STY: Apply fixes suggested by pylint

* Use f-strings: They are more readable and faster than other
                 string formatting options

.pre-commit-config.yaml

@@ -33,11 +33,6 @@ repos:
     hooks:
     -   id: black
         args: [--target-version, py36]
-# -   repo: https://github.com/asottile/pyupgrade
-#     rev: v2.31.1
-#     hooks:
-#     -   id: pyupgrade
-#         args: [--py36-plus]
 -   repo: https://github.com/asottile/blacken-docs
     rev: v1.12.1
     hooks:

PyPDF2/__init__.py

@@ -1,3 +1,12 @@
+"""
+PyPDF2 is a free and open-source pure-python PDF library capable of splitting,
+merging, cropping, and transforming the pages of PDF files. It can also add
+custom data, viewing options, and passwords to PDF files. PyPDF2 can retrieve
+text and metadata from PDFs as well.
+
+You can read the full docs at https://pypdf2.readthedocs.io/.
+"""
+
 from ._merger import PdfFileMerger, PdfMerger
 from ._page import PageObject, Transformation
 from ._reader import DocumentInformation, PdfFileReader, PdfReader

PyPDF2/_reader.py

@@ -1317,7 +1317,7 @@ def read(self, stream: StreamType) -> None:
                 for id in self.xref[gen]:
                     stream.seek(self.xref[gen][id], 0)
                     try:
-                        pid, pgen = self.read_object_header(stream)
+                        pid, _pgen = self.read_object_header(stream)
                     except ValueError:
                         break
                     if pid == id - self.xref_index:
@@ -1678,8 +1678,8 @@ def _decrypt(self, password: Union[str, bytes]) -> int:
                 val = real_O
                 for i in range(19, -1, -1):
                     new_key = b""
-                    for l in range(len(key)):
-                        new_key += b_(chr(ord_(key[l]) ^ i))
+                    for key_char in key:
+                        new_key += b_(chr(ord_(key_char) ^ i))
                     val = RC4_encrypt(new_key, val)
                 userpass = val
             owner_password, key = self._authenticate_user_password(userpass)

PyPDF2/_security.py

@@ -119,8 +119,8 @@ def _alg33(owner_pwd: str, user_pwd: str, rev: int, keylen: int) -> bytes:
     if rev >= 3:
         for i in range(1, 20):
             new_key = ""
-            for l in range(len(key)):
-                new_key += chr(ord_(key[l]) ^ i)
+            for key_char in key:
+                new_key += chr(ord_(key_char) ^ i)
             val = RC4_encrypt(new_key, val)
     # 8. Store the output from the final invocation of the RC4 as the value of
     # the /O entry in the encryption dictionary.
@@ -233,10 +233,10 @@ def RC4_encrypt(key: Union[str, bytes], plaintext: bytes) -> bytes:
         S[i], S[j] = S[j], S[i]
     i, j = 0, 0
     retval = []
-    for x in range(len(plaintext)):
+    for plaintext_char in plaintext:
         i = (i + 1) % 256
         j = (j + S[i]) % 256
         S[i], S[j] = S[j], S[i]
         t = S[(S[i] + S[j]) % 256]
-        retval.append(b_(chr(ord_(plaintext[x]) ^ t)))
+        retval.append(b_(chr(ord_(plaintext_char) ^ t)))
     return b"".join(retval)

PyPDF2/_writer.py

@@ -224,7 +224,7 @@ def get_page(self, pageNumber: int) -> PageObject:  # TODO: PEP8
         :rtype: :class:`PageObject<PyPDF2._page.PageObject>`
         """
         pages = cast(Dict[str, Any], self.get_object(self._pages))
-        # XXX: crude hack
+        # TODO: crude hack
         return pages[PA.KIDS][pageNumber].get_object()
 
     def getPage(self, pageNumber: int) -> PageObject:  # pragma: no cover
@@ -693,10 +693,8 @@ def write(self, stream: StreamType) -> None:
         """
         if hasattr(stream, "mode") and "b" not in stream.mode:
             warnings.warn(
-                (
-                    "File <{}> to write to is not in binary mode. "  # type: ignore
-                    "It may not be written to correctly."
-                ).format(stream.name)
+                f"File <{stream.name}> to write to is not in binary mode. "
+                "It may not be written to correctly."
             )
 
         if not self._root:
@@ -712,8 +710,7 @@ def write(self, stream: StreamType) -> None:
         # we sweep for indirect references.  This forces self-page-referencing
         # trees to reference the correct new object location, rather than
         # copying in a new copy of the page object.
-        for obj_index in range(len(self._objects)):
-            obj = self._objects[obj_index]
+        for obj_index, obj in enumerate(self._objects):
             if isinstance(obj, PageObject) and obj.indirect_ref is not None:
                 data = obj.indirect_ref
                 if data.pdf not in external_reference_map:
@@ -731,13 +728,13 @@ def write(self, stream: StreamType) -> None:
         object_positions = self._write_header(stream)
         xref_location = self._write_xref_table(stream, object_positions)
         self._write_trailer(stream)
-        stream.write(b_("\nstartxref\n%s\n%%%%EOF\n" % (xref_location)))  # eof
+        stream.write(b_(f"\nstartxref\n{xref_location}\n%%EOF\n"))  # eof
 
     def _write_header(self, stream: StreamType) -> List[int]:
         object_positions = []
         stream.write(self._header + b"\n")
         stream.write(b"%\xE2\xE3\xCF\xD3\n")
-        for i in range(len(self._objects)):
+        for i, obj in enumerate(self._objects):
             obj = self._objects[i]
             # If the obj is None we can't write anything
             if obj is not None:
@@ -1236,8 +1233,7 @@ def remove_images(self, ignore_byte_string_object: bool = False) -> None:
             b"Do",
             b"sh",
         )
-        for j in range(len(pages)):
-            page = pages[j]
+        for page in pages:
             page_ref = cast(DictionaryObject, self.get_object(page))
             content = page_ref["/Contents"].get_object()
             if not isinstance(content, ContentStream):
@@ -1298,8 +1294,7 @@ def remove_text(self, ignore_byte_string_object: bool = False) -> None:
         """
         pg_dict = cast(DictionaryObject, self.get_object(self._pages))
         pages = cast(List[IndirectObject], pg_dict[PA.KIDS])
-        for j in range(len(pages)):
-            page = pages[j]
+        for page in pages:
             page_ref = cast(Dict[str, Any], self.get_object(page))
             content = page_ref["/Contents"].get_object()
             if not isinstance(content, ContentStream):

PyPDF2/filters.py

@@ -232,8 +232,7 @@ def next_code(self) -> int:
                     return -1
                 nextbits = ord_(self.data[self.bytepos])
                 bitsfromhere = 8 - self.bitpos
-                if bitsfromhere > fillbits:
-                    bitsfromhere = fillbits
+                bitsfromhere = min(bitsfromhere, fillbits)
                 value |= (
                     (nextbits >> (8 - self.bitpos - bitsfromhere))
                     & (0xFF >> (8 - bitsfromhere))

PyPDF2/generic.py

@@ -1887,8 +1887,7 @@ def createStringObject(
         elif isinstance(forced_encoding, str):
             if forced_encoding == "bytes":
                 return ByteStringObject(string)
-            else:
-                return TextStringObject(string.decode(forced_encoding))
+            return TextStringObject(string.decode(forced_encoding))
         else:
             try:
                 if string.startswith(codecs.BOM_UTF16_BE):