TST: Replace pytest.mark.external by enable_socket

docs/dev/testing.md

@@ -8,10 +8,10 @@ pypdf makes use of the following pytest markers:
 
 * `slow`: Tests that require more than 5 seconds
 * `samples`: Tests that require the [the `sample-files` git submodule](https:/py-pdf/sample-files) to be initialized. As of October 2022, this is about 25 MB.
-* `external`: Tests that download PDF documents. They are stored locally and thus only need to be downloaded once. As of October 2022, this is about 200 MB.
+* `enable_socket`: Tests that download PDF documents. They are stored locally and thus only need to be downloaded once. As of October 2022, this is about 200 MB.
 
-You can disable them by `pytest -m "not external"` or `pytest -m "not samples"`.
-You can even disable all of them: `pytest -m "not external" -m "not samples" -m "not slow"`.
+You can disable them by `pytest -m "not enable_socket"` or `pytest -m "not samples"`.
+You can even disable all of them: `pytest -m "not enable_socket" -m "not samples" -m "not slow"`.
 
 Please note that this reduces test coverage. The CI will always test all files.
 

pyproject.toml

@@ -56,11 +56,12 @@ package = "./pypdf"
 exclude = [".github/*", "docs/*", "resources/*", "sample-files/*", "sample-files/.github/*", "sample-files/.gitignore", "sample-files/.pre-commit-config.yaml", "requirements/*", "tests/*", ".flake8", ".gitignore", ".gitmodules", ".pylintrc", "tox.ini", "make_changelog.py", "mutmut-test.sh", ".pre-commit-config.yaml", ".gitblame-ignore-revs", "Makefile", "mutmut_config.py"]
 
 [tool.pytest.ini_options]
+addopts = "--disable-socket"
 filterwarnings = ["error"]
 markers = [
  "slow: Test which require more than a second",
  "samples: Tests which use files from https:/py-pdf/sample-files",
- "external: Tests which need to download files"
+ "enable_socket: Tests which need to download files"
 ]
 testpaths = ["tests"]
 norecursedirs = ["tests/pdf_cache"]

requirements/ci-3.11.txt

@@ -1,6 +1,6 @@
 #
-# This file is autogenerated by pip-compile with python 3.11
-# To update, run:
+# This file is autogenerated by pip-compile with Python 3.11
+# by the following command:
 #
 # pip-compile --output-file=requirements/ci-3.11.txt requirements/ci.in
 #
@@ -54,8 +54,11 @@ pytest==7.2.0
  # via
  # -r requirements/ci.in
  # pytest-benchmark
+ # pytest-socket
 pytest-benchmark==4.0.0
  # via -r requirements/ci.in
+pytest-socket==0.6.0
+ # via -r requirements/ci.in
 ruff==0.0.252
  # via -r requirements/ci.in
 typeguard==2.13.3

requirements/ci.in

@@ -8,6 +8,7 @@ pillow
 pycryptodome
 pytest
 pytest-benchmark
+pytest-socket
 typeguard
 types-dataclasses
 types-Pillow

requirements/ci.txt

@@ -61,8 +61,11 @@ pytest==7.0.1
  # via
  # -r requirements/ci.in
  # pytest-benchmark
+ # pytest-socket
 pytest-benchmark==3.4.1
  # via -r requirements/ci.in
+pytest-socket==0.4.1
+ # via -r requirements/ci.in
 six==1.16.0
  # via flake8-print
 tomli==1.2.3

tests/test_cmap.py

@@ -10,7 +10,7 @@
 from . import get_pdf_from_url
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 @pytest.mark.slow
 def test_compute_space_width():
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/923/923406.pdf"
@@ -21,7 +21,7 @@ def test_compute_space_width():
  page.extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 @pytest.mark.slow
 def test_parse_to_unicode_process_rg():
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/959/959173.pdf"
@@ -36,7 +36,7 @@ def test_parse_to_unicode_process_rg():
  page.extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_parse_encoding_advanced_encoding_not_implemented():
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/957/957144.pdf"
  name = "tika-957144.pdf"
@@ -47,7 +47,7 @@ def test_parse_encoding_advanced_encoding_not_implemented():
  page.extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_get_font_width_from_default(): # L40
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/908/908104.pdf"
  name = "tika-908104.pdf"
@@ -56,7 +56,7 @@ def test_get_font_width_from_default(): # L40
  page.extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_multiline_bfrange():
  # non regression test for iss_1285
  url = (
@@ -77,7 +77,7 @@ def test_multiline_bfrange():
  page.extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_bfchar_on_2_chars():
  # iss #1293
  url = (
@@ -90,7 +90,7 @@ def test_bfchar_on_2_chars():
  page.extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_ascii_charset():
  # iss #1312
  url = "https:/py-pdf/pypdf/files/9472500/main.pdf"
@@ -99,23 +99,23 @@ def test_ascii_charset():
  assert "/a" not in reader.pages[0].extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_iss1370():
  url = "https:/py-pdf/pypdf/files/9667138/cmap1370.pdf"
  name = "cmap1370.pdf"
  reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
  reader.pages[0].extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_iss1379():
  url = "https:/py-pdf/pypdf/files/9712729/02voc.pdf"
  name = "02voc.pdf"
  reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
  reader.pages[2].extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_iss1533():
  url = "https:/py-pdf/pypdf/files/10376149/iss1533.pdf"
  name = "iss1533.pdf"

tests/test_filters.py

@@ -202,7 +202,7 @@ def test_CCITTFaxDecode():
  )
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 @patch("pypdf._reader.logger_warning")
 def test_decompress_zlib_error(mock_logger_warning):
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/952/952445.pdf"
@@ -215,7 +215,7 @@ def test_decompress_zlib_error(mock_logger_warning):
  )
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_lzw_decode_neg1():
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/921/921632.pdf"
  name = "tika-921632.pdf"
@@ -226,15 +226,15 @@ def test_lzw_decode_neg1():
  assert exc.value.args[0] == "Missed the stop code in LZWDecode!"
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_issue_399():
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/976/976970.pdf"
  name = "tika-976970.pdf"
  reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
  reader.pages[1].extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_image_without_imagemagic():
  with patch.dict(sys.modules):
  sys.modules["PIL"] = None

tests/test_generic.py

@@ -583,7 +583,7 @@ def test_remove_child_in_tree():
  tree.empty_tree()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_dict_read_from_stream(caplog):
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/984/984877.pdf"
  name = "tika-984877.pdf"
@@ -597,7 +597,7 @@ def test_dict_read_from_stream(caplog):
  )
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_parse_content_stream_peek_percentage():
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/985/985770.pdf"
  name = "tika-985770.pdf"
@@ -607,7 +607,7 @@ def test_parse_content_stream_peek_percentage():
  page.extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_read_inline_image_no_has_q():
  # pdf/df7e1add3156af17a372bc165e47a244.pdf
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/998/998719.pdf"
@@ -618,7 +618,7 @@ def test_read_inline_image_no_has_q():
  page.extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_read_inline_image_loc_neg_1():
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/935/935066.pdf"
  name = "tika-935066.pdf"
@@ -629,7 +629,7 @@ def test_read_inline_image_loc_neg_1():
 
 
 @pytest.mark.slow
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_text_string_write_to_stream():
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/924/924562.pdf"
  name = "tika-924562.pdf"
@@ -639,7 +639,7 @@ def test_text_string_write_to_stream():
  page.compress_content_streams()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_name_object_read_from_stream_unicode_error(): # L588
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/974/974966.pdf"
  name = "tika-974966.pdf"
@@ -649,7 +649,7 @@ def test_name_object_read_from_stream_unicode_error(): # L588
  page.extract_text()
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_bool_repr(tmp_path):
  url = "https://corpora.tika.apache.org/base/docs/govdocs1/932/932449.pdf"
  name = "tika-932449.pdf"
@@ -669,7 +669,7 @@ def test_bool_repr(tmp_path):
  )
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 @patch("pypdf._reader.logger_warning")
 def test_issue_997(mock_logger_warning):
  url = (
@@ -1046,7 +1046,7 @@ def test_cloning(caplog):
  assert isinstance(obj21.get("/Test2"), IndirectObject)
 
 
-@pytest.mark.external
+@pytest.mark.enable_socket
 def test_append_with_indirectobject_not_pointing(caplog):
  """
  reported in #1631