BUG: Line breaks are not generated due to incorrect calculation of te…

…xt leading (#2890)

Closes #2262.

pypdf/_page.py

@@ -1965,7 +1965,8 @@ def process_operation(operator: bytes, operands: List[Any]) -> None:
  elif operator == b"Tw":
  space_scale = 1.0 + float(operands[0])
  elif operator == b"TL":
- TL = float(operands[0])
+ scale_x = math.sqrt(tm_matrix[0]**2 + tm_matrix[2]**2)
+ TL = float(operands[0]) * font_size * scale_x
  elif operator == b"Tf":
  if text != "":
  output += text # .translate(cmap)

tests/test_text_extraction.py

@@ -211,3 +211,11 @@ def test_space_position_calculation():
  page = reader.pages[3]
  extracted = page.extract_text()
  assert "Shortly after the Geneva BOF session, the" in extracted
+
+
+def test_text_leading_height_unit():
+ """Tests for #2262"""
+ reader = PdfReader(RESOURCE_ROOT / "toy.pdf")
+ page = reader.pages[0]
+ extracted = page.extract_text()
+ assert "Something[cited]\n" in extracted