DEV: Run CI with windows-latest (#2258)

.github/workflows/github-ci.yaml

@@ -17,6 +17,39 @@ on:
   workflow_dispatch:
 
 jobs:
+  test_windows:
+    name: pytest on windows
+    runs-on: windows-latest
+    steps:
+    - name: Checkout Code
+      uses: actions/checkout@v4
+      with:
+        submodules: 'recursive'
+    - name: Setup Python (3.11+)
+      uses: actions/setup-python@v4
+      with:
+        python-version: 3.12  # latest stable python
+        allow-prereleases: true
+    - name: Upgrade pip
+      run: |
+        python -m pip install --upgrade pip
+    - name: Install requirements (Python 3.11+)
+      run: |
+        pip install -r requirements/ci-3.11.txt
+    - name: Install cryptography
+      run: |
+        pip install cryptography
+    - name: Install pypdf
+      run: |
+        pip install .
+    - name: Prepare
+      run: |
+        python -c "from tests import download_test_pdfs; download_test_pdfs()"
+    - name: Test with pytest
+      run: |
+        python -m pytest tests --cov=pypdf --cov-append -n auto -vv
+
+
   tests:
     name: pytest on ${{ matrix.python-version }}
     runs-on: ubuntu-20.04

tests/test_filters.py

@@ -2,6 +2,7 @@
 import shutil
 import string
 import subprocess
+import sys
 from io import BytesIO
 from itertools import product as cartesian_product
 from pathlib import Path
@@ -259,6 +260,10 @@ def test_issue_399():
     reader.pages[1].extract_text()
 
 
+@pytest.mark.skipif(
+    sys.platform.startswith("win"),
+    reason="Supbrocess running python seems to linux-specific",
+)
 @pytest.mark.enable_socket()
 def test_image_without_pillow(tmp_path):
     url = "https://corpora.tika.apache.org/base/docs/govdocs1/914/914102.pdf"
@@ -267,7 +272,8 @@ def test_image_without_pillow(tmp_path):
     pdf_path = Path(__file__).parent / "pdf_cache" / name
 
     source_file = tmp_path / "script.py"
-    source_file.write_text(f"""
+    source_file.write_text(
+        f"""
 import sys
 from pypdf import PdfReader
 
@@ -284,14 +290,18 @@ def test_image_without_pillow(tmp_path):
         "pillow is required to do image extraction. "
         "It can be installed via 'pip install pypdf[image]'"
     ), exc.value.args[0]
-""")
+"""
+    )
     result = subprocess.run(  # noqa: UP022
-        [shutil.which("python"), source_file], stdout=subprocess.PIPE, stderr=subprocess.PIPE  # noqa: S603
+        [shutil.which("python"), source_file],  # noqa: S603
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
     )
     assert result.returncode == 0
     assert result.stdout == b""
     assert result.stderr == b"Superfluous whitespace found in object header b'4' b'0'\n"
 
+
 @pytest.mark.enable_socket()
 def test_issue_1737():
     url = "https://github.com/py-pdf/pypdf/files/11068604/tt1.pdf"

tests/test_workflows.py

@@ -100,9 +100,10 @@ def test_pdfreader_file_load():
         text = page.extract_text().encode("utf-8")
 
         # Compare the text of the PDF to a known source
-        for expected_line, actual_line in zip(text.split(b"\n"), pdftext.split(b"\n")):
+        for expected_line, actual_line in zip(text.splitlines(), pdftext.splitlines()):
             assert expected_line == actual_line
 
+        pdftext = pdftext.replace(b"\r\n", b"\n")  # fix for windows
         assert text == pdftext, (
             "PDF extracted text differs from expected value.\n\n"
             "Expected:\n\n%r\n\nExtracted:\n\n%r\n\n" % (pdftext, text)