BUG: Fix error in cmap extraction (#1544)

Fixes #1533 and late #1091

pypdf/_cmap.py

@@ -280,13 +280,11 @@ def parse_bfrange(
 ) -> Union[None, Tuple[int, int]]:
  lst = [x for x in line.split(b" ") if x]
  closure_found = False
- nbi = max(len(lst[0]), len(lst[1]))
- map_dict[-1] = ceil(nbi / 2)
- fmt = b"%%0%dX" % (map_dict[-1] * 2)
  if multiline_rg is not None:
+ fmt = b"%%0%dX" % (map_dict[-1] * 2)
  a = multiline_rg[0] # a, b not in the current line
  b = multiline_rg[1]
- for sq in lst[1:]:
+ for sq in lst[0:]:
  if sq == b"]":
  closure_found = True
  break
@@ -301,6 +299,9 @@ def parse_bfrange(
  else:
  a = int(lst[0], 16)
  b = int(lst[1], 16)
+ nbi = max(len(lst[0]), len(lst[1]))
+ map_dict[-1] = ceil(nbi / 2)
+ fmt = b"%%0%dX" % (map_dict[-1] * 2)
  if lst[2] == b"[":
  for sq in lst[3:]:
  if sq == b"]":

tests/test_cmap.py

@@ -3,6 +3,7 @@
 import pytest
 
 from pypdf import PdfReader
+from pypdf._cmap import build_char_map
 from pypdf.errors import PdfReadWarning
 
 from . import get_pdf_from_url
@@ -102,3 +103,12 @@ def test_iss1379():
  name = "02voc.pdf"
  reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
  reader.pages[2].extract_text()
+
+
+@pytest.mark.external
+def test_iss1533():
+ url = "https://github.com/py-pdf/pypdf/files/10376149/iss1533.pdf"
+ name = "iss1533.pdf"
+ reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+ reader.pages[0].extract_text() # no error
+ assert build_char_map("/F", 200, reader.pages[0])[3]["\x01"] == "Ü"