Remove code duplication

PyPDF2/_merger.py

@@ -45,11 +45,12 @@
     NumberObject,
     TextStringObject,
     TreeObject,
-    createStringObject,
+    _create_bookmark,
 )
 from .pagerange import PageRange, PageRangeSpec
 from .types import (
     BookmarkTypes,
+    FitType,
     LayoutType,
     OutlinesType,
     PagemodeType,
@@ -590,7 +591,7 @@ def _associate_bookmarks_to_pages(
             if pageno is not None:
                 b[NameObject("/Page")] = NumberObject(pageno)
             else:
-                raise ValueError("Unresolved bookmark '{}'".format(b["/Title"]))
+                raise ValueError(f"Unresolved bookmark '{b['/Title']}'")
 
     def find_bookmark(
         self,
@@ -621,8 +622,8 @@ def addBookmark(
         color: Optional[Tuple[float, float, float]] = None,
         bold: bool = False,
         italic: bool = False,
-        fit: str = "/Fit",
-        *args: ZoomArgType,
+        fit: FitType = "/Fit",
+        *args: ZoomArgsType,
     ) -> IndirectObject:  # pragma: no cover
         """
         .. deprecated:: 1.28.0
@@ -641,8 +642,8 @@ def add_bookmark(
         color: Optional[Tuple[float, float, float]] = None,
         bold: bool = False,
         italic: bool = False,
-        fit: str = "/Fit",
-        *args: ZoomArgType,
+        fit: FitType = "/Fit",
+        *args: ZoomArgsType,
     ) -> IndirectObject:
         """
         Add a bookmark to this PDF file.
@@ -656,7 +657,7 @@ def add_bookmark(
         :param bool bold: Bookmark is bold
         :param bool italic: Bookmark is italic
         :param str fit: The fit of the destination page. See
-            :meth:`addLink()<addLin>` for details.
+            :meth:`addLink()<addLink>` for details.
         """
         if self.output is None:
             raise RuntimeError(ERR_CLOSED_WRITER)
@@ -687,32 +688,13 @@ def add_bookmark(
         if parent is None:
             parent = outline_ref
 
-        bookmark = TreeObject()
+        bookmark = _create_bookmark(action_ref, title, color, italic, bold)
 
-        bookmark.update(
-            {
-                NameObject("/A"): action_ref,
-                NameObject("/Title"): createStringObject(title),
-            }
-        )
-
-        if color is not None:
-            bookmark.update(
-                {NameObject("/C"): ArrayObject([FloatObject(c) for c in color])}
-            )
-
-        format_flag = 0
-        if italic:
-            format_flag += 1
-        if bold:
-            format_flag += 2
-        if format_flag:
-            bookmark.update({NameObject("/F"): NumberObject(format_flag)})
-
-        bookmark_ref = self.output._add_object(bookmark)
-        parent = cast(Bookmark, parent.get_object())
         assert parent is not None, "hint for mypy"
-        parent.add_child(bookmark_ref, self.output)
+        bookmark_ref = self.output._add_object(bookmark)
+        parent_obj = cast(Bookmark, parent.get_object())
+        assert parent_obj is not None, "hint for mypy"
+        parent_obj.add_child(bookmark_ref, self.output)
 
         return bookmark_ref
 

PyPDF2/_reader.py

@@ -1228,8 +1228,8 @@ def read(self, stream: StreamType) -> None:
                 )
 
         # read all cross reference tables and their trailers
-        self.xref: Dict[Any, Any] = {}
-        self.xref_objStm: Dict[Any, Any] = {}
+        self.xref: Dict[int, Dict[Any, Any]] = {}
+        self.xref_objStm: Dict[int, Tuple[Any, Any]] = {}
         self.trailer = DictionaryObject()
         while True:
             # load the xref table
@@ -1302,11 +1302,11 @@ def read(self, stream: StreamType) -> None:
         # if not zero-indexed, verify that the table is correct; change it if necessary
         if self.xref_index and not self.strict:
             loc = stream.tell()
-            for gen in self.xref:
+            for gen, xref_entry in self.xref.items():
                 if gen == 65535:
                     continue
-                for id in self.xref[gen]:
-                    stream.seek(self.xref[gen][id], 0)
+                for id in xref_entry:
+                    stream.seek(xref_entry[id], 0)
                     try:
                         pid, _pgen = self.read_object_header(stream)
                     except ValueError:
@@ -1440,7 +1440,7 @@ def get_entry(i: int) -> Union[int, Tuple[int, ...]]:
 
         def used_before(num: int, generation: Union[int, Tuple[int, ...]]) -> bool:
             # We move backwards through the xrefs, don't replace any.
-            return num in self.xref.get(generation, []) or num in self.xref_objStm
+            return num in self.xref.get(generation, []) or num in self.xref_objStm  # type: ignore
 
         # Iterate through each subsection
         self._read_xref_subsections(idx_pairs, get_entry, used_before)
@@ -1519,9 +1519,9 @@ def _read_xref_subsections(
                     byte_offset = get_entry(1)
                     generation = get_entry(2)
                     if generation not in self.xref:
-                        self.xref[generation] = {}
+                        self.xref[generation] = {}  # type: ignore
                     if not used_before(num, generation):
-                        self.xref[generation][num] = byte_offset
+                        self.xref[generation][num] = byte_offset  # type: ignore
                 elif xref_type == 2:
                     # compressed objects
                     objstr_num = get_entry(1)

PyPDF2/_writer.py

@@ -67,6 +67,7 @@
     StreamObject,
     TextStringObject,
     TreeObject,
+    _create_bookmark,
     createStringObject,
 )
 from .types import (
@@ -1078,27 +1079,7 @@ def add_bookmark(
         if parent is None:
             parent = outline_ref
 
-        bookmark = TreeObject()
-
-        bookmark.update(
-            {
-                NameObject("/A"): action_ref,
-                NameObject("/Title"): createStringObject(title),
-            }
-        )
-
-        if color is not None:
-            bookmark.update(
-                {NameObject("/C"): ArrayObject([FloatObject(c) for c in color])}
-            )
-
-        format_flag = 0
-        if italic:
-            format_flag += 1
-        if bold:
-            format_flag += 2
-        if format_flag:
-            bookmark.update({NameObject("/F"): NumberObject(format_flag)})
+        bookmark = _create_bookmark(action_ref, title, color, italic, bold)
 
         bookmark_ref = self._add_object(bookmark)
 

PyPDF2/filters.py

@@ -153,7 +153,7 @@ def _decode_png_prediction(data: str, columns: int) -> str:
                     rowdata[i] = (rowdata[i] + paeth) % 256
             else:
                 # unsupported PNG filter
-                raise PdfReadError("Unsupported PNG filter %r" % filter_byte)
+                raise PdfReadError(f"Unsupported PNG filter {filter_byte!r}")
             prev_rowdata = tuple(rowdata)
             output.write("".join([chr(x) for x in rowdata[1:]]))
         return output.getvalue()

PyPDF2/generic.py

@@ -1904,6 +1904,37 @@ def createStringObject(
         raise TypeError("createStringObject should have str or unicode arg")
 
 
+def _create_bookmark(
+    action_ref: IndirectObject,
+    title: str,
+    color: Optional[Tuple[float, float, float]],
+    italic: bool,
+    bold: bool,
+) -> TreeObject:
+    bookmark = TreeObject()
+
+    bookmark.update(
+        {
+            NameObject("/A"): action_ref,
+            NameObject("/Title"): createStringObject(title),
+        }
+    )
+
+    if color is not None:
+        bookmark.update(
+            {NameObject("/C"): ArrayObject([FloatObject(c) for c in color])}
+        )
+
+    format_flag = 0
+    if italic:
+        format_flag += 1
+    if bold:
+        format_flag += 2
+    if format_flag:
+        bookmark.update({NameObject("/F"): NumberObject(format_flag)})
+    return bookmark
+
+
 def encode_pdfdocencoding(unicode_string: str) -> bytes:
     retval = b""
     for c in unicode_string: