BUG: Accept tabs in cmaps (#2174)

Closes #2173

pypdf/_cmap.py

@@ -232,7 +232,7 @@ def parse_to_unicode(
  cm = prepare_cm(ft)
  for line in cm.split(b"\n"):
  process_rg, process_char, multiline_rg = process_cm_line(
- line.strip(b" "),
+ line.strip(b" \t"),
  process_rg,
  process_char,
  multiline_rg,
@@ -295,8 +295,9 @@ def process_cm_line(
  map_dict: Dict[Any, Any],
  int_entry: List[int],
 ) -> Tuple[bool, bool, Union[None, Tuple[int, int]]]:
- if line in (b"", b" ") or line[0] == 37: # 37 = %
+ if line == b"" or line[0] == 37: # 37 = %
  return process_rg, process_char, multiline_rg
+ line = line.replace(b"\t", b" ")
  if b"beginbfrange" in line:
  process_rg = True
  elif b"endbfrange" in line:

tests/test_cmap.py

@@ -189,3 +189,12 @@ def test_unixxx_glyphs():
  txt = reader.pages[0].extract_text() # no error
  for pat in ("闫耀庭", "龚龑", "张江水", "1′′.2"):
  assert pat in txt
+
+
+@pytest.mark.enable_socket()
+def test_tabs_in_cmap():
+ """Issue #2173"""
+ url = "https://github.com/py-pdf/pypdf/files/12552700/tt.pdf"
+ name = "iss2173.pdf"
+ reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+ reader.pages[0].extract_text()