-
Notifications
You must be signed in to change notification settings - Fork 0
/
reader.go
718 lines (624 loc) · 21.2 KB
/
reader.go
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
/*
* This file is subject to the terms and conditions defined in
* file 'LICENSE.md', which is part of this source code package.
*/
package model
import (
"errors"
"fmt"
"io"
"strings"
"github.com/xwc1125/gopdf/common"
"github.com/xwc1125/gopdf/core"
"github.com/xwc1125/gopdf/core/security"
)
// PdfReader represents a PDF file reader. It is a frontend to the lower level parsing mechanism and provides
// a higher level access to work with PDF structure and information, such as the page structure etc.
type PdfReader struct {
parser *core.PdfParser
root core.PdfObject
pagesContainer *core.PdfIndirectObject
pages *core.PdfObjectDictionary
pageList []*core.PdfIndirectObject
PageList []*PdfPage
pageCount int
catalog *core.PdfObjectDictionary
outlineTree *PdfOutlineTreeNode
AcroForm *PdfAcroForm
modelManager *modelManager
// Lazy loading: When enabled reference objects need to be resolved (via lookup, disk access) rather
// than loading entire document into memory on load.
isLazy bool
// For tracking traversal (cache).
traversed map[core.PdfObject]struct{}
rs io.ReadSeeker
}
// NewPdfReader returns a new PdfReader for an input io.ReadSeeker interface. Can be used to read PDF from
// memory or file. Immediately loads and traverses the PDF structure including pages and page contents (if
// not encrypted). Loads entire document structure into memory.
// Alternatively a lazy-loading reader can be created with NewPdfReaderLazy which loads only references,
// and references are loaded from disk into memory on an as-needed basis.
func NewPdfReader(rs io.ReadSeeker) (*PdfReader, error) {
pdfReader := &PdfReader{
rs: rs,
traversed: map[core.PdfObject]struct{}{},
modelManager: newModelManager(),
isLazy: false,
}
// Create the parser, loads the cross reference table and trailer.
parser, err := core.NewParser(rs)
if err != nil {
return nil, err
}
pdfReader.parser = parser
isEncrypted, err := pdfReader.IsEncrypted()
if err != nil {
return nil, err
}
// Load pdf doc structure if not encrypted.
if !isEncrypted {
err = pdfReader.loadStructure()
if err != nil {
return nil, err
}
}
return pdfReader, nil
}
// NewPdfReaderLazy creates a new PdfReader for `rs` in lazy-loading mode. The difference
// from NewPdfReader is that in lazy-loading mode, objects are only loaded into memory when needed
// rather than entire structure being loaded into memory on reader creation.
// Note that it may make sense to use the lazy-load reader when processing only parts of files,
// rather than loading entire file into memory. Example: splitting a few pages from a large PDF file.
func NewPdfReaderLazy(rs io.ReadSeeker) (*PdfReader, error) {
pdfReader := &PdfReader{
rs: rs,
traversed: map[core.PdfObject]struct{}{},
modelManager: newModelManager(),
isLazy: true,
}
// Create the parser, loads the cross reference table and trailer.
parser, err := core.NewParser(rs)
if err != nil {
return nil, err
}
pdfReader.parser = parser
isEncrypted, err := pdfReader.IsEncrypted()
if err != nil {
return nil, err
}
// Load pdf doc structure if not encrypted.
if !isEncrypted {
err = pdfReader.loadStructure()
if err != nil {
return nil, err
}
}
return pdfReader, nil
}
// PdfVersion returns version of the PDF file.
func (r *PdfReader) PdfVersion() core.Version {
return r.parser.PdfVersion()
}
// IsEncrypted returns true if the PDF file is encrypted.
func (r *PdfReader) IsEncrypted() (bool, error) {
return r.parser.IsEncrypted()
}
// GetEncryptionMethod returns a descriptive information string about the encryption method used.
func (r *PdfReader) GetEncryptionMethod() string {
crypter := r.parser.GetCrypter()
return crypter.String()
}
// Decrypt decrypts the PDF file with a specified password. Also tries to
// decrypt with an empty password. Returns true if successful,
// false otherwise.
func (r *PdfReader) Decrypt(password []byte) (bool, error) {
success, err := r.parser.Decrypt(password)
if err != nil {
return false, err
}
if !success {
return false, nil
}
err = r.loadStructure()
if err != nil {
common.Log.Debug("ERROR: Fail to load structure (%s)", err)
return false, err
}
return true, nil
}
// CheckAccessRights checks access rights and permissions for a specified password. If either user/owner
// password is specified, full rights are granted, otherwise the access rights are specified by the
// Permissions flag.
//
// The bool flag indicates that the user can access and view the file.
// The AccessPermissions shows what access the user has for editing etc.
// An error is returned if there was a problem performing the authentication.
func (r *PdfReader) CheckAccessRights(password []byte) (bool, security.Permissions, error) {
return r.parser.CheckAccessRights(password)
}
// Loads the structure of the pdf file: pages, outlines, etc.
func (r *PdfReader) loadStructure() error {
if r.parser.GetCrypter() != nil && !r.parser.IsAuthenticated() {
return fmt.Errorf("file need to be decrypted first")
}
trailerDict := r.parser.GetTrailer()
if trailerDict == nil {
return fmt.Errorf("missing trailer")
}
// Catalog.
root, ok := trailerDict.Get("Root").(*core.PdfObjectReference)
if !ok {
return fmt.Errorf("invalid Root (trailer: %s)", trailerDict)
}
oc, err := r.parser.LookupByReference(*root)
if err != nil {
common.Log.Debug("ERROR: Failed to read root element catalog: %s", err)
return err
}
pcatalog, ok := oc.(*core.PdfIndirectObject)
if !ok {
common.Log.Debug("ERROR: Missing catalog: (root %q) (trailer %s)", oc, *trailerDict)
return errors.New("missing catalog")
}
catalog, ok := (*pcatalog).PdfObject.(*core.PdfObjectDictionary)
if !ok {
common.Log.Debug("ERROR: Invalid catalog (%s)", pcatalog.PdfObject)
return errors.New("invalid catalog")
}
common.Log.Trace("Catalog: %s", catalog)
// Pages.
pagesRef, ok := catalog.Get("Pages").(*core.PdfObjectReference)
if !ok {
return errors.New("pages in catalog should be a reference")
}
op, err := r.parser.LookupByReference(*pagesRef)
if err != nil {
common.Log.Debug("ERROR: Failed to read pages")
return err
}
ppages, ok := op.(*core.PdfIndirectObject)
if !ok {
common.Log.Debug("ERROR: Pages object invalid")
common.Log.Debug("op: %p", ppages)
return errors.New("pages object invalid")
}
pages, ok := ppages.PdfObject.(*core.PdfObjectDictionary)
if !ok {
common.Log.Debug("ERROR: Pages object invalid (%s)", ppages)
return errors.New("pages object invalid")
}
pageCount, ok := core.GetInt(pages.Get("Count"))
if !ok {
common.Log.Debug("ERROR: Pages count object invalid")
return errors.New("pages count invalid")
}
if _, ok = core.GetName(pages.Get("Type")); !ok {
common.Log.Debug("Pages dict Type field not set. Setting Type to Pages.")
pages.Set("Type", core.MakeName("Pages"))
}
r.root = root
r.catalog = catalog
r.pages = pages
r.pagesContainer = ppages
r.pageCount = int(*pageCount)
r.pageList = []*core.PdfIndirectObject{}
traversedPageNodes := map[core.PdfObject]struct{}{}
err = r.buildPageList(ppages, nil, traversedPageNodes)
if err != nil {
return err
}
common.Log.Trace("---")
common.Log.Trace("TOC")
common.Log.Trace("Pages")
common.Log.Trace("%d: %s", len(r.pageList), r.pageList)
// Outlines.
r.outlineTree, err = r.loadOutlines()
if err != nil {
common.Log.Debug("ERROR: Failed to build outline tree (%s)", err)
return err
}
// Load interactive forms and fields.
r.AcroForm, err = r.loadForms()
if err != nil {
return err
}
return nil
}
func (r *PdfReader) loadOutlines() (*PdfOutlineTreeNode, error) {
if r.parser.GetCrypter() != nil && !r.parser.IsAuthenticated() {
return nil, fmt.Errorf("file need to be decrypted first")
}
// Has outlines? Otherwise return an empty outlines structure.
catalog := r.catalog
outlinesObj := catalog.Get("Outlines")
if outlinesObj == nil {
return nil, nil
}
common.Log.Trace("-Has outlines")
// Trace references to the object.
outlineRootObj := core.ResolveReference(outlinesObj)
common.Log.Trace("Outline root: %v", outlineRootObj)
if _, isNull := outlineRootObj.(*core.PdfObjectNull); isNull {
common.Log.Trace("Outline root is null - no outlines")
return nil, nil
}
outlineRoot, ok := outlineRootObj.(*core.PdfIndirectObject)
if !ok {
if _, ok := core.GetDict(outlineRootObj); !ok {
common.Log.Debug("Invalid outline root - skipping")
return nil, nil
}
common.Log.Debug("Outline root is a dict. Should be an indirect object")
outlineRoot = core.MakeIndirectObject(outlineRootObj)
}
dict, ok := outlineRoot.PdfObject.(*core.PdfObjectDictionary)
if !ok {
return nil, errors.New("outline indirect object should contain a dictionary")
}
common.Log.Trace("Outline root dict: %v", dict)
outlineTree, _, err := r.buildOutlineTree(outlineRoot, nil, nil)
if err != nil {
return nil, err
}
common.Log.Trace("Resulting outline tree: %v", outlineTree)
return outlineTree, nil
}
// Recursive build outline tree.
// prev PdfObject,
// Input: The indirect object containing an Outlines or Outline item dictionary.
// Parent, Prev are the parent or previous node in the hierarchy.
// The function returns the corresponding tree node and the last node which is used
// for setting the Last pointer of the tree node structures.
func (r *PdfReader) buildOutlineTree(obj core.PdfObject, parent *PdfOutlineTreeNode, prev *PdfOutlineTreeNode) (*PdfOutlineTreeNode, *PdfOutlineTreeNode, error) {
container, isInd := obj.(*core.PdfIndirectObject)
if !isInd {
return nil, nil, fmt.Errorf("outline container not an indirect object %T", obj)
}
dict, ok := container.PdfObject.(*core.PdfObjectDictionary)
if !ok {
return nil, nil, errors.New("not a dictionary object")
}
common.Log.Trace("build outline tree: dict: %v (%v) p: %p", dict, container, container)
if obj := dict.Get("Title"); obj != nil {
// Outline item has a title. (required)
outlineItem, err := r.newPdfOutlineItemFromIndirectObject(container)
if err != nil {
return nil, nil, err
}
outlineItem.Parent = parent
outlineItem.Prev = prev
if firstObj := dict.Get("First"); firstObj != nil {
firstObj = core.ResolveReference(firstObj)
if !core.IsNullObject(firstObj) {
first, last, err := r.buildOutlineTree(firstObj, &outlineItem.PdfOutlineTreeNode, nil)
if err != nil {
common.Log.Debug("DEBUG: could not build outline item tree: %v. Skipping node children.", err)
} else {
outlineItem.First = first
outlineItem.Last = last
}
}
}
// Resolve the reference to next
if nextObj := dict.Get("Next"); nextObj != nil {
nextObj = core.ResolveReference(nextObj)
if _, isNull := nextObj.(*core.PdfObjectNull); !isNull {
next, last, err := r.buildOutlineTree(nextObj, parent, &outlineItem.PdfOutlineTreeNode)
if err != nil {
common.Log.Debug("DEBUG: could not build outline tree for Next node: %v. Skipping node.", err)
} else {
outlineItem.Next = next
return &outlineItem.PdfOutlineTreeNode, last, nil
}
}
}
return &outlineItem.PdfOutlineTreeNode, &outlineItem.PdfOutlineTreeNode, nil
}
// Outline dictionary (structure element).
outline, err := newPdfOutlineFromIndirectObject(container)
if err != nil {
return nil, nil, err
}
outline.Parent = parent
if firstObj := dict.Get("First"); firstObj != nil {
// Has children...
firstObj = core.ResolveReference(firstObj)
firstObjDirect := core.TraceToDirectObject(firstObj)
if _, isNull := firstObjDirect.(*core.PdfObjectNull); !isNull && firstObjDirect != nil {
first, last, err := r.buildOutlineTree(firstObj, &outline.PdfOutlineTreeNode, nil)
if err != nil {
common.Log.Debug("DEBUG: could not build outline tree: %v. Skipping node children.", err)
} else {
outline.First = first
outline.Last = last
}
}
}
return &outline.PdfOutlineTreeNode, &outline.PdfOutlineTreeNode, nil
}
// GetOutlineTree returns the outline tree.
func (r *PdfReader) GetOutlineTree() *PdfOutlineTreeNode {
return r.outlineTree
}
// GetOutlinesFlattened returns a flattened list of tree nodes and titles.
func (r *PdfReader) GetOutlinesFlattened() ([]*PdfOutlineTreeNode, []string, error) {
var outlineNodeList []*PdfOutlineTreeNode
var flattenedTitleList []string
// Recursive flattening function.
var flattenFunc func(*PdfOutlineTreeNode, *[]*PdfOutlineTreeNode, *[]string, int)
flattenFunc = func(node *PdfOutlineTreeNode, outlineList *[]*PdfOutlineTreeNode, titleList *[]string, depth int) {
if node == nil {
return
}
if node.context == nil {
common.Log.Debug("ERROR: Missing node.context") // Should not happen ever.
return
}
if item, isItem := node.context.(*PdfOutlineItem); isItem {
*outlineList = append(*outlineList, &item.PdfOutlineTreeNode)
title := strings.Repeat(" ", depth*2) + item.Title.Str()
*titleList = append(*titleList, title)
if item.Next != nil {
flattenFunc(item.Next, outlineList, titleList, depth)
}
}
if node.First != nil {
title := strings.Repeat(" ", depth*2) + "+"
*titleList = append(*titleList, title)
flattenFunc(node.First, outlineList, titleList, depth+1)
}
}
flattenFunc(r.outlineTree, &outlineNodeList, &flattenedTitleList, 0)
return outlineNodeList, flattenedTitleList, nil
}
// loadForms loads the AcroForm.
func (r *PdfReader) loadForms() (*PdfAcroForm, error) {
if r.parser.GetCrypter() != nil && !r.parser.IsAuthenticated() {
return nil, fmt.Errorf("file need to be decrypted first")
}
// Has forms?
catalog := r.catalog
obj := catalog.Get("AcroForm")
if obj == nil {
// Nothing to load.
return nil, nil
}
formsContainer, _ := core.GetIndirect(obj)
obj = core.TraceToDirectObject(obj)
if core.IsNullObject(obj) {
common.Log.Trace("Acroform is a null object (empty)\n")
return nil, nil
}
formsDict, ok := core.GetDict(obj)
if !ok {
common.Log.Debug("Invalid AcroForm entry %T", obj)
common.Log.Debug("Does not have forms")
return nil, fmt.Errorf("invalid acroform entry %T", obj)
}
common.Log.Trace("Has Acro forms")
// Load it.
// Ensure we have access to everything.
common.Log.Trace("Traverse the Acroforms structure")
if !r.isLazy {
err := r.traverseObjectData(formsDict)
if err != nil {
common.Log.Debug("ERROR: Unable to traverse AcroForms (%s)", err)
return nil, err
}
}
// Create the acro forms object.
acroForm, err := r.newPdfAcroFormFromDict(formsContainer, formsDict)
if err != nil {
return nil, err
}
return acroForm, nil
}
func (r *PdfReader) lookupPageByObject(obj core.PdfObject) (*PdfPage, error) {
// can be indirect, direct, or reference
// look up the corresponding page
return nil, errors.New("page not found")
}
// Build the table of contents.
// tree, ex: Pages -> Pages -> Pages -> Page
// Traverse through the whole thing recursively.
func (r *PdfReader) buildPageList(node *core.PdfIndirectObject, parent *core.PdfIndirectObject, traversedPageNodes map[core.PdfObject]struct{}) error {
if node == nil {
return nil
}
if _, alreadyTraversed := traversedPageNodes[node]; alreadyTraversed {
common.Log.Debug("Cyclic recursion, skipping (%v)", node.ObjectNumber)
return nil
}
traversedPageNodes[node] = struct{}{}
nodeDict, ok := node.PdfObject.(*core.PdfObjectDictionary)
if !ok {
return errors.New("node not a dictionary")
}
objType, ok := (*nodeDict).Get("Type").(*core.PdfObjectName)
if !ok {
if nodeDict.Get("Kids") == nil {
return errors.New("node missing Type (Required)")
}
common.Log.Debug("ERROR: node missing Type, but has Kids. Assuming Pages node.")
objType = core.MakeName("Pages")
nodeDict.Set("Type", objType)
}
common.Log.Trace("buildPageList node type: %s (%+v)", *objType, node)
if *objType == "Page" {
p, err := r.newPdfPageFromDict(nodeDict)
if err != nil {
return err
}
p.setContainer(node)
if parent != nil {
// Set the parent (in case missing or incorrect).
nodeDict.Set("Parent", parent)
}
r.pageList = append(r.pageList, node)
r.PageList = append(r.PageList, p)
return nil
}
if *objType != "Pages" {
common.Log.Debug("ERROR: Table of content containing non Page/Pages object! (%s)", objType)
return errors.New("table of content containing non Page/Pages object")
}
// A Pages object. Update the parent.
if parent != nil {
nodeDict.Set("Parent", parent)
}
// Resolve the object recursively.
if !r.isLazy {
err := r.traverseObjectData(node)
if err != nil {
return err
}
}
kidsObj, err := r.parser.Resolve(nodeDict.Get("Kids"))
if err != nil {
common.Log.Debug("ERROR: Failed loading Kids object")
return err
}
var kids *core.PdfObjectArray
kids, ok = kidsObj.(*core.PdfObjectArray)
if !ok {
kidsIndirect, isIndirect := kidsObj.(*core.PdfIndirectObject)
if !isIndirect {
return errors.New("invalid Kids object")
}
kids, ok = kidsIndirect.PdfObject.(*core.PdfObjectArray)
if !ok {
return errors.New("invalid Kids indirect object")
}
}
common.Log.Trace("Kids: %s", kids)
for idx, child := range kids.Elements() {
child, ok := core.GetIndirect(child)
if !ok {
common.Log.Debug("ERROR: Page not indirect object - (%s)", child)
return errors.New("page not indirect object")
}
kids.Set(idx, child)
err = r.buildPageList(child, node, traversedPageNodes)
if err != nil {
return err
}
}
return nil
}
// GetNumPages returns the number of pages in the document.
func (r *PdfReader) GetNumPages() (int, error) {
if r.parser.GetCrypter() != nil && !r.parser.IsAuthenticated() {
return 0, fmt.Errorf("file need to be decrypted first")
}
return len(r.pageList), nil
}
// Resolves a reference, returning the object and indicates whether or not
// it was cached.
func (r *PdfReader) resolveReference(ref *core.PdfObjectReference) (core.PdfObject, bool, error) {
cachedObj, isCached := r.parser.ObjCache[int(ref.ObjectNumber)]
if !isCached {
common.Log.Trace("Reader Lookup ref: %s", ref)
obj, err := r.parser.LookupByReference(*ref)
if err != nil {
return nil, false, err
}
r.parser.ObjCache[int(ref.ObjectNumber)] = obj
return obj, false, nil
}
return cachedObj, true, nil
}
/*
* Recursively traverse through the page object data and look up
* references to indirect objects.
*
* GH: Are we fully protected against circular references? (Add tests).
*/
func (r *PdfReader) traverseObjectData(o core.PdfObject) error {
return core.ResolveReferencesDeep(o, r.traversed)
}
// PageFromIndirectObject returns the PdfPage and page number for a given indirect object.
func (r *PdfReader) PageFromIndirectObject(ind *core.PdfIndirectObject) (*PdfPage, int, error) {
if len(r.PageList) != len(r.pageList) {
return nil, 0, errors.New("page list invalid")
}
for i, pageind := range r.pageList {
if pageind == ind {
return r.PageList[i], i + 1, nil
}
}
return nil, 0, errors.New("page not found")
}
// GetPage returns the PdfPage model for the specified page number.
func (r *PdfReader) GetPage(pageNumber int) (*PdfPage, error) {
if r.parser.GetCrypter() != nil && !r.parser.IsAuthenticated() {
return nil, fmt.Errorf("file needs to be decrypted first")
}
if len(r.pageList) < pageNumber {
return nil, errors.New("invalid page number (page count too short)")
}
idx := pageNumber - 1
if idx < 0 {
return nil, fmt.Errorf("page numbering must start at 1")
}
page := r.PageList[idx]
return page, nil
}
// GetOCProperties returns the optional content properties PdfObject.
func (r *PdfReader) GetOCProperties() (core.PdfObject, error) {
dict := r.catalog
obj := dict.Get("OCProperties")
obj = core.ResolveReference(obj)
// Resolve all references...
// Should be pretty safe. Should not be referencing to pages or
// any large structures. Local structures and references
// to OC Groups.
if !r.isLazy {
err := r.traverseObjectData(obj)
if err != nil {
return nil, err
}
}
return obj, nil
}
// GetNamedDestinations returns the Names entry in the PDF catalog.
// See section 12.3.2.3 "Named Destinations" (p. 367 PDF32000_2008).
func (r *PdfReader) GetNamedDestinations() (core.PdfObject, error) {
obj := core.ResolveReference(r.catalog.Get("Names"))
if obj == nil {
return nil, nil
}
// Resolve references.
if !r.isLazy {
err := r.traverseObjectData(obj)
if err != nil {
return nil, err
}
}
return obj, nil
}
// Inspect inspects the object types, subtypes and content in the PDF file returning a map of
// object type to number of instances of each.
func (r *PdfReader) Inspect() (map[string]int, error) {
return r.parser.Inspect()
}
// GetObjectNums returns the object numbers of the PDF objects in the file
// Numbered objects are either indirect objects or stream objects.
// e.g. objNums := pdfReader.GetObjectNums()
// The underlying objects can then be accessed with
// pdfReader.GetIndirectObjectByNumber(objNums[0]) for the first available object.
func (r *PdfReader) GetObjectNums() []int {
return r.parser.GetObjectNums()
}
// GetIndirectObjectByNumber retrieves and returns a specific PdfObject by object number.
func (r *PdfReader) GetIndirectObjectByNumber(number int) (core.PdfObject, error) {
obj, err := r.parser.LookupByNumber(number)
return obj, err
}
// GetTrailer returns the PDF's trailer dictionary.
func (r *PdfReader) GetTrailer() (*core.PdfObjectDictionary, error) {
trailerDict := r.parser.GetTrailer()
if trailerDict == nil {
return nil, errors.New("trailer missing")
}
return trailerDict, nil
}