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
|
"""Test the pypdf._doc_common module."""
import itertools
import re
import shutil
import subprocess
from io import BytesIO
from operator import itemgetter
from pathlib import Path
from unittest import mock
import pytest
from pypdf import PdfReader, PdfWriter
from pypdf.errors import LimitReachedError, PdfReadError
from pypdf.filters import FlateDecode
from pypdf.generic import (
ArrayObject,
DictionaryObject,
EmbeddedFile,
EncodedStreamObject,
NameObject,
NullObject,
TextStringObject,
ViewerPreferences,
)
from tests import RESOURCE_ROOT, SAMPLE_ROOT, get_data_from_url
PDFATTACH_BINARY = shutil.which("pdfattach")
@pytest.mark.skipif(PDFATTACH_BINARY is None, reason="Requires poppler-utils")
def test_attachments(tmpdir):
tmpdir = Path(tmpdir)
# No attachments.
clean_path = SAMPLE_ROOT / "002-trivial-libre-office-writer" / "002-trivial-libre-office-writer.pdf"
with PdfReader(clean_path) as pdf:
assert pdf._list_attachments() == []
assert list(pdf.attachment_list) == []
# UF = name.
attached_path = tmpdir / "attached.pdf"
file_path = tmpdir / "test.txt"
file_path.write_bytes(b"Hello World\n")
subprocess.run([PDFATTACH_BINARY, clean_path, file_path, attached_path]) # noqa: S603
with PdfReader(attached_path) as pdf:
assert pdf._list_attachments() == ["test.txt"]
assert pdf._get_attachments("test.txt") == {"test.txt": b"Hello World\n"}
assert [(x.name, x.content) for x in pdf.attachment_list] == [("test.txt", b"Hello World\n")]
assert next(pdf.attachment_list).alternative_name == "test.txt"
# UF != name.
different_path = tmpdir / "different.pdf"
different_path.write_bytes(re.sub(rb" /UF [^/]+ /", b" /UF(my-file.txt) /", attached_path.read_bytes()))
with PdfReader(different_path) as pdf:
assert pdf._list_attachments() == ["test.txt", "my-file.txt"]
assert pdf._get_attachments("test.txt") == {"test.txt": b"Hello World\n"}
assert pdf._get_attachments("my-file.txt") == {"my-file.txt": b"Hello World\n"}
assert [(x.name, x.content) for x in pdf.attachment_list] == [("test.txt", b"Hello World\n")]
assert next(pdf.attachment_list).alternative_name == "my-file.txt"
# Only name.
no_f_path = tmpdir / "no-f.pdf"
no_f_path.write_bytes(re.sub(rb" /UF [^/]+ /", b" /", attached_path.read_bytes()))
with PdfReader(no_f_path) as pdf:
assert pdf._list_attachments() == ["test.txt"]
assert pdf._get_attachments("test.txt") == {"test.txt": b"Hello World\n"}
assert [(x.name, x.content) for x in pdf.attachment_list] == [("test.txt", b"Hello World\n")]
assert next(pdf.attachment_list).alternative_name is None
# UF and F.
uf_f_path = tmpdir / "uf-f.pdf"
uf_f_path.write_bytes(attached_path.read_bytes().replace(b" /UF ", b"/F(file.txt) /UF "))
with PdfReader(uf_f_path) as pdf:
assert pdf._list_attachments() == ["test.txt"]
assert pdf._get_attachments("test.txt") == {"test.txt": b"Hello World\n"}
assert [(x.name, x.content) for x in pdf.attachment_list] == [("test.txt", b"Hello World\n")]
assert next(pdf.attachment_list).alternative_name == "test.txt"
# Only F.
only_f_path = tmpdir / "f.pdf"
only_f_path.write_bytes(attached_path.read_bytes().replace(b" /UF ", b" /F "))
with PdfReader(only_f_path) as pdf:
assert pdf._list_attachments() == ["test.txt"]
assert pdf._get_attachments("test.txt") == {"test.txt": b"Hello World\n"}
assert [(x.name, x.content) for x in pdf.attachment_list] == [("test.txt", b"Hello World\n")]
assert next(pdf.attachment_list).alternative_name == "test.txt"
def test_get_attachments__same_attachment_more_than_twice():
writer = PdfWriter()
writer.add_blank_page(100, 100)
for i in range(5):
writer.add_attachment("test.txt", f"content{i}")
assert writer._get_attachments("test.txt") == {
"test.txt": [b"content0", b"content1", b"content2", b"content3", b"content4"]
}
assert [(x.name, x.content) for x in writer.attachment_list] == [
("test.txt", b"content0"),
("test.txt", b"content1"),
("test.txt", b"content2"),
("test.txt", b"content3"),
("test.txt", b"content4"),
]
def test_get_attachments__alternative_name_is_none():
writer = PdfWriter()
attachment = EmbeddedFile(name="test.txt", pdf_object=writer.root_object)
assert attachment.alternative_name is None
with mock.patch(
"pypdf._writer.PdfWriter.attachment_list",
new_callable=mock.PropertyMock(return_value=[attachment])
), mock.patch(
"pypdf.generic._files.EmbeddedFile.content",
new_callable=mock.PropertyMock(return_value=b"content")
):
assert writer._get_attachments() == {"test.txt": b"content"}
@pytest.mark.enable_socket
def test_byte_encoded_named_destinations():
url = "https://github.com/user-attachments/files/19820164/pypdf_issue.pdf"
name = "issue3261.pdf"
reader = PdfReader(BytesIO(get_data_from_url(url=url, name=name)))
page = reader.pages[0]
for annotation in page.annotations:
if annotation.get("/Subtype") == "/Link":
action = annotation["/A"]
if action["/S"] == "/GoTo":
named_dest = action["/D"]
assert str(named_dest) in reader.named_destinations
assert TextStringObject(named_dest) in reader.named_destinations
assert reader.named_destinations == {
"Doc-Start": {
"/Title": "Doc-Start",
"/Page": page.indirect_reference,
"/Type": "/XYZ",
"/Left": 133.768,
"/Top": 667.198,
"/Zoom": NullObject()
},
"cite.dacÃ\xadk2025racerflightweightstaticdata": {
"/Title": "cite.dacÃ\xadk2025racerflightweightstaticdata",
"/Page": page.indirect_reference,
"/Type": "/XYZ",
"/Left": 133.768,
"/Top": 614.424,
"/Zoom": NullObject()
},
# This is the same as the previous entry, but with `str(name)` instead of the title.
"楣整搮捡귃㉫㈰爵捡牥汦杩瑨敷杩瑨瑳瑡捩慤慴": {
"/Left": 133.768,
"/Page": page.indirect_reference,
"/Title": "cite.dacÃ\xadk2025racerflightweightstaticdata",
"/Top": 614.424,
"/Type": "/XYZ",
"/Zoom": NullObject()
},
"page.1": {
"/Title": "page.1",
"/Page": page.indirect_reference,
"/Type": "/XYZ",
"/Left": 132.768,
"/Top": 705.06,
"/Zoom": NullObject()
},
"section*.1": {
"/Title": "section*.1",
"/Page": page.indirect_reference,
"/Type": "/XYZ",
"/Left": 133.768,
"/Top": 642.222,
"/Zoom": NullObject()
}
}
def test_viewer_preferences__indirect_reference():
input_path = RESOURCE_ROOT / "git.pdf"
reader = PdfReader(input_path)
assert (0, 24) not in reader.resolved_objects
viewer_preferences = reader.viewer_preferences
assert isinstance(viewer_preferences, ViewerPreferences)
assert viewer_preferences == {"/DisplayDocTitle": True}
assert (0, 24) in reader.resolved_objects
assert id(viewer_preferences) == id(reader.viewer_preferences)
assert id(viewer_preferences) == id(reader.resolved_objects[(0, 24)])
@pytest.mark.enable_socket
def test_named_destinations__tree_is_null_object():
url = "https://github.com/user-attachments/files/20885216/test.pdf"
name = "issue3330.pdf"
reader = PdfReader(BytesIO(get_data_from_url(url=url, name=name)))
assert reader.named_destinations == {}
@pytest.mark.enable_socket
def test_outline__issue3462():
url = "https://github.com/user-attachments/files/22293402/e371fffe0b_a7cccde95a.pdf"
name = "issue3462.pdf"
reader = PdfReader(BytesIO(get_data_from_url(url=url, name=name)))
outline_flat = list(
itertools.chain.from_iterable(
entry if isinstance(entry, list) else [entry] for entry in reader.outline
)
)
assert list(map(itemgetter("/Title"), outline_flat)) == [
"AR 2021 - Daftar Isi",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"AR 2021 Book 001 (Highlights - Ikhtisar Saham)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"AR 2021 Book 002 (Laporan Manajemen)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"Page 7",
"Page 8",
"Page 9",
"AR 2021 Book 003-1 (Profil Perusahaan)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"Page 7",
"Page 8",
"Page 9",
"Page 10",
"Page 11",
"Page 12",
"Page 13",
"Page 14",
"Page 15",
"Page 16",
"Page 17",
"Page 18",
"Page 19",
"Page 20",
"Page 21",
"Page 22",
"Page 23",
"Page 24",
"Page 25",
"Page 26",
"Page 27",
"Page 28",
"Page 29",
"Page 30",
"Page 31",
"Page 32",
"Page 33",
"Page 34",
"Page 35",
"Page 36",
"Page 37",
"Page 38",
"Page 39",
"Page 40",
"Page 41",
"Page 42",
"Page 43",
"Page 44",
"Page 45",
"Page 46",
"Page 47",
"AR 2021 Book 003-2 (Sumber Daya Manusia)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"Page 7",
"Page 8",
"Page 9",
"Page 10",
"Page 11",
"Page 12",
"AR 2021 Book 003-3 (Komposisi pemegang saham)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"AR 2021 Book 003-4 (Kronologis Pencatatan Saham)",
"Page 1",
"Page 2",
"AR 2021 Book 003-5 (Akuntan Publik Independen)",
"Page 1",
"Page 2",
"Page 3",
"AR 2021 Book 004 (Analisa dan Pembahasan Manajemen)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"Page 7",
"Page 8",
"Page 9",
"Page 10",
"Page 11",
"Page 12",
"Page 13",
"Page 14",
"Page 15",
"Page 16",
"Page 17",
"Page 18",
"Page 19",
"Page 20",
"Page 21",
"AR 2021 Book 005-1 (Tata Kelola Perusahaan)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"Page 7",
"Page 8",
"Page 9",
"Page 10",
"Page 11",
"Page 12",
"AR 2021 Book 005-2 (Direksi-Komisaris)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"Page 7",
"Page 8",
"Page 9",
"Page 10",
"Page 11",
"Page 12",
"Page 13",
"Page 14",
"Page 15",
"Page 16",
"Page 17",
"Page 18",
"Page 19",
"Page 20",
"Page 21",
"Page 22",
"Page 23",
"Page 24",
"Page 25",
"Page 26",
"Page 27",
"Page 28",
"Page 29",
"Page 30",
"Page 31",
"Page 32",
"Page 33",
"Page 34",
"Page 35",
"Page 36",
"Page 37",
"Page 38",
"AR 2021 Book 005-3 (Komite Audit)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"Page 7",
"Page 8",
"Page 9",
"AR 2021 Book 005-4 (Sekretaris Perusahaan)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"Page 7",
"Page 8",
"Page 9",
"Page 10",
"AR 2021 Book 005-5 (Unit Audit Internal)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"AR 2021 Book 005-6 (Sistem Pengendalian Internal)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"Page 7",
"Page 8",
"AR 2021 Book 005-7 (Program Saham)",
"Page 1",
"AR 2021 Book 005-8 ( Whistleblowing)",
"Page 1",
"Page 2",
"Page 3",
"Page 4",
"Page 5",
"Page 6",
"Page 7",
"Page 8",
"Page 9",
"Page 10",
"Page 11",
"Page 12",
"Page 13",
"Page 14",
"Page 15",
"Page 16",
"Page 17",
"Page 18",
"Page 19",
"Page 20",
"Page 21",
"Page 22",
"Page 23",
"Page 24",
"Page 25",
"AR 2021 Book 006 (Tanggung Jawab Sosial - CSR)",
"Page 1",
"Page 2",
"AR 2021 Book 007-1 (LAPORAN KEUANGAN KONSOLIDASIAN)",
"Page 1",
"AR 2021 Book 007-2 (Isi Laporan Keuangan)",
"AR 2021 Book 008 (Tanggung Jawab Atas Laporan Tahunan)",
"Page 1",
"Page 2"
]
def test_flatten__cyclic_references():
path = RESOURCE_ROOT / "crazyones.pdf"
reader = PdfReader(path)
assert len(reader.pages) == 1
reader._flatten()
# Make the first child point to the object itself.
pages_object = reader.get_object(10)
pages_object[NameObject("/Kids")][0].indirect_reference.idnum = 10
reader.resolved_objects[(10, 0)] = pages_object
with pytest.raises(expected_exception=PdfReadError, match=r"^Detected cyclic page references\.$"):
reader._flatten()
@pytest.mark.enable_socket
@pytest.mark.timeout(10)
def test_get_outline__cyclic_references(caplog):
url = "https://github.com/user-attachments/files/24859044/circular_outline.pdf"
name = "circular_outline.pdf"
reader = PdfReader(BytesIO(get_data_from_url(url=url, name=name)))
assert reader.outline == [
{
"/%is_open%": True,
"/Page": reader.pages[0].indirect_reference,
"/Title": "Bookmark A",
"/Type": "/Fit"
},
{
"/%is_open%": True,
"/Page": reader.pages[0].indirect_reference,
"/Title": "Bookmark B",
"/Type": "/Fit"
}
]
assert caplog.messages[0].startswith("Detected cycle in outline structure for {")
@pytest.mark.enable_socket
@pytest.mark.timeout(10)
def test_get_outline__cyclic_references__nested_handling(caplog):
url = "https://github.com/user-attachments/files/24859044/circular_outline.pdf"
name = "circular_outline.pdf"
writer = PdfWriter(clone_from=BytesIO(get_data_from_url(url=url, name=name)))
nested_outline = DictionaryObject()
writer._add_object(nested_outline)
nested_outline.update({
NameObject("/Title"): TextStringObject("Nested entry"),
NameObject("/Parent"): writer.get_object(5),
NameObject("/Dest"): ArrayObject([writer.pages[0].indirect_reference, NameObject("/Fit")]),
NameObject("/Next"): writer.get_object(6),
})
writer.get_object(5)[NameObject("/First")] = nested_outline.indirect_reference
writer.get_object(6)[NameObject("/First")] = nested_outline.indirect_reference
assert writer.outline == [
{
"/%is_open%": True,
"/Page": writer.pages[0].indirect_reference,
"/Title": "Bookmark A",
"/Type": "/Fit"
},
[
{
"/%is_open%": True,
"/Page": writer.pages[0].indirect_reference,
"/Title": "Nested entry",
"/Type": "/Fit"
},
{
"/%is_open%": True,
"/Page": writer.pages[0].indirect_reference,
"/Title": "Bookmark B",
"/Type": "/Fit"
}
],
{
"/%is_open%": True,
"/Page": writer.pages[0].indirect_reference,
"/Title": "Bookmark B",
"/Type": "/Fit"
},
[
{
"/%is_open%": True,
"/Page": writer.pages[0].indirect_reference,
"/Title": "Nested entry",
"/Type": "/Fit"
}
]
]
assert caplog.messages[0].startswith("Detected cycle in outline structure for {")
def test_xfa__decompression_limit():
payload = b"A" * 100_0000
compressed = FlateDecode.encode(payload, 9)
writer = PdfWriter()
writer.add_blank_page(width=72, height=72)
stream = EncodedStreamObject()
stream._data = compressed
stream[NameObject("/Filter")] = NameObject("/FlateDecode")
stream_reference = writer._add_object(stream)
acro = DictionaryObject()
acro[NameObject("/XFA")] = ArrayObject([TextStringObject("datasets"), stream_reference])
writer.root_object[NameObject("/AcroForm")] = writer._add_object(acro)
data = BytesIO()
writer.write(data)
data.flush()
reader = PdfReader(data)
with mock.patch("pypdf.filters.ZLIB_MAX_OUTPUT_LENGTH", 75_000), pytest.raises(
expected_exception=LimitReachedError, match=r"^Limit reached while decompressing. 902 bytes remaining.$"
):
_ = reader.xfa
|
