TST: Add xfail test for #2336

tests/example_files.yaml

@@ -110,3 +110,5 @@
   url: https://github.com/py-pdf/pypdf/assets/4083478/56c93021-33cd-4387-ae13-5cbe7e673f42
 - local_filename: paid.pdf
   url: https://github.com/py-pdf/pypdf/files/12050253/tt.pdf
+- local_filename: Pesquisa-de-Precos-Combustiveis-novembro-2023.pdf
+  url: https://www.joinville.sc.gov.br/wp-content/uploads/2023/11/Pesquisa-de-Precos-Combustiveis-novembro-2023.pdf

tests/test_text_extraction.py

@@ -3,13 +3,16 @@
 
 The tested code might be in _page.py.
 """
+from io import BytesIO
 from pathlib import Path
 
 import pytest
 
 from pypdf import PdfReader, mult
 from pypdf._text_extraction import set_custom_rtl
 
+from . import get_data_from_url
+
 TESTS_ROOT = Path(__file__).parent.resolve()
 PROJECT_ROOT = TESTS_ROOT.parent
 RESOURCE_ROOT = PROJECT_ROOT / "resources"
@@ -99,3 +102,13 @@ def visitor_text(text, cm, tm, font_dict, font_size) -> None:
         x = matches[0]["x"]
         y = matches[0]["y"]
         assert constraint(x, y), f'Line "{text}" is wrong at x:{x}, y:{y}'
+
+
+@pytest.mark.xfail(reason="known whitespace issue #2336")
+@pytest.mark.enable_socket()
+def test_issue_2336():
+    name = "Pesquisa-de-Precos-Combustiveis-novembro-2023.pdf"
+    reader = PdfReader(BytesIO(get_data_from_url(name=name)))
+    page = reader.pages[0]
+    actual_text = page.extract_text()
+    assert "Beira Rio" in actual_text