex_fail("PDF inclusion: invalid ProcSet entry type <%s>",
                        procset->getTypeName());
        copyName(procset->getName());
        pdf_puts(" ");
    }
    pdf_puts("]\n");
}

#define REPLACE_TYPE1C true

static void copyFont(char *tag, Object * fontRef)
{
    PdfObject fontdict, subtype, basefont, fontdescRef, fontdesc, charset,
        fontfile, ffsubtype, stemV;
    GfxFont *gfont;
    fd_entry *fd;
    fm_entry *fontmap;
    // Check whether the font has already been embedded before analysing it.
    InObj *p;
    Ref ref = fontRef->getRef();
    for (p = inObjList; p; p = p->next) {
        if (p->ref.num == ref.num && p->ref.gen == ref.gen) {
            copyName(tag);
            pdf_printf(" %d 0 R ", p->num);
            return;
        }
    }
    // Only handle included Type1 (and Type1C) fonts; anything else will be copied.
    // Type1C fonts are replaced by Type1 fonts, if REPLACE_TYPE1C is true.
    if (!fixedinclusioncopyfont && fontRef->fetch(xref, &fontdict)->isDict()
        && fontdict->dictLookup("Subtype", &subtype)->isName()
        && !strcmp(subtype->getName(), "Type1")
        && fontdict->dictLookup("BaseFont", &basefont)->isName()
        && fontdict->dictLookupNF("FontDescriptor", &fontdescRef)->isRef()
        && fontdescRef->fetch(xref, &fontdesc)->isDict()
        && (fontdesc->dictLookup("FontFile", &fontfile)->isStream()
            || (REPLACE_TYPE1C
                && fontdesc->dictLookup("FontFile3", &fontfile)->isStream()
                && fontfile->streamGetDict()->lookup("Subtype",
                                                     &ffsubtype)->isName()
                && !strcmp(ffsubtype->getName(), "Type1C")))
        && (fontmap = lookup_fontmap(basefont->getName())) != NULL) {
        // copy the value of /StemV
        fontdesc->dictLookup("StemV", &stemV);
        fd = epdf_create_fontdescriptor(fontmap, zround(stemV->getNum()));
        if (fontdesc->dictLookup("CharSet", &charset) &&
            charset->isString() && is_subsetable(fontmap))
            epdf_mark_glyphs(fd, charset->getString()->getCString());
        else
            embed_whole_font(fd);
        addFontDesc(fontdescRef->getRef(), fd);
        copyName(tag);
        gfont = GfxFont::makeFont(xref, tag, fontRef->getRef(),
                                  fontdict->getDict());
        pdf_printf(" %d 0 R ", addFont(fontRef->getRef(), fd,
                                       addEncoding(gfont)));
    } else {
        copyName(tag);
        pdf_puts(" ");
        copyObject(fontRef);
    }
}

static void copyFontResources(Object * obj)
{
    PdfObject fontRef;
    int i, l;
    if (!obj->isDict())
        pdftex_fail("PDF inclusion: invalid font resources dict type <%s>",
                    obj->getTypeName());
    pdf_puts("/Font << ");
    for (i = 0, l = obj->dictGetLength(); i < l; ++i) {
        obj->dictGetValNF(i, &fontRef);
        if (fontRef->isRef())
            copyFont(obj->dictGetKey(i), &fontRef);
        else if (fontRef->isDict()) {   // some programs generate pdf with embedded font object
            copyName(obj->dictGetKey(i));
            pdf_puts(" ");
            copyObject(&fontRef);
        }
        else
            pdftex_fail("PDF inclusion: invalid font in reference type <%s>",
                        fontRef->getTypeName());
    }
    pdf_puts(">>\n");
}

static void copyOtherResources(Object * obj, char *key)
{
    // copies all other resources (write_epdf handles Fonts and ProcSets),

    // if Subtype is present, it must be a name
    if (strcmp("Subtype", key) == 0) {
        if (!obj->isName()) {
            pdftex_warn("PDF inclusion: Subtype in Resources dict is not a name"
                        " (key '%s', type <%s>); ignored.",
                        key, obj->getTypeName());
            return;
        }
    } else if (!obj->isDict()) {
        //FIXME: Write the message only to the log file
        pdftex_warn("PDF inclusion: invalid other resource which is no dict"
                    " (key '%s', type <%s>); ignored.",
                    key, obj->getTypeName());
        return;
    }
    copyName(key);
    pdf_puts(" ");
    copyObject(obj);
}

// Function onverts double to string; very small and very large numbers
// are NOT converted to scientific notation.
// n must be a number or real conforming to the implementation limits
// of PDF as specified in appendix C.1 of the PDF Ref.
// These are:
// maximum value of ints is +2^32
// maximum value of reals is +2^15
// smalles values of reals is 1/(2^16)

static char *convertNumToPDF(double n)
{
    static const int precision = 6;
    static const int fact = (int) 1E6;  // must be 10^precision
    static const double epsilon = 0.5E-6;       // 2epsilon must be 10^-precision
    static char buf[64];
    // handle very small values: return 0
    if (fabs(n) < epsilon) {
        buf[0] = '0';
        buf[1] = '\0';
    } else {
        char ints[64];
        int bindex = 0, sindex = 0;
        int ival, fval;
        // handle the sign part if n is negative
        if (n < 0) {
            buf[bindex++] = '-';
            n = -n;
        }
        n += epsilon;           // for rounding
        // handle the integer part, simply with sprintf
        ival = (int) floor(n);
        n -= ival;
        sprintf(ints, "%d", ival);
        while (ints[sindex] != 0)
            buf[bindex++] = ints[sindex++];
        // handle the fractional part up to 'precision' digits
        fval = (int) floor(n * fact);
        if (fval) {
            // set a dot
            buf[bindex++] = '.';
            sindex = bindex + precision;
            buf[sindex--] = '\0';
            // fill up trailing zeros with the string terminator NULL
            while (((fval % 10) == 0) && (sindex >= bindex)) {
                buf[sindex--] = '\0';
                fval /= 10;
            }
            // fill up the fractional part back to front
            while (sindex >= bindex) {
                buf[sindex--] = (fval % 10) + '0';
                fval /= 10;
            }
        } else
            buf[bindex++] = 0;
    }
    return (char *) buf;
}

static void copyObject(Object * obj)
{
    PdfObject obj1;
    int i, l, c;
    Ref ref;
    char *p;
    GString *s;
    if (obj->isBool()) {
        pdf_printf("%s", obj->getBool()? "true" : "false");
    } else if (obj->isInt()) {
        pdf_printf("%i", obj->getInt());
    } else if (obj->isReal()) {
        pdf_printf("%s", convertNumToPDF(obj->getReal()));
    } else if (obj->isNum()) {
        pdf_printf("%s", convertNumToPDF(obj->getNum()));
    } else if (obj->isString()) {
        s = obj->getString();
        p = s->getCString();
        l = s->getLength();
        if (strlen(p) == (unsigned int) l) {
            pdf_puts("(");
            for (; *p != 0; p++) {
                c = (unsigned char) *p;
                if (c == '(' || c == ')' || c == '\\')
                    pdf_printf("\\%c", c);
                else if (c < 0x20 || c > 0x7F)
                    pdf_printf("\\%03o", c);
                else
                    pdfout(c);
            }
            pdf_puts(")");
        } else {
            pdf_puts("<");
            for (i = 0; i < l; i++) {
                c = s->getChar(i) & 0xFF;
                pdf_printf("%.2x", c);
            }
            pdf_puts(">");
        }
    } else if (obj->isName()) {
        copyName(obj->getName());
    } else if (obj->isNull()) {
        pdf_puts("null");
    } else if (obj->isArray()) {
        pdf_puts("[");
        for (i = 0, l = obj->arrayGetLength(); i < l; ++i) {
            obj->arrayGetNF(i, &obj1);
            if (!obj1->isName())
                pdf_puts(" ");
            copyObject(&obj1);
        }
        pdf_puts("]");
    } else if (obj->isDict()) {
        pdf_puts("<<\n");
        copyDict(obj);
        pdf_puts(">>");
    } else if (obj->isStream()) {
        initDictFromDict(obj1, obj->streamGetDict());
        pdf_puts("<<\n");
        copyDict(&obj1);
        pdf_puts(">>\n");
        pdf_puts("stream\n");
        copyStream(obj->getStream()->getUndecodedStream());
        pdf_puts("\nendstream");
    } else if (obj->isRef()) {
        ref = obj->getRef();
        if (ref.num == 0) {
            pdftex_fail
                ("PDF inclusion: reference to invalid object"
                 " (is the included pdf broken?)");
        } else
            pdf_printf("%d 0 R", addOther(ref));
    } else {
        pdftex_fail("PDF inclusion: type <%s> cannot be copied",
                    obj->getTypeName());
    }
}

static void writeRefs()
{
    InObj *r;
    for (r = inObjList; r != 0; r = r->next) {
        if (!r->written) {
            Object obj1;
            r->written = 1;
            xref->fetch(r->ref.num, r->ref.gen, &obj1);
            if (r->type == objFont) {
                assert(!obj1.isStream());
                pdfbeginobj(r->num, 2);         // \pdfobjcompresslevel = 2 is for this
                copyFontDict(&obj1, r);
                pdf_puts("\n");
                pdfendobj();
            } else if (r->type != objFontDesc) {        // /FontDescriptor is written via write_fontdescriptor()
                if (obj1.isStream())
                    pdfbeginobj(r->num, 0);
                else
                    pdfbeginobj(r->num, 2);     // \pdfobjcompresslevel = 2 is for this
                copyObject(&obj1);
                pdf_puts("\n");
                pdfendobj();
            }
            obj1.free();
        }
    }
}

static void writeEncodings()
{
    UsedEncoding *r, *n;
    char *glyphNames[256], *s;
    int i;
    for (r = encodingList; r != 0; r = r->next) {
        for (i = 0; i < 256; i++) {
            if (r->font->isCIDFont()) {
                pdftex_fail
                    ("PDF inclusion: CID fonts are not supported"
                     " (try to disable font replacement to fix this)");
            }
            if ((s = ((Gfx8BitFont *) r->font)->getCharName(i)) != 0)
                glyphNames[i] = s;
            else
                glyphNames[i] = notdef;
        }
        epdf_write_enc(glyphNames, r->enc_objnum);
    }
    for (r = encodingList; r != 0; r = n) {
        n = r->next;
#ifdef POPPLER_VERSION
        r->font->decRefCnt();
#else
        delete r->font;
#endif
        delete r;
    }
}

// get the pagebox according to the pagebox_spec
static PDFRectangle *get_pagebox(Page * page, int pagebox_spec)
{
    if (pagebox_spec == pdfboxspecmedia)
        return page->getMediaBox();
    else if (pagebox_spec == pdfboxspeccrop)
        return page->getCropBox();
    else if (pagebox_spec == pdfboxspecbleed)
        return page->getBleedBox();
    else if (pagebox_spec == pdfboxspectrim)
        return page->getTrimBox();
    else if (pagebox_spec == pdfboxspecart)
        return page->getArtBox();
    else
        pdftex_fail("PDF inclusion: unknown value of pagebox spec (%i)",
                    (int) pagebox_spec);
    return page->getMediaBox(); // to make the compiler happy
}


// Reads various information about the PDF and sets it up for later inclusion.
// This will fail if the PDF version of the PDF is higher than
// minor_pdf_version_wanted or page_name is given and can not be found.
// It makes no sense to give page_name _and_ page_num.
// Returns the page number.

int
read_pdf_info(char *image_name, char *page_name, int page_num,
              int pagebox_spec, int minor_pdf_version_wanted,
              int pdf_inclusion_errorlevel)
{
    PdfDocument *pdf_doc;
    Page *page;
    PDFRectangle *pagebox;
#ifdef POPPLER_VERSION
    int pdf_major_version_found, pdf_minor_version_found;
#else
    float pdf_version_found, pdf_version_wanted;
#endif
    // initialize
    if (!isInit) {
        globalParams = new GlobalParams();
        globalParams->setErrQuiet(gFalse);
        isInit = gTrue;
    }
    // open PDF file
    pdf_doc = find_add_document(image_name);
    epdf_doc = (void *) pdf_doc;

    // check PDF version
    // this works only for PDF 1.x -- but since any versions of PDF newer
    // than 1.x will not be backwards compatible to PDF 1.x, pdfTeX will
    // then have to changed drastically anyway.
#ifdef POPPLER_VERSION
    pdf_major_version_found = pdf_doc->doc->getPDFMajorVersion();
    pdf_minor_version_found = pdf_doc->doc->getPDFMinorVersion();
    if ((pdf_major_version_found > 1)
     || (pdf_minor_version_found > minor_pdf_version_wanted)) {
        const char *msg =
            "PDF inclusion: found PDF version <%d.%d>, but at most version <1.%d> allowed";
        if (pdf_inclusion_errorlevel > 0) {
            pdftex_fail(msg, pdf_major_version_found, pdf_minor_version_found, minor_pdf_version_wanted);
        } else if (pdf_inclusion_errorlevel < 0) {
            ; /* do nothing */
        } else { /* = 0, give warning */
            pdftex_warn(msg, pdf_major_version_found, pdf_minor_version_found, minor_pdf_version_wanted);
        }
    }
#else
    pdf_version_found = pdf_doc->doc->getPDFVersion();
    pdf_version_wanted = 1 + (minor_pdf_version_wanted * 0.1);
    if (pdf_version_found > pdf_version_wanted + 0.01) {
        char msg[] =
            "PDF inclusion: found PDF version <%.1f>, but at most version <%.1f> allowed";
        if (pdf_inclusion_errorlevel > 0) {
            pdftex_fail(msg, pdf_version_found, pdf_version_wanted);
        } else if (pdf_inclusion_errorlevel < 0) {
            ; /* do nothing */
        } else { /* = 0, give warning */
            pdftex_warn(msg, pdf_version_found, pdf_version_wanted);
        }
    }
#endif
    epdf_num_pages = pdf_doc->doc->getCatalog()->getNumPages();
    if (page_name) {
        // get page by name
        GString name(page_name);
        LinkDest *link = pdf_doc->doc->findDest(&name);
        if (link == 0 || !link->isOk())
            pdftex_fail("PDF inclusion: invalid destination <%s>", page_name);
        Ref ref = link->getPageRef();
        page_num = pdf_doc->doc->getCatalog()->findPage(ref.num, ref.gen);
        if (page_num == 0)
            pdftex_fail("PDF inclusion: destination is not a page <%s>",
                        page_name);
        delete link;
    } else {
        // get page by number
        if (page_num <= 0 || page_num > epdf_num_pages)
            pdftex_fail("PDF inclusion: required page does not exist <%i>",
                        epdf_num_pages);
    }
    // get the required page
    page = pdf_doc->doc->getCatalog()->getPage(page_num);

    // get the pagebox (media, crop...) to use.
    pagebox = get_pagebox(page, pagebox_spec);
    if (pagebox->x2 > pagebox->x1) {
        epdf_orig_x = pagebox->x1;
        epdf_width = pagebox->x2 - pagebox->x1;
    } else {
        epdf_orig_x = pagebox->x2;
        epdf_width = pagebox->x1 - pagebox->x2;
    }
    if (pagebox->y2 > pagebox->y1) {
        epdf_orig_y = pagebox->y1;
        epdf_height = pagebox->y2 - pagebox->y1;
    } else {
        epdf_orig_y = pagebox->y2;
        epdf_height = pagebox->y1 - pagebox->y2;
    }

    // get page rotation
    epdf_rotate = page->getRotate() % 360;
    if (epdf_rotate < 0)
        epdf_rotate += 360;

    // page group
    if (page->getGroup() != NULL)
        epdf_has_page_group = 1;    // only flag that page group is present;
                                    // the actual object number will be
                                    // generated in pdftex.web
    else
        epdf_has_page_group = 0;    // no page group present

    pdf_doc->xref = pdf_doc->doc->getXRef();
    return page_num;
}

// writes the current epf_doc.
// Here the included PDF is copied, so most errors that can happen during PDF
// inclusion will arise here.

void write_epdf(void)
{
    Page *page;
    Ref *pageRef;
    Dict *pageDict;
    PdfObject contents, obj1, obj2, pageObj, dictObj;
    PdfObject groupDict;
    bool writeSepGroup = false;
    Object info;
    char *key;
    char s[256];
    int i, l;
    int rotate;
    double scale[6] = { 0, 0, 0, 0, 0, 0 };
    bool writematrix = false;
    int suppress_ptex_info = getpdfsuppressptexinfo();
    static const char *pageDictKeys[] = {
        "LastModified",
        "Metadata",
        "PieceInfo",
        "SeparationInfo",
//         "Group",
//         "Resources",
        NULL
    };

    PdfDocument *pdf_doc = (PdfDocument *) epdf_doc;
    (pdf_doc->occurences)--;
    xref = pdf_doc->xref;
    inObjList = pdf_doc->inObjList;
    encodingList = 0;
    page = pdf_doc->doc->getCatalog()->getPage(epdf_selected_page);
    pageRef = pdf_doc->doc->getCatalog()->getPageRef(epdf_selected_page);
    xref->fetch(pageRef->num, pageRef->gen, &pageObj);
    pageDict = pageObj->getDict();
    rotate = page->getRotate();
    PDFRectangle *pagebox;
    // write the Page header
    pdf_puts("/Type /XObject\n");
    pdf_puts("/Subtype /Form\n");
    pdf_puts("/FormType 1\n");

    // write additional information
    if ((suppress_ptex_info & MASK_SUPPRESS_PTEX_FILENAME) == 0) {
        pdf_printf("/%s.FileName (%s)\n", pdfkeyprefix,
                   convertStringToPDFString(pdf_doc->file_name,
                                            strlen(pdf_doc->file_name)));
    }
    if ((suppress_ptex_info & MASK_SUPPRESS_PTEX_PAGENUMBER) == 0) {
        pdf_printf("/%s.PageNumber %i\n", pdfkeyprefix, (int) epdf_selected_page);
    }
    if ((suppress_ptex_info & MASK_SUPPRESS_PTEX_INFODICT) == 0) {
        pdf_doc->doc->getDocInfoNF(&info);
        if (info.isRef()) {
            // the info dict must be indirect (PDF Ref p. 61)
            pdf_printf("/%s.InfoDict ", pdfkeyprefix);
            pdf_printf("%d 0 R\n", addOther(info.getRef()));
        }
    }
    // get the pagebox (media, crop...) to use.
    pagebox = get_pagebox(page, epdf_page_box);

    // handle page rotation
    if (rotate != 0) {
        if (rotate % 90 == 0) {
            // this handles only the simple case: multiple of 90s but these
            // are the only values allowed according to the reference
            // (v1.3, p. 78).
            // the image is rotated around its center.
            // the /Rotate key is clockwise while the matrix is
            // counterclockwise :-%
            tex_printf(", page is rotated %d degrees", rotate);
            switch (rotate) {
            case 90:
                scale[1] = -1;
                scale[2] = 1;
                scale[4] = pagebox->x1 - pagebox->y1;
                scale[5] = pagebox->y1 + pagebox->x2;
                writematrix = true;
                break;
            case 180:
                scale[0] = scale[3] = -1;
                scale[4] = pagebox->x1 + pagebox->x2;
                scale[5] = pagebox->y1 + pagebox->y2;
                writematrix = true;
                break;          // width and height are exchanged
            case 270:
                scale[1] = 1;
                scale[2] = -1;
                scale[4] = pagebox->x1 + pagebox->y2;
                scale[5] = pagebox->y1 - pagebox->x1;
                writematrix = true;
                break;
            }
            if (writematrix) {  // The matrix is only written if the image is rotated.
                sprintf(s, "/Matrix [%.8f %.8f %.8f %.8f %.8f %.8f]\n",
                        scale[0],
                        scale[1], scale[2], scale[3], scale[4], scale[5]);
                pdf_puts(stripzeros(s));
            }
        }
    }

    sprintf(s, "/BBox [%.8f %.8f %.8f %.8f]\n",
            pagebox->x1, pagebox->y1, pagebox->x2, pagebox->y2);
    pdf_puts(stripzeros(s));

    // Metadata validity check (as a stream it must be indirect)
    pageDict->lookupNF("Metadata", &dictObj);
    if (!dictObj->isNull() && !dictObj->isRef())
        pdftex_warn("PDF inclusion: /Metadata must be indirect object");

    // copy selected items in Page dictionary except Resources & Group
    for (i = 0; pageDictKeys[i] != NULL; i++) {
        pageDict->lookupNF(pageDictKeys[i], &dictObj);
        if (!dictObj->isNull()) {
            pdf_newline();
            pdf_printf("/%s ", pageDictKeys[i]);
            copyObject(&dictObj); // preserves indirection
        }
    } 

    // handle page group
    pageDict->lookupNF("Group", &dictObj);
    if (!dictObj->isNull()) {
        if (pdfpagegroupval == 0) { 
            // another pdf with page group was included earlier on the
            // same page; copy the Group entry as is.  See manual for
            // info on why this is a warning.
            if (getpdfsuppresswarningpagegroup() == 0) {
                pdftex_warn
    ("PDF inclusion: multiple pdfs with page group included in a single page");
            }
            pdf_newline();
            pdf_puts("/Group ");
            copyObject(&dictObj);
        } else {
            // write Group dict as a separate object, since the Page dict also refers to it
            pageDict->lookup("Group", &dictObj);
            if (!dictObj->isDict())
                pdftex_fail("PDF inclusion: /Group dict missing");
            writeSepGroup = true;
            initDictFromDict(groupDict, page->getGroup());
            pdf_printf("/Group %ld 0 R\n", (long)pdfpagegroupval);
        }
    }

    // write the Resources dictionary
    if (page->getResourceDict() == NULL) {
        // Resources can be missing (files without them have been spotted
        // in the wild); in which case the /Resouces of the /Page will be used.
        // "This practice is not recommended".
        pdftex_warn
            ("PDF inclusion: /Resources missing. 'This practice is not recommended' (PDF Ref)");
    } else {
        initDictFromDict(obj1, page->getResourceDict());
        if (!obj1->isDict())
            pdftex_fail("PDF inclusion: invalid resources dict type <%s>",
                        obj1->getTypeName());
        pdf_newline();
        pdf_puts("/Resources <<\n");
        for (i = 0, l = obj1->dictGetLength(); i < l; ++i) {
            obj1->dictGetVal(i, &obj2);
            key = obj1->dictGetKey(i);
            if (strcmp("Font", key) == 0)
                copyFontResources(&obj2);
            else if (strcmp("ProcSet", key) == 0)
                copyProcSet(&obj2);
            else
                copyOtherResources(&obj2, key);
        }
        pdf_puts(">>\n");
    }

    // write the page contents
    page->getContents(&contents);
    if (contents->isStream()) {

        // Variant A: get stream and recompress under control
        // of \pdfcompresslevel
        //
        // pdfbeginstream();
        // copyStream(contents->getStream());
        // pdfendstream();

        // Variant B: copy stream without recompressing
        //
        contents->streamGetDict()->lookup("F", &obj1);
        if (!obj1->isNull()) {
            pdftex_fail("PDF inclusion: Unsupported external stream");
        }
        contents->streamGetDict()->lookup("Length", &obj1);
        assert(!obj1->isNull());
        pdf_puts("/Length ");
        copyObject(&obj1);
        pdf_puts("\n");
        contents->streamGetDict()->lookup("Filter", &obj1);
        if (!obj1->isNull()) {
            pdf_puts("/Filter ");
            copyObject(&obj1);
            pdf_puts("\n");
            contents->streamGetDict()->lookup("DecodeParms", &obj1);
            if (!obj1->isNull()) {
                pdf_puts("/DecodeParms ");
                copyObject(&obj1);
                pdf_puts("\n");
            }
        }
        pdf_puts(">>\nstream\n");
        copyStream(contents->getStream()->getUndecodedStream());
        pdfendstream();
    } else if (contents->isArray()) {
        pdfbeginstream();
        for (i = 0, l = contents->arrayGetLength(); i < l; ++i) {
            Object contentsobj;
            copyStream((contents->arrayGet(i, &contentsobj))->getStream());
            contentsobj.free();
            if (i < l - 1)
                pdf_newline();  // add a newline after each stream except the last
        }
        pdfendstream();
    } else {                    // the contents are optional, but we need to include an empty stream
        pdfbeginstream();
        pdfendstream();
    }

    // write out all indirect objects
    writeRefs();

    // write out all used encodings (and delete list)
    writeEncodings();

    // write the Group dict if needed
    if (writeSepGroup) {
        pdfbeginobj(pdfpagegroupval, 2);
        copyObject(&groupDict);
        pdf_puts("\n");
        pdfendobj();
        pdfpagegroupval = 0;    // only the 1st included pdf on a page gets its
                                // Group included in the Page dict
    }

    // save object list, xref
    pdf_doc->inObjList = inObjList;
    pdf_doc->xref = xref;
}

// Called when an image has been written and it's resources in image_tab are
// freed and it's not referenced anymore.

void epdf_delete()
{
    PdfDocument *pdf_doc = (PdfDocument *) epdf_doc;
    xref = pdf_doc->xref;
    if (pdf_doc->occurences < 0) {
        delete_document(pdf_doc);
    }
}

// Called when PDF embedding system is finalized.
// Now deallocate all remaining PdfDocuments.

void epdf_check_mem()
{
    if (isInit) {
        PdfDocument *p, *n;
        for (p = pdfDocuments; p; p = n) {
            n = p->next;
            delete_document(p);
        }
        // see above for globalParams
        delete globalParams;
    }
}