Fix unicode encoding issue on Windows (#11)

* Fix unicode encoding issue on Windows
Add UTF-8 encoding to text diff output and enforce file encoding checks

Author: JustusRijke

pyproject.toml

@@ -63,11 +63,14 @@ addopts = [
 ]
 
 [tool.ruff.lint]
+preview = true
 extend-select = [
     "I",    # Sort imports
     "ANN",  # Enforce type annotations
     "PT",   # Common style issues or inconsistencies with pytest-based tests
-]
+    "PTH",  # Use PathLib
+    "PLW1514", # Must specify file encoding
+    ]
 
 [tool.ruff.lint.isort]
 combine-as-imports = true # Combines "as" imports on the same line

src/diffpdf/hash_check.py

@@ -4,7 +4,7 @@
 
 def compute_file_hash(filepath: Path) -> str:
     sha256 = hashlib.sha256()
-    with open(filepath, "rb") as f:
+    with Path(filepath).open("rb") as f:
         for chunk in iter(lambda: f.read(8192), b""):
             sha256.update(chunk)
     return sha256.hexdigest()

src/diffpdf/text_check.py

@@ -46,7 +46,7 @@ def check_text_content(ref: Path, actual: Path, output_dir: Path | None) -> bool
         if output_dir is not None:
             output_dir.mkdir(parents=True, exist_ok=True)
             diff_file = output_dir / f"{ref.stem}_vs_{actual.stem}_text_diff.txt"
-            diff_file.write_text(diff_text)
+            diff_file.write_text(diff_text, encoding="utf-8")
 
         logger.error(f"Text content mismatch:\n {diff_text}")
         return False

tests/assets/fail/unicode-A.pdf

@@ -19,6 +19,7 @@
         ("fail/1-letter-diff-A.pdf", "fail/1-letter-diff-B.pdf", False),
         ("fail/major-color-diff-A.pdf", "fail/major-color-diff-B.pdf", False),
         ("fail/page-count-diff-A.pdf", "fail/page-count-diff-B.pdf", False),
+        ("fail/unicode-A.pdf", "fail/unicode-B.pdf", False),
     ],
 )
 def test_api(ref_pdf_rel, actual_pdf_rel, should_pass):
@@ -39,4 +40,4 @@ def test_text_diff_output(tmp_path):
     assert result is False
     diff_file = tmp_path / "1-letter-diff-A_vs_1-letter-diff-B_text_diff.txt"
     assert diff_file.exists()
-    assert diff_file.read_text()
+    assert diff_file.read_text(encoding="utf-8")