MAINT: Package updates; solve mypy strict remarks (#1163)

Author: MartinThoma

.pre-commit-config.yaml

@@ -30,7 +30,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 22.6.0
     hooks:
     -   id: black
         args: [--target-version, py36]
@@ -40,7 +40,7 @@ repos:
     -   id: blacken-docs
         additional_dependencies: [black==22.1.0]
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.34.0
+    rev: v2.37.2
     hooks:
     -   id: pyupgrade
         args: [--py36-plus]

Makefile

@@ -31,3 +31,6 @@ mutation-results:
 
 benchmark:
 	pytest tests/bench.py
+
+mypy:
+	mypy PyPDF2 --ignore-missing-imports --check-untyped --strict

PyPDF2/_cmap.py

@@ -56,12 +56,12 @@ def build_char_map(
         float(sp_width / 2),
         encoding,
         # https://github.com/python/mypy/issues/4374
-        map_dict,  # type: ignore
-    )  # type: ignore
+        map_dict,
+    )
 
 
 # used when missing data, e.g. font def missing
-unknown_char_map: Tuple[str, float, Union[str, Dict[int, str]], Dict] = (
+unknown_char_map: Tuple[str, float, Union[str, Dict[int, str]], Dict[Any, Any]] = (
     "Unknown",
     9999,
     dict(zip(range(256), ["�"] * 256)),
@@ -108,15 +108,15 @@ def parse_encoding(
     encoding: Union[str, List[str], Dict[int, str]] = []
     if "/Encoding" not in ft:
         try:
-            if "/BaseFont" in ft and ft["/BaseFont"] in charset_encoding:
+            if "/BaseFont" in ft and cast(str, ft["/BaseFont"]) in charset_encoding:
                 encoding = dict(
                     zip(range(256), charset_encoding[cast(str, ft["/BaseFont"])])
                 )
             else:
                 encoding = "charmap"
             return encoding, _default_fonts_space_width[cast(str, ft["/BaseFont"])]
         except Exception:
-            if ft["/Subtype"] == "/Type1":
+            if cast(str, ft["/Subtype"]) == "/Type1":
                 return "charmap", space_code
             else:
                 return "", space_code
@@ -314,7 +314,7 @@ def compute_space_width(
         except Exception:
             w1[-1] = 1000.0
         if "/W" in ft1:
-            w = list(ft1["/W"])  # type: ignore
+            w = list(ft1["/W"])
         else:
             w = []
         while len(w) > 0:

PyPDF2/_encryption.py

@@ -29,10 +29,10 @@
 import random
 import struct
 from enum import IntEnum
-from typing import Optional, Tuple, Union, cast
+from typing import Any, Dict, Optional, Tuple, Union, cast
 
-from PyPDF2.errors import DependencyError
 from PyPDF2._utils import logger_warning
+from PyPDF2.errors import DependencyError
 from PyPDF2.generic import (
     ArrayObject,
     ByteStringObject,
@@ -566,7 +566,7 @@ def verify_perms(
     @staticmethod
     def generate_values(
         user_pwd: bytes, owner_pwd: bytes, key: bytes, p: int, metadata_encrypted: bool
-    ) -> dict:
+    ) -> Dict[Any, Any]:
         u_value, ue_value = AlgV5.compute_U_value(user_pwd, key)
         o_value, oe_value = AlgV5.compute_O_value(owner_pwd, key, u_value)
         perms = AlgV5.compute_Perms_value(key, p, metadata_encrypted)

PyPDF2/_merger.py

@@ -556,7 +556,7 @@ def find_bookmark(
                 res = self.find_bookmark(bookmark, b)  # type: ignore
                 if res:
                     return [i] + res
-            elif b == bookmark or b["/Title"] == bookmark:
+            elif b == bookmark or cast(Dict[Any, Any], b["/Title"]) == bookmark:
                 # we found a leaf node
                 return [i]
 

PyPDF2/_page.py

@@ -506,9 +506,9 @@ def _merge_page(
         # Combine /ProcSet sets.
         new_resources[NameObject(RES.PROC_SET)] = ArrayObject(
             frozenset(
-                original_resources.get(RES.PROC_SET, ArrayObject()).get_object()  # type: ignore
+                original_resources.get(RES.PROC_SET, ArrayObject()).get_object()
             ).union(
-                frozenset(page2resources.get(RES.PROC_SET, ArrayObject()).get_object())  # type: ignore
+                frozenset(page2resources.get(RES.PROC_SET, ArrayObject()).get_object())
             )
         )
 
@@ -1248,7 +1248,7 @@ def process_operation(operator: bytes, operands: List) -> None:
                         cmaps[operands[0]][2],
                         cmaps[operands[0]][3],
                         operands[0],
-                    )  # type:ignore
+                    )
                 except KeyError:  # font not found
                     _space_width = unknown_char_map[1]
                     cmap = (
@@ -1395,7 +1395,7 @@ def process_operation(operator: bytes, operands: List) -> None:
                 except IndexError:
                     pass
                 try:
-                    xobj = resources_dict["/XObject"]  # type: ignore
+                    xobj = resources_dict["/XObject"]
                     if xobj[operands[0]]["/Subtype"] != "/Image":  # type: ignore
                         # output += text
                         text = self.extract_xform_text(xobj[operands[0]], space_width)  # type: ignore

PyPDF2/_reader.py

@@ -861,7 +861,9 @@ def _build_outline(self, node: DictionaryObject) -> Optional[Destination]:
         elif isinstance(dest, str):
             # named destination, addresses NameObject Issue #193
             try:
-                outline = self._build_destination(title, self._namedDests[dest].dest_array)  # type: ignore
+                outline = self._build_destination(
+                    title, self._namedDests[dest].dest_array
+                )
             except KeyError:
                 # named destination not found in Name Dict
                 outline = self._build_destination(title, None)
@@ -1045,7 +1047,7 @@ def _get_object_from_stream(
         stmnum, idx = self.xref_objStm[indirect_reference.idnum]
         obj_stm: EncodedStreamObject = IndirectObject(stmnum, 0, self).get_object()  # type: ignore
         # This is an xref to a stream, so its type better be a stream
-        assert obj_stm["/Type"] == "/ObjStm"
+        assert cast(str, obj_stm["/Type"]) == "/ObjStm"
         # /N is the number of indirect objects in the stream
         assert idx < obj_stm["/N"]
         stream_data = BytesIO(b_(obj_stm.get_data()))  # type: ignore
@@ -1501,7 +1503,7 @@ def _read_pdf15_xref_stream(
         stream.seek(-1, 1)
         idnum, generation = self.read_object_header(stream)
         xrefstream = cast(ContentStream, read_object(stream, self))
-        assert xrefstream["/Type"] == "/XRef"
+        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

PyPDF2/_utils.py

@@ -46,7 +46,7 @@
     # Python 3.10+: https://www.python.org/dev/peps/pep-0484/
     from typing import TypeAlias  # type: ignore[attr-defined]
 except ImportError:
-    from typing_extensions import TypeAlias  # type: ignore[misc]
+    from typing_extensions import TypeAlias
 
 from .errors import STREAM_TRUNCATED_PREMATURELY, PdfStreamError
 
@@ -130,7 +130,7 @@ def skip_over_comment(stream: StreamType) -> None:
 
 
 def read_until_regex(
-    stream: StreamType, regex: Pattern, ignore_eof: bool = False
+    stream: StreamType, regex: Pattern[bytes], ignore_eof: bool = False
 ) -> bytes:
     """
     Read until the regular expression pattern matched (ignore the match).

PyPDF2/_writer.py

@@ -195,7 +195,7 @@ def getObject(self, ido: IndirectObject) -> PdfObject:  # pragma: no cover
     def _add_page(
         self, page: PageObject, action: Callable[[Any, IndirectObject], None]
     ) -> None:
-        assert page[PA.TYPE] == CO.PAGE
+        assert cast(str, page[PA.TYPE]) == CO.PAGE
         if page.pdf is not None:
             other = page.pdf.pdf_header
             if isinstance(other, str):
@@ -292,7 +292,7 @@ def get_page(
             raise ValueError("Please specify the page_number")
         pages = cast(Dict[str, Any], self.get_object(self._pages))
         # TODO: crude hack
-        return pages[PA.KIDS][page_number].get_object()
+        return cast(PageObject, pages[PA.KIDS][page_number].get_object())
 
     def getPage(self, pageNumber: int) -> PageObject:  # pragma: no cover
         """

PyPDF2/generic.py

@@ -192,7 +192,7 @@ def readFromStream(stream: StreamType) -> "BooleanObject":  # pragma: no cover
 
 
 class ArrayObject(list, PdfObject):
-    def items(self) -> Iterable:
+    def items(self) -> Iterable[Any]:
         """
         Emulate DictionaryObject.items for a list
         (index, object)
@@ -517,7 +517,7 @@ def read_string_from_stream(
     return create_string_object(txt, forced_encoding)
 
 
-class ByteStringObject(bytes, PdfObject):  # type: ignore
+class ByteStringObject(bytes, PdfObject):
     """
     Represents a string object where the text encoding could not be determined.
     This occurs quite often, as the PDF spec doesn't provide an alternate way to