Merge branch 'main' into nbits-image

.pre-commit-config.yaml

@@ -22,23 +22,23 @@ repos:
 # hooks:
 # - id: mypy
 - repo: https://github.com/psf/black
- rev: 23.3.0
+ rev: 23.7.0
  hooks:
  - id: black
  args: [--target-version, py36]
 - repo: https://github.com/asottile/blacken-docs
- rev: 1.14.0
+ rev: 1.15.0
  hooks:
  - id: blacken-docs
  additional_dependencies: [black==22.1.0]
  exclude: "docs/user/robustness.md"
 - repo: https://github.com/charliermarsh/ruff-pre-commit
- rev: 'v0.0.275'
+ rev: 'v0.0.278'
  hooks:
  - id: ruff
  args: ['--fix']
 - repo: https://github.com/asottile/pyupgrade
- rev: v3.7.0
+ rev: v3.9.0
  hooks:
  - id: pyupgrade
  args: [--py36-plus]

pypdf/_encryption.py

@@ -194,10 +194,7 @@ def encrypt_object(self, obj: PdfObject) -> PdfObject:
  obj2[key] = self.encrypt_object(value)
  obj = obj2
  elif isinstance(obj, ArrayObject):
- obj2 = ArrayObject() # type: ignore
- for x in obj:
- obj2.append(self.encrypt_object(x)) # type: ignore
- obj = obj2
+ obj = ArrayObject(self.encrypt_object(x) for x in obj) # type: ignore
  return obj
 
  def decrypt_object(self, obj: PdfObject) -> PdfObject:

pypdf/_page.py

@@ -978,7 +978,7 @@ def replace_contents(
  self[NameObject(PG.CONTENTS)] = content
 
  def merge_page(
- self, page2: "PageObject", expand: bool = False,  over: bool = True
+ self, page2: "PageObject", expand: bool = False, over: bool = True
  ) -> None:
  """
  Merge the content streams of two pages into one.
@@ -1046,7 +1046,7 @@ def _merge_page(
  annots = page[PG.ANNOTS]
  if isinstance(annots, ArrayObject):
  for ref in annots:
- new_annots.append(ref)
+ new_annots.append(ref) # noqa: PERF402
 
  for res in (
  RES.EXT_G_STATE,

pypdf/_reader.py

@@ -2217,11 +2217,7 @@ def _list_attachments(self) -> List[str]:
  )
  except KeyError:
  return []
- attachments_names = []
- # Loop through attachments
- for f in filenames:
- if isinstance(f, str):
- attachments_names.append(f)
+ attachments_names = [f for f in filenames if isinstance(f, str)]
  return attachments_names
 
  def _get_attachment_list(self, name: str) -> List[bytes]:

pypdf/_writer.py

@@ -956,9 +956,7 @@ def update_page_form_field_values(
  or self._get_qualified_field_name(writer_annot) == field
  ):
  if isinstance(value, list):
- lst = ArrayObject()
- for v in value:
- lst.append(TextStringObject(v))
+ lst = ArrayObject(TextStringObject(v) for v in value)
  writer_annot[NameObject(FA.V)] = lst
  else:
  writer_annot[NameObject(FA.V)] = TextStringObject(value)
@@ -3395,10 +3393,7 @@ def _pdf_objectify(obj: Union[Dict[str, Any], str, int, List[Any]]) -> PdfObject
  to_add[name_key] = casted_value
  return to_add
  elif isinstance(obj, list):
- arr = ArrayObject()
- for el in obj:
- arr.append(_pdf_objectify(el))
- return arr
+ return ArrayObject(_pdf_objectify(el) for el in obj)
  elif isinstance(obj, str):
  if obj.startswith("/"):
  return NameObject(obj)

pyproject.toml

@@ -183,6 +183,8 @@ ignore = [
  "S101", # Use of `assert` detected
  "SLF001", # Private member accessed
  "PD011", # Use `.to_numpy()` instead of `.values`
+ "FA102", # Missing `from __future__ import annotations`, but uses PEP 604 union
+ "PERF203", # `try`-`except` within a loop incurs performance overhead
 ]
 
 [tool.ruff.per-file-ignores]

requirements/ci-3.11.txt

@@ -61,7 +61,7 @@ pytest-socket==0.6.0
  # via -r requirements/ci.in
 pytest-timeout==2.1.0
  # via -r requirements/ci.in
-ruff==0.0.275
+ruff==0.0.278
  # via -r requirements/ci.in
 typeguard==3.0.2
  # via -r requirements/ci.in

tests/test_reader.py

@@ -712,7 +712,7 @@ def get_dest_pages(x) -> int:
 
  # oi can be destination or a list:preferred to just print them
  for oi in outline:
- out.append(get_dest_pages(oi))
+ out.append(get_dest_pages(oi)) # noqa: PERF401
 
 
 def test_decode_permissions():

tests/test_xmp.py

@@ -71,9 +71,7 @@ def get_all_tiff(xmp: pypdf.xmp.XmpInformation):
  about_uri="", namespace="http://ns.adobe.com/tiff/1.0/"
  )
  for tag in tiff_ns:
- contents = []
- for content in tag.childNodes:
- contents.append(content.data)
+ contents = [content.data for content in tag.childNodes]
  data[tag.tagName] = contents
  return data