Skip to content

Avoid unused object ids when saving PDF #10091

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
radarhere merged 2 commits into from
Oct 2, 2026
Merged

Avoid unused object ids when saving PDF #10091

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8665cd5
Allocate PDF image objects when they are written
Rodrigo-Palma Oct 1, 2026
98036ad
Add comment
radarhere Oct 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions Tests/test_file_pdf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,6 +179,17 @@ def im_generator(ims: list[Image.Image]) -> Generator[Image.Image]:
assert os.path.getsize(outfile) > 0


def test_save_all_object_ids(tmp_path: Path) -> None:
outfile = str(tmp_path / "temp.pdf")
with Image.open("Tests/images/transparent_dispose.gif") as im:
im.save(outfile, save_all=True)

with PdfParser.PdfParser(outfile) as pdf:
# Test that each object id was used
for object_id in pdf.xref_table.existing_entries:
pdf.read_indirect(PdfParser.IndirectReference(object_id, 0))


def test_multiframe_normal_save(tmp_path: Path) -> None:
# Test saving a multiframe image without save_all
with Image.open("Tests/images/dispose_bgnd.gif") as im:
Expand Down
15 changes: 4 additions & 11 deletions src/PIL/PdfImagePlugin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,6 @@ def _write_image(
im: Image.Image,
filename: str | bytes,
existing_pdf: PdfParser.PdfParser,
image_refs: list[PdfParser.IndirectReference],
) -> tuple[PdfParser.IndirectReference, str]:
# FIXME: Should replace ASCIIHexDecode with RunLengthDecode
# (packbits) or LZWDecode (tiff/lzw compression). Note that
Expand Down Expand Up @@ -118,7 +117,7 @@ def _write_image(
smask = im.convert("LA").getchannel("A")
smask.encoderinfo = {}

image_ref = _write_image(smask, filename, existing_pdf, image_refs)[0]
image_ref = _write_image(smask, filename, existing_pdf)[0]
dict_obj["SMask"] = image_ref
elif im.mode == "RGB":
decode_filter = "DCTDecode"
Expand Down Expand Up @@ -173,9 +172,8 @@ def _write_image(
else:
filter = PdfParser.PdfName(decode_filter)

image_ref = image_refs.pop(0)
existing_pdf.write_obj(
image_ref,
image_ref = existing_pdf.write_obj(
None,
stream=stream,
Type=PdfParser.PdfName("XObject"),
Subtype=PdfParser.PdfName("Image"),
Expand Down Expand Up @@ -241,7 +239,6 @@ def _save(
append_im.encoderinfo = im.encoderinfo.copy()
ims.append(append_im)
number_of_pages = 0
image_refs = []
page_refs = []
contents_refs = []
for im in ims:
Expand All @@ -250,10 +247,6 @@ def _save(
im_number_of_pages = getattr(im, "n_frames", 1)
number_of_pages += im_number_of_pages
for i in range(im_number_of_pages):
image_refs.append(existing_pdf.next_object_id(0))
if im.mode == "P" and "transparency" in im.info:
image_refs.append(existing_pdf.next_object_id(0))

page_refs.append(existing_pdf.next_object_id(0))
contents_refs.append(existing_pdf.next_object_id(0))
existing_pdf.pages.append(page_refs[-1])
Expand All @@ -268,7 +261,7 @@ def _save(
ImageSequence.Iterator(im_sequence) if save_all else [im_sequence]
)
for im in im_pages:
image_ref, procset = _write_image(im, filename, existing_pdf, image_refs)
image_ref, procset = _write_image(im, filename, existing_pdf)

#
# page
Expand Down
Loading