pool/python-PyPDF2
SHA256
17
0
Fork 2
Code Issues Pull Requests Activity

I did not manage to run the testsuite (many tests needing internet), but the tests added by the patches were fine

Browse Source 
- Add security patches:
  * CVE-2025-55197.patch (bsc#1248089)
  * CVE-2026-27024.patch (bsc#1258691)
  * CVE-2026-27025.patch (bsc#1258692)
  * CVE-2026-27026.patch (bsc#1258693)

OBS-URL: https://build.opensuse.org/package/show/devel:languages:python/python-PyPDF2?expand=0&rev=26
This commit is contained in:
Simon Lees
2026-02-23 11:32:38 +00:00
committed by Git OBS Bridge
commit dc93183e5e
9 changed files with 1470 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
.gitattributes vendored Normal file
View File

@@ -0,0 +1,24 @@
*.changes merge=merge-changes
*.7z filter=lfs diff=lfs merge=lfs -text
*.bsp filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.gem filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.jar filter=lfs diff=lfs merge=lfs -text
*.lz filter=lfs diff=lfs merge=lfs -text
*.lzma filter=lfs diff=lfs merge=lfs -text
*.obscpio filter=lfs diff=lfs merge=lfs -text
*.oxt filter=lfs diff=lfs merge=lfs -text
*.pdf filter=lfs diff=lfs merge=lfs -text
*.png filter=lfs diff=lfs merge=lfs -text
*.rpm filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tbz filter=lfs diff=lfs merge=lfs -text
*.tbz2 filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.ttf filter=lfs diff=lfs merge=lfs -text
*.txz filter=lfs diff=lfs merge=lfs -text
*.whl filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text

4
.gitignore vendored Normal file
View File

@@ -0,0 +1,4 @@
*.obscpio
*.osc
_build.*
.pbuild

3
2.11.1.tar.gz Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4e323120adc5103d53c370782bfc86381143ea7b69e9213eb1263c7aaf39df8
size 6460157

118
CVE-2025-55197.patch Normal file
View File

@@ -0,0 +1,118 @@
From bb3a69030fde7da545229438ff327b8c971cef49 Mon Sep 17 00:00:00 2001
From: Stefan <96178532+stefan6419846@users.noreply.github.com>
Date: Mon, 11 Aug 2025 16:10:25 +0200
Subject: [PATCH] SEC: Limit decompressed size for FlateDecode filter (#3430)
Closes #3429.
---
PyPDF2/_reader.py | 10 ++++-
PyPDF2/errors.py | 4 ++
PyPDF2/filters.py | 89 +++++++++++++++++++++++++---------------
tests/example_files.yaml | 2 +
tests/test_filters.py | 41 ++++++++++++++----
tests/test_reader.py | 15 +++++++
6 files changed, 119 insertions(+), 42 deletions(-)
Index: PyPDF2-2.11.1/PyPDF2/_reader.py
===================================================================
--- PyPDF2-2.11.1.orig/PyPDF2/_reader.py
+++ PyPDF2-2.11.1/PyPDF2/_reader.py
@@ -1681,15 +1681,20 @@ class PdfReader:
xrefstream = cast(ContentStream, read_object(stream, self))
assert cast(str, xrefstream["/Type"]) == "/XRef"
self.cache_indirect_object(generation, idnum, xrefstream)
- stream_data = BytesIO(b_(xrefstream.get_data()))
+
# Index pairs specify the subsections in the dictionary. If
# none create one subsection that spans everything.
- idx_pairs = xrefstream.get("/Index", [0, xrefstream.get("/Size")])
+ if "/Size" not in xrefstream:
+ # According to table 17 of the PDF 2.0 specification, this key is required.
+ raise PdfReadError(f"Size missing from XRef stream {xrefstream!r}!")
+ idx_pairs = xrefstream.get("/Index", [0, xrefstream["/Size"]])
entry_sizes = cast(Dict[Any, Any], xrefstream.get("/W"))
assert len(entry_sizes) >= 3
if self.strict and len(entry_sizes) > 3:
raise PdfReadError(f"Too many entry sizes: {entry_sizes}")
+ stream_data = BytesIO(xrefstream.get_data())
+
def get_entry(i: int) -> Union[int, Tuple[int, ...]]:
# Reads the correct number of bytes for each entry. See the
# discussion of the W parameter in PDF spec table 17.
Index: PyPDF2-2.11.1/PyPDF2/errors.py
===================================================================
--- PyPDF2-2.11.1.orig/PyPDF2/errors.py
+++ PyPDF2-2.11.1/PyPDF2/errors.py
@@ -46,3 +46,7 @@ class EmptyFileError(PdfReadError):
STREAM_TRUNCATED_PREMATURELY = "Stream has ended unexpectedly"
+
+
+class LimitReachedError(PyPdfError):
+ """Raised when a limit is reached."""
Index: PyPDF2-2.11.1/PyPDF2/filters.py
===================================================================
--- PyPDF2-2.11.1.orig/PyPDF2/filters.py
+++ PyPDF2-2.11.1/PyPDF2/filters.py
@@ -58,12 +58,12 @@ from .constants import GraphicsStatePara
from .constants import ImageAttributes as IA
from .constants import LzwFilterParameters as LZW
from .constants import StreamAttributes as SA
-from .errors import PdfReadError, PdfStreamError
+from .errors import LimitReachedError, PdfReadError, PdfStreamError
def decompress(data: bytes) -> bytes:
try:
- return zlib.decompress(data)
+ return _decompress_with_limit(data)
except zlib.error:
d = zlib.decompressobj(zlib.MAX_WBITS | 32)
result_str = b""
@@ -74,6 +74,18 @@ def decompress(data: bytes) -> bytes:
pass
return result_str
+ZLIB_MAX_OUTPUT_LENGTH = 75_000_000
+
+
+def _decompress_with_limit(data: bytes) -> bytes:
+ decompressor = zlib.decompressobj()
+ result = decompressor.decompress(data, max_length=ZLIB_MAX_OUTPUT_LENGTH)
+ if decompressor.unconsumed_tail:
+ raise LimitReachedError(
+ f"Limit reached while decompressing. {len(decompressor.unconsumed_tail)} bytes remaining."
+ )
+ return result
+
class FlateDecode:
@staticmethod
Index: PyPDF2-2.11.1/tests/test_filters.py
===================================================================
--- PyPDF2-2.11.1.orig/tests/test_filters.py
+++ PyPDF2-2.11.1/tests/test_filters.py
@@ -1,4 +1,5 @@
import string
+import zlib
from io import BytesIO
from itertools import product as cartesian_product
from unittest.mock import patch
@@ -6,13 +7,14 @@ from unittest.mock import patch
import pytest
from PyPDF2 import PdfReader
-from PyPDF2.errors import PdfReadError, PdfStreamError
+from PyPDF2.errors import LimitReachedError, PdfReadError, PdfStreamError
from PyPDF2.filters import (
ASCII85Decode,
ASCIIHexDecode,
CCITParameters,
CCITTFaxDecode,
FlateDecode,
+ decompress,
)
from PyPDF2.generic import ArrayObject, DictionaryObject, NumberObject

58
CVE-2026-27024.patch Normal file
View File

@@ -0,0 +1,58 @@
From bd2f6d052fe5941e85e37082c2a43453d48d1295 Mon Sep 17 00:00:00 2001
From: Stefan <96178532+stefan6419846@users.noreply.github.com>
Date: Tue, 17 Feb 2026 17:51:28 +0100
Subject: [PATCH] SEC: Detect cyclic references when accessing
TreeObject.children (#3645)
---
PyPDF2/generic/_data_structures.py | 11 ++++++++++-
tests/generic/test_data_structures.py | 18 ++++++++++++++++--
2 files changed, 26 insertions(+), 3 deletions(-)
Index: PyPDF2-2.11.1/PyPDF2/generic/_data_structures.py
===================================================================
--- PyPDF2-2.11.1.orig/PyPDF2/generic/_data_structures.py
+++ PyPDF2-2.11.1/PyPDF2/generic/_data_structures.py
@@ -372,10 +372,19 @@ class TreeObject(DictionaryObject):
return
child_ref = self[NameObject("/First")]
+ last = self[NameObject("/Last")]
child = child_ref.get_object()
+ visited: set[int] = set()
while True:
+ child_id = id(child)
+ if child_id in visited:
+ logger_warning(f"Detected cycle in outline structure for {child}", __name__)
+ return
+ visited.add(child_id)
+
yield child
- if child == self[NameObject("/Last")]:
+
+ if child == last:
return
child_ref = child.get(NameObject("/Next")) # type: ignore
if child_ref is None:
Index: PyPDF2-2.11.1/tests/test_generic.py
===================================================================
--- PyPDF2-2.11.1.orig/tests/test_generic.py
+++ PyPDF2-2.11.1/tests/test_generic.py
@@ -918,3 +918,17 @@ def test_create_string_object_force():
)
def test_float_object_decimal_to_string(value, expected):
assert repr(FloatObject(value)) == expected
+
+
+def test_tree_object__cyclic_reference(caplog):
+ writer = PdfWriter()
+ child1 = writer._add_object(DictionaryObject())
+ child2 = writer._add_object(DictionaryObject({NameObject("/Next"): child1}))
+ child3 = writer._add_object(DictionaryObject({NameObject("/Next"): child2}))
+ child1.get_object()[NameObject("/Next")] = child3
+ tree = TreeObject()
+ tree[NameObject("/First")] = child2
+ tree[NameObject("/Last")] = writer._add_object(DictionaryObject())
+
+ assert list(tree.children()) == [child2.get_object(), child1.get_object(), child3.get_object()]
+ assert "Detected cycle in outline structure for " in caplog.text

189
CVE-2026-27025.patch Normal file
View File

@@ -0,0 +1,189 @@
From 77d7b8d7cfbe8dd179858dfa42666f73fc6e57a2 Mon Sep 17 00:00:00 2001
From: Stefan <96178532+stefan6419846@users.noreply.github.com>
Date: Tue, 17 Feb 2026 17:46:56 +0100
Subject: [PATCH] SEC: Limit size of `/ToUnicode` entries (#3646)
---
PyPDF2/_cmap.py | 20 ++++++++++
tests/test_cmap.py | 91 +++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 109 insertions(+), 2 deletions(-)
Index: PyPDF2-2.11.1/PyPDF2/_cmap.py
===================================================================
--- PyPDF2-2.11.1.orig/PyPDF2/_cmap.py
+++ PyPDF2-2.11.1/PyPDF2/_cmap.py
@@ -5,7 +5,7 @@ from typing import Any, Dict, List, Tupl
from ._codecs import adobe_glyphs, charset_encoding
from ._utils import logger_warning
-from .errors import PdfReadWarning
+from .errors import PdfReadWarning, LimitReachedError
from .generic import DecodedStreamObject, DictionaryObject
@@ -262,6 +262,15 @@ def process_cm_line(
return process_rg, process_char, multiline_rg
+# Usual values should be up to 65_536.
+MAPPING_DICTIONARY_SIZE_LIMIT = 100_000
+
+
+def _check_mapping_size(size: int) -> None:
+ if size > MAPPING_DICTIONARY_SIZE_LIMIT:
+ raise LimitReachedError(f"Maximum /ToUnicode size limit reached: {size} > {MAPPING_DICTIONARY_SIZE_LIMIT}.")
+
+
def parse_bfrange(
l: bytes,
map_dict: Dict[Any, Any],
@@ -273,6 +282,8 @@ def parse_bfrange(
nbi = max(len(lst[0]), len(lst[1]))
map_dict[-1] = ceil(nbi / 2)
fmt = b"%%0%dX" % (map_dict[-1] * 2)
+ entry_count = len(int_entry)
+ _check_mapping_size(entry_count)
if multiline_rg is not None:
a = multiline_rg[0] # a, b not in the current line
b = multiline_rg[1]
@@ -280,6 +291,8 @@ def parse_bfrange(
if sq == b"]":
closure_found = True
break
+ entry_count += 1
+ _check_mapping_size(entry_count)
map_dict[
unhexlify(fmt % a).decode(
"charmap" if map_dict[-1] == 1 else "utf-16-be",
@@ -296,6 +309,8 @@ def parse_bfrange(
if sq == b"]":
closure_found = True
break
+ entry_count += 1
+ _check_mapping_size(entry_count)
map_dict[
unhexlify(fmt % a).decode(
"charmap" if map_dict[-1] == 1 else "utf-16-be",
@@ -308,6 +323,8 @@ def parse_bfrange(
c = int(lst[2], 16)
fmt2 = b"%%0%dX" % max(4, len(lst[2]))
closure_found = True
+ range_size = max(0, b - a + 1)
+ _check_mapping_size(entry_count + range_size) # This can be checked beforehand.
while a <= b:
map_dict[
unhexlify(fmt % a).decode(
@@ -323,6 +340,8 @@ def parse_bfrange(
def parse_bfchar(l: bytes, map_dict: Dict[Any, Any], int_entry: List[int]) -> None:
lst = [x for x in l.split(b" ") if x]
+ new_count = len(lst) // 2
+ _check_mapping_size(len(int_entry) + new_count) # This can be checked beforehand.
map_dict[-1] = len(lst[0]) // 2
while len(lst) > 1:
map_to = ""
Index: PyPDF2-2.11.1/tests/test_cmap.py
===================================================================
--- PyPDF2-2.11.1.orig/tests/test_cmap.py
+++ PyPDF2-2.11.1/tests/test_cmap.py
@@ -3,7 +3,9 @@ from io import BytesIO
import pytest
from PyPDF2 import PdfReader
-from PyPDF2.errors import PdfReadWarning
+from PyPDF2._cmap import parse_bfchar, parse_bfrange
+from PyPDF2.errors import PdfReadWarning, LimitReachedError
+from PyPDF2.generic import StreamObject
from . import get_pdf_from_url
@@ -91,3 +93,89 @@ def test_iss1379():
name = "02voc.pdf"
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
reader.pages[2].extract_text()
+
+
+def test_parse_bfrange__iteration_limit():
+ writer = PdfWriter()
+
+ to_unicode = StreamObject()
+ to_unicode.set_data(
+ b"beginbfrange\n"
+ b"<00000000> <001FFFFF> <00000000>\n"
+ b"endbfrange\n"
+ )
+ font = writer._add_object(DictionaryObject({
+ NameObject("/Type"): NameObject("/Font"),
+ NameObject("/Subtype"): NameObject("/Type1"),
+ NameObject("/BaseFont"): NameObject("/Helvetica"),
+ NameObject("/ToUnicode"): to_unicode,
+ }))
+
+ page = writer.add_blank_page(width=100, height=100)
+ page[NameObject("/Resources")] = DictionaryObject({
+ NameObject("/Font"): DictionaryObject({
+ NameObject("/F1"): font.indirect_reference,
+ })
+ })
+
+ # Case without list, exceeding list directly.
+ with pytest.raises(
+ expected_exception=LimitReachedError, match=r"^Maximum /ToUnicode size limit reached: 2097152 > 100000\.$"
+ ):
+ _ = page.extract_text()
+
+ # Use a pre-filled dummy list to simulate multiple calls where the upper bound does
+ # not overflow, but the overall size does. Case without list.
+ int_entry = [0] * 99_999
+ map_dict = {}
+ with pytest.raises(
+ expected_exception=LimitReachedError, match=r"^Maximum /ToUnicode size limit reached: 165535 > 100000\.$"
+ ):
+ _ = parse_bfrange(line=b"0000 FFFF 0000", map_dict=map_dict, int_entry=int_entry, multiline_rg=None)
+ assert map_dict == {-1: 2}
+
+ # Exceeding from previous call.
+ int_entry.append(1)
+ map_dict = {}
+ with pytest.raises(
+ expected_exception=LimitReachedError, match=r"^Maximum /ToUnicode size limit reached: 100001 > 100000\.$"
+ ):
+ _ = parse_bfrange(line=b"00000000 00000000 00000000", map_dict=map_dict, int_entry=int_entry, multiline_rg=None)
+ assert map_dict == {-1: 4}
+
+ # multiline_rg
+ int_entry = [0] * 99_995
+ map_dict = {-1: 1}
+ with pytest.raises(
+ expected_exception=LimitReachedError, match=r"^Maximum /ToUnicode size limit reached: 100001 > 100000\.$"
+ ):
+ _ = parse_bfrange(
+ line=b"0020 0021 0022 0023 0024 0025 0026 2019",
+ map_dict=map_dict, int_entry=int_entry, multiline_rg=(32, 251)
+ )
+ assert map_dict == {-1: 1, " ": " ", "!": "!", '"': '"', "#": "#", "$": "$"}
+
+ # No multiline_rg, but list.
+ int_entry = [0] * 99_995
+ map_dict = {}
+ with pytest.raises(
+ expected_exception=LimitReachedError, match=r"^Maximum /ToUnicode size limit reached: 100001 > 100000\.$"
+ ):
+ _ = parse_bfrange(
+ line=b"01 8A [ FFFD FFFD FFFD FFFF FFAB AAAA BBBB",
+ map_dict=map_dict, int_entry=int_entry, multiline_rg=None
+ )
+ assert map_dict == {-1: 1, "\x01": "<22>", "\x02": "<22>", "\x03": "<22>", "\x04": "\uffff", "\x05": "ﾫ"}
+
+
+def test_parse_bfchar__iteration_limit():
+ int_entry = [0] * 99_995
+ map_dict = {}
+ with pytest.raises(
+ expected_exception=LimitReachedError, match=r"^Maximum /ToUnicode size limit reached: 100002 > 100000\.$"
+ ):
+ parse_bfchar(
+ line=b"0003 0020 0008 0025 0009 0026 000A 0027 000B 0028 000C 0029 000D 002A",
+ map_dict=map_dict, int_entry=int_entry,
+ )
+ assert map_dict == {}

52
CVE-2026-27026.patch Normal file
View File

@@ -0,0 +1,52 @@
From 7905842d833f899f1d3228af7e7467ad80277016 Mon Sep 17 00:00:00 2001
From: Stefan <96178532+stefan6419846@users.noreply.github.com>
Date: Tue, 17 Feb 2026 17:38:44 +0100
Subject: [PATCH] SEC: Limit FlateDecode recovery attempts (#3644)
---
docs/user/security.md | 3 +++
PyPDF2/filters.py | 16 ++++++++++++----
tests/test_filters.py | 13 ++++++++++---
3 files changed, 25 insertions(+), 7 deletions(-)
Index: PyPDF2-2.11.1/PyPDF2/filters.py
===================================================================
--- PyPDF2-2.11.1.orig/PyPDF2/filters.py
+++ PyPDF2-2.11.1/PyPDF2/filters.py
@@ -60,6 +60,11 @@ from .constants import LzwFilterParamete
from .constants import StreamAttributes as SA
from .errors import LimitReachedError, PdfReadError, PdfStreamError
+ZLIB_MAX_RECOVERY_INPUT_LENGTH = 5_000_000
+
+# Reuse cached 1-byte values in the fallback loop to avoid per-byte allocations.
+_SINGLE_BYTES = tuple(bytes((i,)) for i in range(256))
+
def decompress(data: bytes) -> bytes:
try:
@@ -67,10 +72,22 @@ def decompress(data: bytes) -> bytes:
except zlib.error:
d = zlib.decompressobj(zlib.MAX_WBITS | 32)
result_str = b""
- for b in [data[i : i + 1] for i in range(len(data))]:
+ remaining_limit = ZLIB_MAX_OUTPUT_LENGTH
+ for index in range(len(data)):
+ chunk = _SINGLE_BYTES[data[index]]
try:
- result_str += d.decompress(b)
+ decompressed = d.decompress(chunk)
+ result_str += decompressed
+ remaining_limit -= len(decompressed)
+ if remaining_limit <= 0:
+ raise LimitReachedError(
+ f"Limit reached while decompressing. {len(data) - index} bytes remaining."
+ )
except zlib.error:
+ if index > ZLIB_MAX_RECOVERY_INPUT_LENGTH:
+ raise LimitReachedError(
+ f"Recovery limit reached while decompressing. {data_length - index} bytes remaining."
+ )
pass
return result_str

942
python-PyPDF2.changes Normal file
View File

@@ -0,0 +1,942 @@
-------------------------------------------------------------------
Mon Feb 23 10:42:53 UTC 2026 - Markéta Machová <mmachova@suse.com>
- Add security patches:
* CVE-2025-55197.patch (bsc#1248089)
* CVE-2026-27024.patch (bsc#1258691)
* CVE-2026-27025.patch (bsc#1258692)
* CVE-2026-27026.patch (bsc#1258693)
-------------------------------------------------------------------
Mon May 12 10:44:03 UTC 2025 - Markéta Machová <mmachova@suse.com>
- Convert to pip-based build
-------------------------------------------------------------------
Fri Aug 25 14:08:04 UTC 2023 - ecsos <ecsos@opensuse.org>
- Add %{?sle15_python_module_pythons}
-------------------------------------------------------------------
Thu Oct 27 21:04:36 UTC 2022 - Yogalakshmi Arunachalam <yarunachalam@suse.com>
- Update to version 2.11.1
Bug Fixes (BUG)
* td matrix (#1373)
* Cope with cmap from #1322 (#1372)
Robustness (ROB)
* Cope with str returned from get_data in cmap (#1380)
Full Changelog: https://github.com/py-pdf/PyPDF2/compare/2.11.0…2.11.1
-------------------------------------------------------------------
Wed Oct 12 02:36:06 UTC 2022 - Yogalakshmi Arunachalam <yarunachalam@suse.com>
- Update to version 2.11.0
* New Features (ENH)
Addition of optional visitor-functions in extract_text() (#1252)
Add metadata.creation_date and modification_date (#1364)
Add PageObject.images attribute (#1330)
* Bug Fixes (BUG)
Lookup index in _xobj_to_image can be ByteStringObject (#1366)
‘IndexError: index out of range’ when using extract_text (#1361)
Errors in transfer_rotation_to_content() (#1356)
* Robustness (ROB)
Ensure update_page_form_field_values does not fail if no fields (#1346)
Full Changelog: https://github.com/py-pdf/PyPDF2/compare/2.10.9…2.11.0
-------------------------------------------------------------------
Wed Sep 7 18:19:10 UTC 2022 - Yogalakshmi Arunachalam <yarunachalam@suse.com>
- Spec changes:
Changed the source to github
Renamed CHANGELOG to CHANGELOG.md
-------------------------------------------------------------------
Wed Sep 7 16:36:36 UTC 2022 - Yogalakshmi Arunachalam <yarunachalam@suse.com>
- Update to version 2.6.0:
New Features (ENH):
- Add color and font_format to PdfReader.outlines[i] (#1104)
- Extract Text Enhancement (whitespaces) (#1084)
Bug Fixes (BUG):
- Use `build_destination` for named destination outlines (#1128)
- Avoid a crash when a ToUnicode CMap has an empty dstString in beginbfchar (#1118)
- Prevent deduplication of PageObject (#1105)
- None-check in DictionaryObject.read_from_stream (#1113)
- Avoid IndexError in _cmap.parse_to_unicode (#1110)
Documentation (DOC): - Explanation for git submodule - Watermark and stamp (#1095) Maintenance (MAINT):
- Text extraction improvements (#1126)
- Destination.color returns ArrayObject instead of tuple as fallback (#1119)
- Use add_bookmark_destination in add_bookmark (#1100)
- Use add_bookmark_destination in add_bookmark_dict (#1099)
Testing (TST):
- Remove xfail from test_outline_title_issue_1121
- Add test for arab text (#1127)
- Add xfail for decryption fail (#1125)
- Add xfail test for IndexError when extracting text (#1124)
- Add MCVE showing outline title issue (#1123)
Code Style (STY):
- Apply black and isort
- Use IntFlag for permissions_flag / update_page_form_field_values (#1094)
- Simplify code (#1101)
- Update to version 2.5.0:
New Features (ENH):
- Add PageObject._get_fonts (#1083)
- Add support for indexed color spaces / BitsPerComponent for decoding PNGs (#1067)
Performance Improvements (PI):
- Use iterative DFS in PdfWriter._sweep_indirect_references (#1072)
Bug Fixes (BUG):
- Let Page.scale also scale the crop-/trim-/bleed-/artbox (#1066)
- Column default for CCITTFaxDecode (#1079)
Robustness (ROB):
- Guard against None-value in _get_outlines (#1060)
Documentation (DOC):
- Stamps and watermarks (#1082)
- OCR vs PDF text extraction (#1081)
- Python Version support
- Formatting of CHANGELOG
Developer Experience (DEV):
- Cache downloaded files (#1070)
- Speed-up for CI (#1069)
Maintenance (MAINT):
- Set page.rotate(angle: int) (#1092)
- Issue #416 was fixed by #1015 (#1078)
Testing (TST):
- Image extraction (#1080)
- Image extraction (#1077)
Code Style (STY):
- Apply black
- Typo in Changelog
- Update to version 2.4.2:
New Features (ENH):
- Add PdfReader.xfa attribute (#1026)
Bug Fixes (BUG):
- Wrong page inserted when PdfMerger.merge is done (#1063)
- Resolve IndirectObject when it refers to a free entry (#1054)
Developer Experience (DEV):
- Added {posargs} to tox.ini (#1055)
Maintenance (MAINT):
- Remove PyPDF2._utils.bytes_type (#1053)
Testing (TST):
- Scale page (indirect rect object) (#1057)
- Simplify pathlib PdfReader test (#1056)
- IndexError of VirtualList (#1052)
- Invalid XML in xmp information (#1051)
- No pycryptodome (#1050)
- Increase test coverage (#1045)
Code Style (STY):
- DOC of compress_content_streams (#1061)
- Minimize diff for #879 (#1049)
- Update to version 2.4.1:
New Features (ENH):
- Add writer.pdf_header property (getter and setter) (#1038)
Performance Improvements (PI):
- Remove b_ call in FloatObject.write_to_stream (#1044)
- Check duplicate objects in writer._sweep_indirect_references (#207)
Documentation (DOC):
- How to surppress exceptions/warnings/log messages (#1037)
- Remove hyphen from lossless (#1041)
- Compression of content streams (#1040)
- Fix inconsistent variable names in add-watermark.md (#1039)
- File size reduction
- Add CHANGELOG to the rendered docs (#1023)
Maintenance (MAINT):
- Handle XML error when reading XmpInformation (#1030)
- Deduplicate Code / add mutmut config (#1022)
Code Style (STY):
- Use unnecessary one-line function / class attribute (#1043)
- Docstring formatting (#1033)
- Update to version 2.4.0:
New Features (ENH):
- Support R6 decrypting (#1015)
- Add PdfReader.pdf_header (#1013)
Performance Improvements (PI):
- Remove ord_ calls (#1014)
Bug Fixes (BUG):
- Fix missing page for bookmark (#1016)
Robustness (ROB):
- Deal with invalid Destinations (#1028)
Documentation (DOC):
- get_form_text_fields does not extract dropdown data (#1029)
- Adjust PdfWriter.add_uri docstring
- Mention crypto extra_requires for installation (#1017)
Developer Experience (DEV):
- Use /n line endings everywhere (#1027)
- Adjust string formatting to be able to use mutmut (#1020)
- Update Bug report template
- Update to version 2.3.1:
BUG: Forgot to add the interal `_codecs` subpackage.
- Update to version 2.3.0:
The highlight of this release is improved support for file encryption
(AES-128 and AES-256, R5 only). See #749 for the amazing work of
@exiledkingcc confetti_ball Thank you hugs
Deprecations (DEP):
- Rename names to be PEP8-compliant (#967)
- `PdfWriter.get_page`: the pageNumber parameter is renamed to page_number
- `PyPDF2.filters`:
* For all classes, a parameter rename: decodeParms ➔ decode_parms
* decodeStreamData ➔ decode_stream_data
- `PyPDF2.xmp`:
* XmpInformation.rdfRoot ➔ XmpInformation.rdf_root
* XmpInformation.xmp_createDate ➔ XmpInformation.xmp_create_date
* XmpInformation.xmp_creatorTool ➔ XmpInformation.xmp_creator_tool
* XmpInformation.xmp_metadataDate ➔ XmpInformation.xmp_metadata_date
* XmpInformation.xmp_modifyDate ➔ XmpInformation.xmp_modify_date
* XmpInformation.xmpMetadata ➔ XmpInformation.xmp_metadata
* XmpInformation.xmpmm_documentId ➔ XmpInformation.xmpmm_document_id
* XmpInformation.xmpmm_instanceId ➔ XmpInformation.xmpmm_instance_id
- `PyPDF2.generic`:
* readHexStringFromStream ➔ read_hex_string_from_stream
* initializeFromDictionary ➔ initialize_from_dictionary
* createStringObject ➔ create_string_object
* TreeObject.hasChildren ➔ TreeObject.has_children
* TreeObject.emptyTree ➔ TreeObject.empty_tree
New Features (ENH):
- Add decrypt support for V5 and AES-128, AES-256 (R5 only) (#749)
Robustness (ROB):
- Fix corrupted (wrongly) linear PDF (#1008)
Maintenance (MAINT):
- Move PDF_Samples folder into ressources
- Fix typos (#1007)
Testing (TST):
- Improve encryption/decryption test (#1009)
- Add merger test cases with real PDFs (#1006)
- Add mutmut config
Code Style (STY):
- Put pure data mappings in separate files (#1005)
- Make encryption module private, apply pre-commit (#1010)
- Update to version 2.2.1:
Performance Improvements (PI):
- Remove b_ calls (#992, #986)
- Apply improvements to _utils suggested by perflint (#993)
Robustness (ROB):
- utf-16-be\' codec can\'t decode (...) (#995)
Documentation (DOC):
- Remove reference to Scripts (#987)
Developer Experience (DEV):
- Fix type annotations for add_bookmarks (#1000)
Testing (TST):
- Add test for PdfMerger (#1001)
- Add tests for XMP information (#996)
- reader.get_fields / zlib issue / LZW decode issue (#1004)
- reader.get_fields with report generation (#1002)
- Improve test coverage by extracting texts (#998)
Code Style (STY):
- Apply fixes suggested by pylint (#999)
- Update to version 2.2.0:
The 2.2.0 release improves text extraction again via (#969):
* Improvements around /Encoding / /ToUnicode
* Extraction of CMaps improved
* Fallback for font def missing
* Support for /Identity-H and /Identity-V: utf-16-be
* Support for /GB-EUC-H / /GB-EUC-V / GBp/c-EUC-H / /GBpc-EUC-V (beta release for evaluation)
* Arabic (for evaluation)
* Whitespace extraction improvements
Those changes should mainly improve the text extraction for non-ASCII alphabets,
e.g. Russian / Chinese / Japanese / Korean / Arabic.
- Update to version 2.1.1:
New Features (ENH):
- Add support for pathlib as input for PdfReader (#979)
Performance Improvements (PI):
- Optimize read_next_end_line (#646)
Bug Fixes (BUG):
- Adobe Acrobat \'Would you like to save this file?\' (#970)
Documentation (DOC):
- Notes on annotations (#982)
- Who uses PyPDF2
- intendet \xe2\x9e\x94 in robustness page (#958)
Maintenance (MAINT):
- pre-commit / requirements.txt updates (#977)
- Mark read_next_end_line as deprecated (#965)
- Export `PageObject` in PyPDF2 root (#960)
Testing (TST):
- Add MCVE of issue #416 (#980)
- FlateDecode.decode decodeParms (#964)
- Xmp module (#962)
- utils.paeth_predictor (#959)
Code Style (STY):
- Use more tuples and list/dict comprehensions (#976)
- Update to version 2.1.0:
The highlight of the 2.1.0 release is the most massive improvement to the
text extraction capabilities of PyPDF2 since 2016 partying_faceconfetti_ball A very big thank you goes
to [pubpub-zz](https://github.com/pubpub-zz) who took a lot of time and
knowledge about the PDF format to finally get those improvements into PyPDF2.
Thank you hugsgreen_heart
In case the new function causes any issues, you can use `_extract_text_old`
for the old functionality. Please also open a bug ticket in that case.
There were several people who have attempted to bring similar improvements to
PyPDF2. All of those were valuable. The main reason why they didn't get merged
is the big amount of open PRs / issues. pubpub-zz was the most comprehensive
PR which also incorporated the latest changes of PyPDF2 2.0.0.
Thank you to [VictorCarlquist](https://github.com/VictorCarlquist) for #858 and
[asabramo](https://github.com/asabramo) for #464 hugs
New Features (ENH):
- Massive text extraction improvement (#924). Closed many open issues:
- Exceptions / missing spaces in extract_text() method (#17) man_dancing
- Whitespace issues in extract_text() (#42) woman_dancing
- pypdf2 reads the hifenated words in a new line (#246)
- PyPDF2 failing to read unicode character (#37)
- Unable to read bullets (#230)
- ExtractText yields nothing for apparently good PDF (#168) tada
- Encoding issue in extract_text() (#235)
- extractText() doesn't work on Chinese PDF (#252)
- encoding error (#260)
- Trouble with apostophes in names in text "O'Doul" (#384)
- extract_text works for some PDF files, but not the others (#437)
- Euro sign not being recognized by extractText (#443)
- Failed extracting text from French texts (#524)
- extract_text doesn't extract ligatures correctly (#598)
- reading spanish text - mark convert issue (#635)
- Read PDF changed from text to random symbols (#654)
- .extractText() reads / as 1. (#789)
- Update glyphlist (#947) - inspired by #464
- Allow adding PageRange objects (#948)
Bug Fixes (BUG):
- Delete .python-version file (#944)
- Compare StreamObject.decoded_self with None (#931)
Robustness (ROB):
- Fix some conversion errors on non conform PDF (#932)
Documentation (DOC):
- Elaborate on PDF text extraction difficulties (#939)
- Add logo (#942)
- rotate vs Transformation().rotate (#937)
- Example how to use PyPDF2 with AWS S3 (#938)
- How to deprecate (#930)
- Fix typos on robustness page (#935)
- Remove scripts (pdfcat) from docs (#934)
Developer Experience (DEV):
- Ignore .python-version file
- Mark deprecated code with no-cover (#943)
- Automatically create Github releases from tags (#870)
Testing (TST):
- Text extraction for non-latin alphabets (#954)
- Ignore PdfReadWarning in benchmark (#949)
- writer.remove_text (#946)
- Add test for Tree and _security (#945)
Code Style (STY):
- black, isort, Flake8, splitting buildCharMap (#950)
- Update to version 2.0.0:
The 2.0.0 release of PyPDF2 includes three core changes:
1. Dropping support for Python 3.5 and older.
2. Introducing type annotations.
3. Interface changes, mostly to have PEP8-compliant names
We introduced a [deprecation process](#930)
that hopefully helps users to avoid unexpected breaking changes.
Breaking Changes(DEP):
- PyPDF2 2.0 requires Python 3.6+. Python 2.7 and 3.5 support were dropped.
- PdfFileReader: The "warndest" parameter was removed
- PdfFileReader and PdfFileMerger no longer have the `overwriteWarnings`
parameter. The new behavior is `overwriteWarnings=False`.
- merger: OutlinesObject was removed without replacement.
- merger.py ➔ _merger.py: You must import PdfFileMerger from PyPDF2 directly.
- utils:
* `ConvertFunctionsToVirtualList` was removed
* `formatWarning` was removed
* `isInt(obj)`: Use `instance(obj, int)` instead
* `u_(s)`: Use `s` directly
* `chr_(c)`: Use `chr(c)` instead
* `barray(b)`: Use `bytearray(b)` instead
* `isBytes(b)`: Use `instance(b, type(bytes()))` instead
* `xrange_fn`: Use `range` instead
* `string_type`: Use `str` instead
* `isString(s)`: Use `instance(s, str)` instead
* `_basestring`: Use `str` instead
* All Exceptions are now in `PyPDF2.errors`:
- PageSizeNotDefinedError
- PdfReadError
- PdfReadWarning
- PyPdfError
-`PyPDF2.pdf` (the `pdf` module) no longer exists. The contents were moved with
the library. You should most likely import directly from `PyPDF2` instead.
The `RectangleObject` is in `PyPDF2.generic`.
-The `Resources`, `Scripts`, and `Tests` will no longer be part of the distribution
files on PyPI. This should have little to no impact on most people. The
`Tests` are renamed to `tests`, the `Resources` are renamed to `resources`.
Both are still in the git repository. The `Scripts` are now in
https://github.com/py-pdf/cpdf. `Sample_Code` was moved to the `docs`.
For a full list of deprecated functions, please see the changelog of version 1.28.0.
New Features (ENH):
- Improve space setting for text extraction (#922)
- Allow setting the decryption password in PdfReader.__init__ (#920)
- Add Page.add_transformation (#883)
Bug Fixes (BUG):
- Fix error adding transformation to page without /Contents (#908)
Robustness (ROB):
- Cope with invalid length in streams (#861)
Documentation (DOC):
- Fix style of 1.25 and 1.27 patch notes (#927)
- Transformation (#907)
Developer Experience (DEV):
- Create flake8 config file (#916)
- Use relative imports (#875)
Maintenance (MAINT):
- Use Python 3.6 language features (#849)
- Add wrapper function for PendingDeprecationWarnings (#928)
- Use new PEP8 compliant names (#884)
- Explicitly represent transformation matrix (#878)
- Inline PAGE_RANGE_HELP string (#874)
- Remove unnecessary generics imports (#873)
- Remove star imports (#865)
- merger.py ➔ _merger.py (#864)
- Type annotations for all functions/methods (#854)
- Add initial type support with mypy (#853)
Testing (TST):
- Regression test for xmp_metadata converter (#923)
- Checkout submodule sample-files for benchmark
- Add text extracting performance benchmark
- Use new PyPDF2 API in benchmark (#902)
- Make test suite fail for uncaught warnings (#892)
- Remove -OO testrun from CI (#901)
- Improve tests for convert_to_int (#899)
- Update to version 1.28.4:
Bug Fixes (BUG):
- XmpInformation._converter_date was unusable (#921)
- Update to version 1.28.3:
Deprecations (DEP):
- PEP8 renaming (#905)
Bug Fixes (BUG):
- XmpInformation missing method _getText (#917)
- Fix PendingDeprecationWarning on _merge_page (#904)
- Update to version 1.28.2:
Bug Fixes (BUG):
- PendingDeprecationWarning for getContents (#893)
- PendingDeprecationWarning on using PdfMerger (#891)
- Update to version 1.28.1:
Bug Fixes (BUG):
- Incorrectly show deprecation warnings on internal usage (#887)
Maintenance (MAINT):
- Add stacklevel=2 to deprecation warnings (#889)
- Remove duplicate warnings imports (#888)
- Update to version 1.28.0:
This release adds a lot of deprecation warnings in preparation of the
PyPDF2 2.0.0 release. The changes are mostly using snake_case function-, method-,
and variable-names as well as using properties instead of getter-methods.
Maintenance (MAINT):
- Remove IronPython Fallback for zlib (#868)
* Make the `PyPDF2.utils` module private
* Rename of core classes:
* PdfFileReader ➔ PdfReader
* PdfFileWriter ➔ PdfWriter
* PdfFileMerger ➔ PdfMerger
* Use PEP8 conventions for function names and parameters
* If a property and a getter-method are both present, use the property
In many places:
- getObject ➔ get_object
- writeToStream ➔ write_to_stream
- readFromStream ➔ read_from_stream
PyPDF2.generic
- readObject ➔ read_object
- convertToInt ➔ convert_to_int
- DocumentInformation.getText ➔ DocumentInformation._get_text :
This method should typically not be used; please let me know if you need it.
PdfReader class:
- `reader.getPage(pageNumber)` ➔ `reader.pages[page_number]`
- `reader.getNumPages()` / `reader.numPages` ➔ `len(reader.pages)`
- getDocumentInfo ➔ metadata
- flattenedPages attribute ➔ flattened_pages
- resolvedObjects attribute ➔ resolved_objects
- xrefIndex attribute ➔ xref_index
- getNamedDestinations / namedDestinations attribute ➔ named_destinations
- getPageLayout / pageLayout ➔ page_layout attribute
- getPageMode / pageMode ➔ page_mode attribute
- getIsEncrypted / isEncrypted ➔ is_encrypted attribute
- getOutlines ➔ get_outlines
- readObjectHeader ➔ read_object_header (TODO: read vs get?)
- cacheGetIndirectObject ➔ cache_get_indirect_object (TODO: public vs private?)
- cacheIndirectObject ➔ cache_indirect_object (TODO: public vs private?)
- getDestinationPageNumber ➔ get_destination_page_number
- readNextEndLine ➔ read_next_end_line
- _zeroXref ➔ _zero_xref
- _authenticateUserPassword ➔ _authenticate_user_password
- _pageId2Num attribute ➔ _page_id2num
- _buildDestination ➔ _build_destination
- _buildOutline ➔ _build_outline
- _getPageNumberByIndirect(indirectRef) ➔ _get_page_number_by_indirect(indirect_ref)
- _getObjectFromStream ➔ _get_object_from_stream
- _decryptObject ➔ _decrypt_object
- _flatten(..., indirectRef) ➔ _flatten(..., indirect_ref)
- _buildField ➔ _build_field
- _checkKids ➔ _check_kids
- _writeField ➔ _write_field
- _write_field(..., fieldAttributes) ➔ _write_field(..., field_attributes)
- _read_xref_subsections(..., getEntry, ...) ➔ _read_xref_subsections(..., get_entry, ...)
PdfWriter class:
- `writer.getPage(pageNumber)` ➔ `writer.pages[page_number]`
- `writer.getNumPages()` ➔ `len(writer.pages)`
- addMetadata ➔ add_metadata
- addPage ➔ add_page
- addBlankPage ➔ add_blank_page
- addAttachment(fname, fdata) ➔ add_attachment(filename, data)
- insertPage ➔ insert_page
- insertBlankPage ➔ insert_blank_page
- appendPagesFromReader ➔ append_pages_from_reader
- updatePageFormFieldValues ➔ update_page_form_field_values
- cloneReaderDocumentRoot ➔ clone_reader_document_root
- cloneDocumentFromReader ➔ clone_document_from_reader
- getReference ➔ get_reference
- getOutlineRoot ➔ get_outline_root
- getNamedDestRoot ➔ get_named_dest_root
- addBookmarkDestination ➔ add_bookmark_destination
- addBookmarkDict ➔ add_bookmark_dict
- addBookmark ➔ add_bookmark
- addNamedDestinationObject ➔ add_named_destination_object
- addNamedDestination ➔ add_named_destination
- removeLinks ➔ remove_links
- removeImages(ignoreByteStringObject) ➔ remove_images(ignore_byte_string_object)
- removeText(ignoreByteStringObject) ➔ remove_text(ignore_byte_string_object)
- addURI ➔ add_uri
- addLink ➔ add_link
- getPage(pageNumber) ➔ get_page(page_number)
- getPageLayout / setPageLayout / pageLayout ➔ page_layout attribute
- getPageMode / setPageMode / pageMode ➔ page_mode attribute
- _addObject ➔ _add_object
- _addPage ➔ _add_page
- _sweepIndirectReferences ➔ _sweep_indirect_references
PdfMerger class
- `__init__` parameter: strict=True ➔ strict=False (the PdfFileMerger still has the old default)
- addMetadata ➔ add_metadata
- addNamedDestination ➔ add_named_destination
- setPageLayout ➔ set_page_layout
- setPageMode ➔ set_page_mode
Page class:
- artBox / bleedBox/ cropBox/ mediaBox / trimBox ➔ artbox / bleedbox/ cropbox/ mediabox / trimbox
- getWidth, getHeight ➔ width / height
- getLowerLeft_x / getUpperLeft_x ➔ left
- getUpperRight_x / getLowerRight_x ➔ right
- getLowerLeft_y / getLowerRight_y ➔ bottom
- getUpperRight_y / getUpperLeft_y ➔ top
- getLowerLeft / setLowerLeft ➔ lower_left property
- upperRight ➔ upper_right
- mergePage ➔ merge_page
- rotateClockwise / rotateCounterClockwise ➔ rotate_clockwise
- _mergeResources ➔ _merge_resources
- _contentStreamRename ➔ _content_stream_rename
- _pushPopGS ➔ _push_pop_gs
- _addTransformationMatrix ➔ _add_transformation_matrix
- _mergePage ➔ _merge_page
XmpInformation class:
- getElement(..., aboutUri, ...) ➔ get_element(..., about_uri, ...)
- getNodesInNamespace(..., aboutUri, ...) ➔ get_nodes_in_namespace(..., aboutUri, ...)
- _getText ➔ _get_text
utils.py:
- matrixMultiply ➔ matrix_multiply
- RC4_encrypt is moved to the security module
- Update to version 1.27.12:
Bug Fixes (BUG):
- _rebuild_xref_table expects trailer to be a dict (#857)
Documentation (DOC):
- Security Policy
- Update to version 1.27.11:
Bug Fixes (BUG):
- Incorrectly issued xref warning/exception (#855)
- Update to version 1.27.10:
Robustness (ROB):
- Handle missing destinations in reader (#840)
- warn-only in readStringFromStream (#837)
- Fix corruption in startxref or xref table (#788 and #830)
Documentation (DOC):
- Project Governance (#799)
- History of PyPDF2
- PDF feature/version support (#816)
- More details on text parsing issues (#815)
Developer Experience (DEV):
- Add benchmark command to Makefile
- Ignore IronPython parts for code coverage (#826)
Maintenance (MAINT):
- Split pdf module (#836)
- Separated CCITTFax param parsing/decoding (#841)
- Update requirements files
Testing (TST):
- Use external repository for larger/more PDFs for testing (#820)
- Swap incorrect test names (#838)
- Add test for PdfFileReader and page properties (#835)
- Add tests for PyPDF2.generic (#831)
- Add tests for utils, form fields, PageRange (#827)
- Add test for ASCII85Decode (#825)
- Add test for FlateDecode (#823)
- Add test for filters.ASCIIHexDecode (#822)
Code Style (STY):
- Apply pre-commit (black, isort) + use snake_case variables (#832)
- Remove debug code (#828)
- Documentation, Variable names (#839)
- Update to version 1.27.9:
A change I would like to highlight is the performance improvement for
large PDF files (#808) tada
New Features (ENH):
- Add papersizes (#800)
- Allow setting permission flags when encrypting (#803)
- Allow setting form field flags (#802)
Bug Fixes (BUG):
- TypeError in xmp._converter_date (#813)
- Improve spacing for text extraction (#806)
- Fix PDFDocEncoding Character Set (#809)
Robustness (ROB):
- Use null ID when encrypted but no ID given (#812)
- Handle recursion error (#804)
Documentation (DOC):
- CMaps (#811)
- The PDF Format + commit prefixes (#810)
- Add compression example (#792)
Developer Experience (DEV):
- Add Benchmark for Performance Testing (#781)
Maintenance (MAINT):
- Validate PDF magic byte in strict mode (#814)
- Make PdfFileMerger.addBookmark() behave life PdfFileWriters\' (#339)
- Quadratic runtime while parsing reduced to linear (#808)
Testing (TST):
- Newlines in text extraction (#807)
- Update to version 1.27.8:
Bug Fixes (BUG):
- Use 1MB as offset for readNextEndLine (#321)
- 'PdfFileWriter' object has no attribute 'stream' (#787)
Robustness (ROB):
- Invalid float object; use 0 as fallback (#782)
Documentation (DOC):
- Robustness (#785)
- Update to version 1.27.7:
Bug Fixes (BUG):
- Import exceptions from PyPDF2.errors in PyPDF2.utils (#780)
Code Style (STY):
- Naming in 'make_changelog.py'
- Update to version 1.27.6:
Deprecations (DEP):
- Remove support for Python 2.6 and older (#776)
New Features (ENH):
- Extract document permissions (#320)
Bug Fixes (BUG):
- Clip by trimBox when merging pages, which would otherwise be ignored (#240)
- Add overwriteWarnings parameter PdfFileMerger (#243)
- IndexError for getPage() of decryped file (#359)
- Handle cases where decodeParms is an ArrayObject (#405)
- Updated PDF fields don't show up when page is written (#412)
- Set Linked Form Value (#414)
- Fix zlib -5 error for corrupt files (#603)
- Fix reading more than last1K for EOF (#642)
- Acciental import
Robustness (ROB):
- Allow extra whitespace before "obj" in readObjectHeader (#567)
Documentation (DOC):
- Link to pdftoc in Sample_Code (#628)
- Working with annotations (#764)
- Structure history
Developer Experience (DEV):
- Add issue templates (#765)
- Add tool to generate changelog
Maintenance (MAINT):
- Use grouped constants instead of string literals (#745)
- Add error module (#768)
- Use decorators for @staticmethod (#775)
- Split long functions (#777)
Testing (TST):
- Run tests in CI once with -OO Flags (#770)
- Filling out forms (#771)
- Add tests for Writer (#772)
- Error cases (#773)
- Check Error messages (#769)
- Regression test for issue #88
- Regression test for issue #327
Code Style (STY):
- Make variable naming more consistent in test
- Update to version 1.27.5:
Security (SEC):
- ContentStream_readInlineImage had potential infinite loop (#740)
Bug fixes (BUG):
- Fix merging encrypted files (#757)
- CCITTFaxDecode decodeParms can be an ArrayObject (#756)
Robustness improvements (ROBUST):
- title sometimes None (#744)
Documentation (DOC):
- Adjust short description of the package
Tests and Test setup (TST):
- Rewrite JS tests from unittest to pytest (#746)
- Increase Test coverage, mainly with filters (#756)
- Add test for inline images (#758)
Developer Experience Improvements (DEV):
- Remove unused Travis-CI configuration (#747)
- Show code coverage (#754, #755)
- Add mutmut (#760)
Miscellaneous:
- STY: Closing file handles, explicit exports, ... (#743)
- Update to version 1.27.4:
Bug fixes (BUG):
- Guard formatting of __init__.__doc__ string (#738)
Packaging (PKG):
- Add more precise license field to setup (#733)
Testing (TST):
- Add test for issue #297
Miscellaneous:
- DOC: Miscallenious ➔ Miscellaneous (Typo)
- TST: Fix CI triggering (master ➔ main) (#739)
- STY: Fix various style issues (#742)
- Update to version 1.27.3:
- PKG: Make Tests not a subpackage (#728)
- BUG: Fix ASCII85Decode.decode assertion (#729)
- BUG: Error in Chinese character encoding (#463)
- BUG: Code duplication in Scripts/2-up.py
- ROBUST: Guard 'obj.writeToStream' with 'if obj is not None'
- ROBUST: Ignore a /Prev entry with the value 0 in the trailer
- MAINT: Remove Sample_Code (#726)
- TST: Close file handle in test_writer (#722)
- TST: Fix test_get_images (#730)
- DEV: Make tox use pytest and add more Python versions (#721)
- DOC: Many (#720, #723-725, #469)
- Update to version 1.27.2:
- Add Scripts (including `pdfcat`), Resources, Tests, and Sample_Code back to
PyPDF2. It was removed by accident in 1.27.0, but might get removed with 2.0.0
See #718 for discussion
- Update to version 1.27.0:
Features:
- Add alpha channel support for png files in Script (#614)
Bug fixes (BUG):
- Fix formatWarning for filename without slash (#612)
- Add whitespace between words for extractText() (#569, #334)
- "invalid escape sequence" SyntaxError (#522)
- Avoid error when printing warning in pythonw (#486)
- Stream operations can be List or Dict (#665)
Documentation (DOC):
- Added Scripts/pdf-image-extractor.py
- Documentation improvements (#550, #538, #324, #426, #394)
Tests and Test setup (TST):
- Add Github Action which automatically run unit tests via pytest and
static code analysis with Flake8 (#660)
- Add several unit tests (#661, #663)
- Add .coveragerc to create coverage reports
Developer Experience Improvements (DEV):
- Pre commit: Developers can now `pre-commit install` to avoid tiny issues
like trailing whitespaces
Miscallenious:
- Add the LICENSE file to the distributed packages (#288)
- Use setuptools instead of distutils (#599)
- Improvements for the PyPI page (#644)
- Python 3 changes (#504, #366)
-------------------------------------------------------------------
Mon Oct 21 22:55:54 UTC 2019 - Simon Lees <simon.lees@suse.com>
- change the copyright to 2019
-------------------------------------------------------------------
Thu Dec 6 13:22:02 UTC 2018 - Tomáš Chvátal <tchvatal@suse.com>
- Fix fdupes call
-------------------------------------------------------------------
Tue Dec 4 12:52:37 UTC 2018 - Matej Cepl <mcepl@suse.com>
- Remove superfluous devel dependency for noarch package
-------------------------------------------------------------------
Mon May 14 10:11:40 UTC 2018 - tchvatal@suse.com
- Use license macro
-------------------------------------------------------------------
Thu Apr 20 04:22:33 UTC 2017 - sflees@suse.de
- Convert to single spec
- Update to version 1.26.0
* NOTE: Active maintenance on PyPDF2 is resuming after a hiatus
* Fixed a bug where image resources where incorrectly overwritten
when merging pages
* Added dictionary for JavaScript actions to the root (louib)
* Added unit tests for the JS functionality (louib)
* Add more Python 3 compatibility when reading inline images (im2703
and (VyacheslavHashov)
* Return NullObject instead of raising error when failing to resolve
object (ctate)
* Don't output warning for non-zeroed xref table when strict=False
(BenRussert)
* Remove extraneous zeroes from output formatting (speedplane)
* Fix bug where reading an inline image would cut off prematurely in
certain cases (speedplane)
- Changes for 1.25
BUGFIXES:
* Added Python 3 algorithm for ASCII85Decode. Fixes issue when
reading reportlab-generated files with Py 3 (jerickbixly)
* Recognize more escape sequence which would otherwise throw an
exception (manuelzs, robertsoakes)
* Fixed overflow error in generic.py. Occurred
when reading a too-large int in Python 2 (by Raja Jamwal)
* Allow access to files which were encrypted with an empty
password. Previously threw a "File has not been decrypted"
exception (Elena Williams)
* Do not attempt to decode an empty data stream. Previously
would cause an error in decode algorithms (vladir)
* Fixed some type issues specific to Py 2 or Py 3
* Fix issue when stream data begins with whitespace (soloma83)
* Recognize abbreviated filter names (AlmightyOatmeal and
Matthew Weiss)
* Copy decryption key from PdfFileReader to PdfFileMerger.
Allows usage of PdfFileMerger with encrypted files (twolfson)
* Fixed bug which occurred when a NameObject is present at end
of a file stream. Threw a "Stream has ended unexpectedly"
exception (speedplane)
FEATURES:
* Initial work on a test suite; to be expanded in future.
Tests and Resources directory added, README updated (robertsoakes)
* Added document cloning methods to PdfFileWriter:
appendPagesFromReader, cloneReaderDocumentRoot, and
cloneDocumentFromReader. See official documentation (robertsoakes)
* Added method for writing to form fields: updatePageFormFieldValues.
This will be enhanced in the future. See official documentation
(robertsoakes)
* New addAttachment method. See documentation. Support for adding
and extracting embedded files to be enhanced in the future
(moshekaplan)
* Added methods to get page number of given PageObject or
Destination: getPageNumber and getDestinationPageNumber.
See documentation (mozbugbox)
-------------------------------------------------------------------
Mon May 11 18:00:56 UTC 2015 - benoit.monin@gmx.fr
- update to version 1.24:
* Bugfixes for reading files in Python 3 (by Anthony Tuininga and
pqqp)
* Appropriate errors are now raised instead of infinite loops (by
naure and Cyrus Vafadari)
* Bugfix for parsing number tokens with leading spaces (by Maxim
Kamenkov)
* Don't crash on bad /Outlines reference (by eshellman)
* Conform tabs/spaces and blank lines to PEP 8 standards
* Utilize the readUntilRegex method when reading Number Objects
(by Brendan Jurd)
* More bugfixes for Python 3 and clearer exception handling
* Fixed encoding issue in merger (with eshellman)
* Created separate folder for scripts
- additional changes from version 1.23:
* Documentation now available at http://pythonhosted.org//PyPDF2
* Bugfix in pagerange.py for when __init__.__doc__ has no value
(by Vladir Cruz)
* Fix typos in OutlinesObject().add() (by shilluc)
* Re-added a missing return statement in a utils.py method
* Corrected viewing mode names (by Jason Scheirer)
* New PdfFileWriter method: addJS() (by vfigueiro)
* New bookmark features: color, boldness, italics, and page fit
(by Joshua Arnott)
* New PdfFileReader method: getFields(). Used to extract field
information from PDFs with interactive forms. See documentation
for details
* Converted README file to markdown format (by Stephen Bussard)
* Several improvements to overall performance and efficiency (by
mozbugbox)
* Fixed a bug where geospatial information was not scaling along
with its page
* Fixed a type issue and a Python 3 issue in the decryption
algorithms (with Francisco Vieira and koba-ninkigumi)
* Fixed a bug causing an infinite loop in the ASCII 85 decoding
algorithm (by madmaardigan)
* Annotations (links, comment windows, etc.) are now preserved
when pages are merged together
* Used the Destination class in addLink() and addBookmark() so
that the page fit option could be properly customized
- additional changes from version 1.22:
* Added .DS_Store to .gitignore (for Mac users) (by Steve Witham)
* Removed __init__() implementation in NameObject (by Steve
Witham)
* Fixed bug (inf. loop) when merging pages in Python 3 (by commx)
* Corrected error when calculating height in scaleTo()
* Removed unnecessary code from DictionaryObject (by Georges
Dubus)
* Fixed bug where an exception was thrown upon reading a NULL
string (by speedplane)
* Allow string literals (non-unicode strings in Python 2) to be
passed to PdfFileReader
* Allow ConvertFunctionsToVirtualList to be indexed with slices
and longs (in Python 2) (by Matt Gilson)
* Major improvements and bugfixes to addLink() method (see
documentation in source code) (by Henry Keiter)
* General code clean-up and improvements (with Steve Witham and
Henry Keiter)
* Fixed bug that caused crash when comments are present at end of
dictionary
- additional changes from version 1.21:
* Fix for when /Type isn't present in the Pages dictionary (by
Rob1080)
* More tolerance for extra whitespace in Indirect Objects
* Improved Exception handling
* Fixed error in getHeight() method (by Simon Kaempflein)
* implement use of utils.string_type to resolve Py2-3
compatibility issues
* Prevent exception for multiple definitions in a dictionary
(with carlosfunk) (only when strict = False)
* Fixed errors when parsing a slice using pdfcat on command line
(by Steve Witham)
* Tolerance for EOF markers within 1024 bytes of the actual end
of the file (with David Wolever)
* Added overwriteWarnings parameter to PdfFileReader constructor,
if False PyPDF2 will NOT overwrite methods from Python's
warnings.py module with a custom implementation.
* Fix NumberObject and NameObject constructors for compatibility
with PyPy (Rüdiger Jungbeck, Xavier Dupré, shezadkhan137,
Steven Witham)
* Utilize utils.Str in pdf.py and pagerange.py to resolve type
issues (by egbutter)
* Improvements in implementing StringIO for Python 2 and BytesIO
for Python 3 (by Xavier Dupré)
* Added /x00 to Whitespaces, defined utils.WHITESPACES to clarify
code (by Maxim Kamenkov)
* Bugfix for merging 3 or more resources with the same name (by
lucky-user)
* Improvements to Xref parsing algorithm (by speedplane)
- additional changes from version 1.20:
* Official Python 3+ support (with contributions from TWAC and
cgammans) Support for Python versions 2.6 and 2.7 will be
maintained
* Command line concatenation (see pdfcat in sample code) (by
Steve Witham)
* New FAQ; link included in README
* Allow more (although unnecessary) escape sequences
* Prevent exception when reading a null object in decoding
parameters
* Corrected error in reading destination types (added a slash
since they are name objects)
* Corrected TypeError in scaleTo() method
* addBookmark() method in PdfFileMerger now returns bookmark (so
nested bookmarks can be created)
* Additions to Sample Code and Sample PDFs
* changes to allow 2up script to work (see sample code) (by Dylan
McNamee)
* changes to metadata encoding (by Chris Hiestand)
* New methods for links: addLink() (by Enrico Lambertini) and
removeLinks()
* Bugfix to handle nested bookmarks correctly (by Jamie Lentin)
* New methods removeImages() and removeText() available for
PdfFileWriter (by Tien Haï)
* Exception handling for illegal characters in Name Objects
- remove unwanted shebang in pagerange.py
- rename README to README.md: changed upstream
-------------------------------------------------------------------
Tue Dec 3 10:52:18 UTC 2013 - cfarrell@suse.com
- license update: BSD-3-Clause
See LICENSE
-------------------------------------------------------------------
Sun Nov 24 21:44:43 UTC 2013 - p.drouand@gmail.com
- Initial release ( version 1.19 )

80
python-PyPDF2.spec Normal file
View File

@@ -0,0 +1,80 @@
#
# spec file for package python-PyPDF2
#
# Copyright (c) 2026 SUSE LLC and contributors
#
# All modifications and additions to the file contributed by third parties
# remain the property of their copyright owners, unless otherwise agreed
# upon. The license for this file, and modifications and additions to the
# file, is the same license as for the pristine package itself (unless the
# license for the pristine package is not an Open Source License, in which
# case the license is the MIT License). An "Open Source License" is a
# license that conforms to the Open Source Definition (Version 1.9)
# published by the Open Source Initiative.
# Please submit bugfixes or comments via https://bugs.opensuse.org/
#
%{?sle15_python_module_pythons}
Name: python-PyPDF2
Version: 2.11.1
Release: 0
Summary: PDF toolkit
License: BSD-3-Clause
Group: Development/Languages/Python
URL: https://github.com/py-pdf/PyPDF2
Source: https://github.com/py-pdf/PyPDF2/archive/refs/tags/%{version}.tar.gz
# PATCH-FIX-UPSTREAM CVE-2025-55197.patch bsc#1248089
Patch0: CVE-2025-55197.patch
# PATCH-FIX-UPSTREAM CVE-2026-27024.patch bsc#1258691
Patch1: CVE-2026-27024.patch
# PATCH-FIX-UPSTREAM CVE-2026-27025.patch bsc#1258692
Patch2: CVE-2026-27025.patch
# PATCH-FIX-UPSTREAM CVE-2026-27026.patch bsc#1258693
Patch3: CVE-2026-27026.patch
BuildRequires: %{python_module pip}
BuildRequires: %{python_module setuptools}
BuildRequires: %{python_module wheel}
BuildRequires: fdupes
BuildRequires: python-rpm-macros
BuildArch: noarch
%python_subpackages
%description
A Pure-Python library built as a PDF toolkit. It is capable of:
- extracting document information (title, author, ...),
- splitting documents page by page,
- merging documents page by page,
- cropping pages,
- merging multiple pages into a single page,
- encrypting and decrypting PDF files.
By being Pure-Python, it should run on any Python platform without any
dependencies on external libraries. It can also work entirely on StringIO
objects rather than file streams, allowing for PDF manipulation in memory.
It is therefore a useful tool for websites that manage or manipulate PDFs.
%prep
%autosetup -p1 -n PyPDF2-%{version}
#remove unwanted shebang
sed -i '/^#!/ d' PyPDF2/pagerange.py
%build
%pyproject_wheel
%install
%pyproject_install
%python_expand %fdupes %{buildroot}%{$python_sitelib}
chmod a-x CHANGELOG.md LICENSE README.md
# many tests need internet connection, cannot be run on OBS
%files %{python_files}
%license LICENSE
%doc CHANGELOG.md README.md
%{python_sitelib}/PyPDF2
%{python_sitelib}/[Pp]y[Pp][Dd][Ff]2-%{version}*-info
%changelog