STY: Apply ruff suggestions (#1570)

Author: MartinThoma

make_changelog.py

@@ -27,7 +27,8 @@ def main(changelog_path: str):
     today = datetime.now()
     header = f"Version {new_version}, {today:%Y-%m-%d}\n"
     header = header + "-" * (len(header) - 1) + "\n"
-    trailer = f"\n[Full Changelog](https://github.com/py-pdf/pypdf/compare/{git_tag}...{new_version})\n\n"
+    url = f"https://github.com/py-pdf/pypdf/compare/{git_tag}...{new_version}"
+    trailer = f"\n[Full Changelog]({url})\n\n"
     new_entry = header + changes + trailer
     print(new_entry)
 

pypdf/_cmap.py

@@ -27,16 +27,20 @@ def build_char_map(
     encoding, space_code = parse_encoding(ft, space_code)
     map_dict, space_code, int_entry = parse_to_unicode(ft, space_code)
 
-    # encoding can be either a string for decode (on 1,2 or a variable number of bytes) of a char table (for 1 byte only for me)
-    # if empty string, it means it is than encoding field is not present and we have to select the good encoding from cmap input data
+    # encoding can be either a string for decode
+    # (on 1,2 or a variable number of bytes) of a char table (for 1 byte only for me)
+    # if empty string, it means it is than encoding field is not present and
+    # we have to select the good encoding from cmap input data
     if encoding == "":
         if -1 not in map_dict or map_dict[-1] == 1:
             # I have not been able to find any rule for no /Encoding nor /ToUnicode
             # One example shows /Symbol,bold I consider 8 bits encoding default
             encoding = "charmap"
         else:
             encoding = "utf-16-be"
-    # apply rule from PDF ref 1.7 §5.9.1, 1st bullet : if cmap not empty encoding should be discarded (here transformed into identity for those characters)
+    # apply rule from PDF ref 1.7 §5.9.1, 1st bullet :
+    #   if cmap not empty encoding should be discarded
+    #   (here transformed into identity for those characters)
     # if encoding is an str it is expected to be a identity translation
     elif isinstance(encoding, dict):
         for x in int_entry:
@@ -131,7 +135,9 @@ def parse_encoding(
     enc: Union(str, DictionaryObject) = ft["/Encoding"].get_object()  # type: ignore
     if isinstance(enc, str):
         try:
-            # allready done : enc = NameObject.unnumber(enc.encode()).decode()  # for #xx decoding
+            # allready done :
+            #       enc = NameObject.unnumber(enc.encode()).decode()
+            # for #xx decoding
             if enc in charset_encoding:
                 encoding = charset_encoding[enc].copy()
             elif enc in _predefined_cmap:
@@ -214,10 +220,12 @@ def prepare_cm(ft: DictionaryObject) -> bytes:
     if isinstance(tu, StreamObject):
         cm = cast(DecodedStreamObject, ft["/ToUnicode"]).get_data()
     elif isinstance(tu, str) and tu.startswith("/Identity"):
-        cm = b"beginbfrange\n<0000> <0001> <0000>\nendbfrange"  # the full range 0000-FFFF will be processed
+        # the full range 0000-FFFF will be processed
+        cm = b"beginbfrange\n<0000> <0001> <0000>\nendbfrange"
     if isinstance(cm, str):
         cm = cm.encode()
-    # we need to prepare cm before due to missing return line in pdf printed to pdf from word
+    # we need to prepare cm before due to missing return line in pdf printed
+    # to pdf from word
     cm = (
         cm.strip()
         .replace(b"beginbfchar", b"\nbeginbfchar\n")

pypdf/_encryption.py

@@ -178,7 +178,8 @@ def merge(
                 )
             else:
                 raise ValueError(
-                    "The argument position of merge is deprecated. Use page_number only."
+                    "The argument position of merge is deprecated. "
+                    "Use page_number only."
                 )
 
         if page_number is None:  # deprecated
@@ -335,7 +336,8 @@ def write(self, fileobj: Union[Path, StrByteType]) -> None:
             page.out_pagedata = self.output.get_reference(
                 pages_obj[PA.KIDS][-1].get_object()
             )
-            # idnum = self.output._objects.index(self.output._pages.get_object()[PA.KIDS][-1].get_object()) + 1
+            # key_temp = self.output._pages.get_object()[PA.KIDS][-1].get_object()
+            # idnum = self.output._objects.index(key_temp) + 1
             # page.out_pagedata = IndirectObject(idnum, 0, self.output)
 
         # Once all pages are added, create outline items to point at those pages
@@ -703,7 +705,8 @@ def add_outline_item(
         """
         if page_number is not None and pagenum is not None:
             raise ValueError(
-                "The argument pagenum of add_outline_item is deprecated. Use page_number only."
+                "The argument pagenum of add_outline_item is deprecated. "
+                "Use page_number only."
             )
         if pagenum is not None:
             old_term = "pagenum"
@@ -809,7 +812,8 @@ def add_named_destination(
         """
         if page_number is not None and pagenum is not None:
             raise ValueError(
-                "The argument pagenum of add_named_destination is deprecated. Use page_number only."
+                "The argument pagenum of add_named_destination is deprecated. "
+                "Use page_number only."
             )
         if pagenum is not None:
             old_term = "pagenum"

pypdf/_merger.py

@@ -94,17 +94,20 @@ def set_custom_rtl(
             If set to `None`, the value will not be changed.
             If set to an integer or string, it will be converted to its ASCII code.
             The default value is -1, which sets no additional range to be converted.
-        _max: The new maximum value for the range of custom characters that will be written right to left.
+        _max: The new maximum value for the range of custom characters that will
+            be written right to left.
             If set to `None`, the value will not be changed.
             If set to an integer or string, it will be converted to its ASCII code.
             The default value is -1, which sets no additional range to be converted.
-        specials: The new list of special characters to be inserted in the current insertion order.
+        specials: The new list of special characters to be inserted in the
+            current insertion order.
             If set to `None`, the current value will not be changed.
             If set to a string, it will be converted to a list of ASCII codes.
             The default value is an empty list.
 
     Returns:
-        A tuple containing the new values for `CUSTOM_RTL_MIN`, `CUSTOM_RTL_MAX`, and `CUSTOM_RTL_SPECIAL_CHARS`.
+        A tuple containing the new values for `CUSTOM_RTL_MIN`,
+        `CUSTOM_RTL_MAX`, and `CUSTOM_RTL_SPECIAL_CHARS`.
     """
     global CUSTOM_RTL_MIN, CUSTOM_RTL_MAX, CUSTOM_RTL_SPECIAL_CHARS
     if isinstance(_min, int):
@@ -919,7 +922,8 @@ def mergeScaledPage(
         """
         deprecation_with_replacement(
             "page.mergeScaledPage(page2, scale, expand)",
-            "page2.add_transformation(Transformation().scale(scale)); page.merge_page(page2, expand)",
+            "page2.add_transformation(Transformation().scale(scale)); "
+            "page.merge_page(page2, expand)",
             "3.0.0",
         )
         op = Transformation().scale(scale, scale)
@@ -944,7 +948,8 @@ def mergeRotatedPage(
         """
         deprecation_with_replacement(
             "page.mergeRotatedPage(page2, rotation, expand)",
-            "page2.add_transformation(Transformation().rotate(rotation)); page.merge_page(page2, expand)",
+            "page2.add_transformation(Transformation().rotate(rotation)); "
+            "page.merge_page(page2, expand)",
             "3.0.0",
         )
         op = Transformation().rotate(rotation)
@@ -970,7 +975,8 @@ def mergeTranslatedPage(
         """
         deprecation_with_replacement(
             "page.mergeTranslatedPage(page2, tx, ty, expand)",
-            "page2.add_transformation(Transformation().translate(tx, ty)); page.merge_page(page2, expand)",
+            "page2.add_transformation(Transformation().translate(tx, ty)); "
+            "page.merge_page(page2, expand)",
             "3.0.0",
         )
         op = Transformation().translate(tx, ty)
@@ -1002,7 +1008,8 @@ def mergeRotatedTranslatedPage(
         """
         deprecation_with_replacement(
             "page.mergeRotatedTranslatedPage(page2, rotation, tx, ty, expand)",
-            "page2.add_transformation(Transformation().rotate(rotation).translate(tx, ty)); page.merge_page(page2, expand)",
+            "page2.add_transformation(Transformation().rotate(rotation).translate(tx, ty)); "
+            "page.merge_page(page2, expand)",
             "3.0.0",
         )
         op = Transformation().translate(-tx, -ty).rotate(rotation).translate(tx, ty)
@@ -1028,7 +1035,8 @@ def mergeRotatedScaledPage(
         """
         deprecation_with_replacement(
             "page.mergeRotatedScaledPage(page2, rotation, scale, expand)",
-            "page2.add_transformation(Transformation().rotate(rotation).scale(scale)); page.merge_page(page2, expand)",
+            "page2.add_transformation(Transformation().rotate(rotation).scale(scale)); "
+            "page.merge_page(page2, expand)",
             "3.0.0",
         )
         op = Transformation().rotate(rotation).scale(scale, scale)
@@ -1060,7 +1068,8 @@ def mergeScaledTranslatedPage(
         """
         deprecation_with_replacement(
             "page.mergeScaledTranslatedPage(page2, scale, tx, ty, expand)",
-            "page2.add_transformation(Transformation().scale(scale).translate(tx, ty)); page.merge_page(page2, expand)",
+            "page2.add_transformation(Transformation().scale(scale).translate(tx, ty)); "
+            "page.merge_page(page2, expand)",
             "3.0.0",
         )
         op = Transformation().scale(scale, scale).translate(tx, ty)
@@ -1095,7 +1104,8 @@ def mergeRotatedScaledTranslatedPage(
         """
         deprecation_with_replacement(
             "page.mergeRotatedScaledTranslatedPage(page2, rotation, tx, ty, expand)",
-            "page2.add_transformation(Transformation().rotate(rotation).scale(scale)); page.merge_page(page2, expand)",
+            "page2.add_transformation(Transformation().rotate(rotation).scale(scale)); "
+            "page.merge_page(page2, expand)",
             "3.0.0",
         )
         op = Transformation().rotate(rotation).scale(scale, scale).translate(tx, ty)
@@ -1359,10 +1369,13 @@ def _extract_text(
             while NameObject(PG.RESOURCES) not in objr:
                 # /Resources can be inherited sometimes so we look to parents
                 objr = objr["/Parent"].get_object()
-                # if no parents we will have no /Resources will be available => an exception wil be raised
+                # if no parents we will have no /Resources will be available
+                # => an exception wil be raised
             resources_dict = cast(DictionaryObject, objr[PG.RESOURCES])
         except Exception:
-            return ""  # no resources means no text is possible (no font) we consider the file as not damaged, no need to check for TJ or Tj
+            # no resources means no text is possible (no font) we consider the
+            # file as not damaged, no need to check for TJ or Tj
+            return ""
         if "/Font" in resources_dict:
             for f in cast(DictionaryObject, resources_dict["/Font"]):
                 cmaps[f] = build_char_map(f, space_width, obj)
@@ -1428,7 +1441,9 @@ def current_spacewidth() -> float:
             return _space_width / 1000.0
 
         def process_operation(operator: bytes, operands: List) -> None:
-            nonlocal cm_matrix, cm_stack, tm_matrix, tm_prev, output, text, char_scale, space_scale, _space_width, TL, font_size, cmap, orientations, rtl_dir, visitor_text
+            nonlocal cm_matrix, cm_stack, tm_matrix, tm_prev, output, text
+            nonlocal char_scale, space_scale, _space_width, TL, font_size, cmap
+            nonlocal orientations, rtl_dir, visitor_text
             global CUSTOM_RTL_MIN, CUSTOM_RTL_MAX, CUSTOM_RTL_SPECIAL_CHARS
 
             check_crlf_space: bool = False
@@ -1509,10 +1524,12 @@ def process_operation(operator: bytes, operands: List) -> None:
                 text = ""
                 # rtl_dir = False
                 try:
-                    # charMapTuple: font_type, float(sp_width / 2), encoding, map_dict, font-dictionary
+                    # charMapTuple: font_type, float(sp_width / 2), encoding,
+                    #               map_dict, font-dictionary
                     charMapTuple = cmaps[operands[0]]
                     _space_width = charMapTuple[1]
-                    # current cmap: encoding, map_dict, font resource name (internal name, not the real font-name),
+                    # current cmap: encoding, map_dict, font resource name
+                    #               (internal name, not the real font-name),
                     # font-dictionary. The font-dictionary describes the font.
                     cmap = (
                         charMapTuple[2],
@@ -1575,7 +1592,10 @@ def process_operation(operator: bytes, operands: List) -> None:
                                 t = tt.decode(
                                     cmap[0], "surrogatepass"
                                 )  # apply str encoding
-                            except Exception:  # the data does not match the expectation, we use the alternative ; text extraction may not be good
+                            except Exception:
+                                # the data does not match the expectation,
+                                # we use the alternative ;
+                                # text extraction may not be good
                                 t = tt.decode(
                                     "utf-16-be" if cmap[0] == "charmap" else "charmap",
                                     "surrogatepass",
@@ -1593,7 +1613,9 @@ def process_operation(operator: bytes, operands: List) -> None:
                         ):
                             xx = ord(x)
                             # fmt: off
-                            if (  # cases where the current inserting order is kept (punctuation,...)
+                            if (
+                                # cases where the current inserting order is
+                                # kept (punctuation,...)
                                 (xx <= 0x2F)                        # punctuations but...
                                 or (0x3A <= xx and xx <= 0x40)      # numbers (x30-39)
                                 or (0x2000 <= xx and xx <= 0x206F)  # upper punctuations..
@@ -1809,9 +1831,11 @@ def extract_text(
         will change if this function is made more sophisticated.
 
         Arabic, Hebrew,... are extracted in the good order.
-        If required an custom RTL range of characters can be defined; see function set_custom_rtl
+        If required an custom RTL range of characters can be defined;
+        see function set_custom_rtl
 
-        Additionally you can provide visitor-methods to get informed on all operands and all text-objects.
+        Additionally you can provide visitor-methods to get informed on all
+        operands and all text-objects.
         For example in some PDF files this can be useful to parse tables.
 
         Args:
@@ -1938,9 +1962,9 @@ def _get_fonts(self) -> Tuple[Set[str], Set[str]]:
 
     mediabox = _create_rectangle_accessor(PG.MEDIABOX, ())
     """
-    A :class:`RectangleObject<pypdf.generic.RectangleObject>`, expressed in default user space units,
-    defining the boundaries of the physical medium on which the page is
-    intended to be displayed or printed.
+    A :class:`RectangleObject<pypdf.generic.RectangleObject>`, expressed in
+    default user space units, defining the boundaries of the physical medium on
+    which the page is intended to be displayed or printed.
     """
 
     @property
@@ -1965,10 +1989,10 @@ def mediaBox(self, value: RectangleObject) -> None:  # deprecated
 
     cropbox = _create_rectangle_accessor("/CropBox", (PG.MEDIABOX,))
     """
-    A :class:`RectangleObject<pypdf.generic.RectangleObject>`, expressed in default user space units,
-    defining the visible region of default user space.  When the page is
-    displayed or printed, its contents are to be clipped (cropped) to this
-    rectangle and then imposed on the output medium in some
+    A :class:`RectangleObject<pypdf.generic.RectangleObject>`, expressed in
+    default user space units, defining the visible region of default user space.
+    When the page is displayed or printed, its contents are to be clipped
+    (cropped) to this rectangle and then imposed on the output medium in some
     implementation-defined manner.  Default value: same as :attr:`mediabox<mediabox>`.
     """
 
@@ -1989,9 +2013,9 @@ def cropBox(self, value: RectangleObject) -> None:  # deprecated
 
     bleedbox = _create_rectangle_accessor("/BleedBox", ("/CropBox", PG.MEDIABOX))
     """
-    A :class:`RectangleObject<pypdf.generic.RectangleObject>`, expressed in default user space units,
-    defining the region to which the contents of the page should be clipped
-    when output in a production environment.
+    A :class:`RectangleObject<pypdf.generic.RectangleObject>`, expressed in
+    default user space units, defining the region to which the contents of the
+    page should be clipped when output in a production environment.
     """
 
     @property
@@ -2011,8 +2035,9 @@ def bleedBox(self, value: RectangleObject) -> None:  # deprecated
 
     trimbox = _create_rectangle_accessor("/TrimBox", ("/CropBox", PG.MEDIABOX))
     """
-    A :class:`RectangleObject<pypdf.generic.RectangleObject>`, expressed in default user space units,
-    defining the intended dimensions of the finished page after trimming.
+    A :class:`RectangleObject<pypdf.generic.RectangleObject>`, expressed in
+    default user space units, defining the intended dimensions of the finished
+    page after trimming.
     """
 
     @property
@@ -2032,9 +2057,9 @@ def trimBox(self, value: RectangleObject) -> None:  # deprecated
 
     artbox = _create_rectangle_accessor("/ArtBox", ("/CropBox", PG.MEDIABOX))
     """
-    A :class:`RectangleObject<pypdf.generic.RectangleObject>`, expressed in default user space units,
-    defining the extent of the page's meaningful content as intended by the
-    page's creator.
+    A :class:`RectangleObject<pypdf.generic.RectangleObject>`, expressed in
+    default user space units, defining the extent of the page's meaningful
+    content as intended by the page's creator.
     """
 
     @property

pypdf/_page.py

@@ -118,7 +118,8 @@ def convertToInt(d: bytes, size: int) -> Union[int, Tuple[Any, ...]]:  # depreca
 class DocumentInformation(DictionaryObject):
     """
     A class representing the basic document metadata provided in a PDF File.
-    This class is accessible through :py:class:`PdfReader.metadata<pypdf.PdfReader.metadata>`.
+    This class is accessible through
+    :py:class:`PdfReader.metadata<pypdf.PdfReader.metadata>`.
 
     All text properties of the document metadata have
     *two* properties, eg. author and author_raw. The non-raw property will

pypdf/_reader.py

@@ -470,8 +470,9 @@ def rename_kwargs(  # type: ignore
                 )
             if new_term in kwargs:
                 raise TypeError(
-                    f"{func_name} received both {old_term} and {new_term} as an argument. "
-                    f"{old_term} is deprecated. Use {new_term} instead."
+                    f"{func_name} received both {old_term} and {new_term} as "
+                    f"an argument. {old_term} is deprecated. "
+                    f"Use {new_term} instead."
                 )
             kwargs[new_term] = kwargs.pop(old_term)
             warnings.warn(