Enable lint for not specifying encoding on opening files in python (r…

…erun-io#5991)

### What

This fixes issues on windows where `open('somefile')` would use the
currently active encoding which may be governed my the locale / the
command line's configuration. This then causes issues loading utf8
encoded files.

The lint is part of Ruff's
[preview](https://docs.astral.sh/ruff/preview/) feature and therefore
requires enabling the `preview` option.
Unfortunately, this also changes the formatting despite specifying
`lint.explicit-preview-rules`, but looking over the changed formatting
it's consistently an improvement!

**Review commit by commit**


### Checklist
* [x] I have read and agree to [Contributor
Guide](https://github.com/rerun-io/rerun/blob/main/CONTRIBUTING.md) and
the [Code of
Conduct](https://github.com/rerun-io/rerun/blob/main/CODE_OF_CONDUCT.md)
* [x] I've included a screenshot or gif (if applicable)
* [x] I have tested the web demo (if applicable):
* Using examples from latest `main` build:
[rerun.io/viewer](https://rerun.io/viewer/pr/5991?manifest_url=https://app.rerun.io/version/main/examples_manifest.json)
* Using full set of examples from `nightly` build:
[rerun.io/viewer](https://rerun.io/viewer/pr/5991?manifest_url=https://app.rerun.io/version/nightly/examples_manifest.json)
* [x] The PR title and labels are set such as to maximize their
usefulness for the next release's CHANGELOG
* [x] If applicable, add a new check to the [release
checklist](https://github.com/rerun-io/rerun/blob/main/tests/python/release_checklist)!

- [PR Build Summary](https://build.rerun.io/pr/5991)
- [Recent benchmark results](https://build.rerun.io/graphs/crates.html)
- [Wasm size tracking](https://build.rerun.io/graphs/sizes.html)

To run all checks from `main`, comment on the PR with `@rerun-bot
full-check`.

docs/snippets/all/annotation_context_connections.py

@@ -7,20 +7,18 @@
 
 rr.log(
     "/",
-    rr.AnnotationContext(
-        [
-            ClassDescription(
-                info=0,
-                keypoint_annotations=[
-                    (0, "zero", (255, 0, 0)),
-                    (1, "one", (0, 255, 0)),
-                    (2, "two", (0, 0, 255)),
-                    (3, "three", (255, 255, 0)),
-                ],
-                keypoint_connections=[(0, 2), (1, 2), (2, 3)],
-            )
-        ]
-    ),
+    rr.AnnotationContext([
+        ClassDescription(
+            info=0,
+            keypoint_annotations=[
+                (0, "zero", (255, 0, 0)),
+                (1, "one", (0, 255, 0)),
+                (2, "two", (0, 0, 255)),
+                (3, "three", (255, 255, 0)),
+            ],
+            keypoint_connections=[(0, 2), (1, 2), (2, 3)],
+        )
+    ]),
     static=True,
 )
 

examples/python/arkit_scenes/main.py

@@ -44,7 +44,7 @@
 
 
 def load_json(js_path: Path) -> dict[str, Any]:
-    with open(js_path) as f:
+    with open(js_path, encoding="utf8") as f:
         json_data: dict[str, Any] = json.load(f)
     return json_data
 

examples/python/detect_and_track_objects/main.py

@@ -328,7 +328,7 @@ def update_trackers_with_detections(
 
 
 def track_objects(video_path: str, *, max_frame_count: int | None) -> None:
-    with open(COCO_CATEGORIES_PATH) as f:
+    with open(COCO_CATEGORIES_PATH, encoding="utf8") as f:
         coco_categories = json.load(f)
     class_descriptions = [
         rr.AnnotationInfo(id=cat["id"], color=cat["color"], label=cat["name"]) for cat in coco_categories

examples/python/external_data_loader/main.py

@@ -74,7 +74,7 @@ def main() -> None:
     else:
         entity_path = args.filepath
 
-    with open(args.filepath) as file:
+    with open(args.filepath, encoding="utf8") as file:
         body = file.read()
         text = f"""## Some Python code\n```python\n{body}\n```\n"""
         rr.log(

examples/python/human_pose_tracking/main.py

@@ -61,12 +61,10 @@ def track_pose(video_path: str, model_path: str, *, segment: bool, max_frame_cou
     # Use a separate annotation context for the segmentation mask.
     rr.log(
         "video/mask",
-        rr.AnnotationContext(
-            [
-                rr.AnnotationInfo(id=0, label="Background"),
-                rr.AnnotationInfo(id=1, label="Person", color=(0, 0, 0)),
-            ]
-        ),
+        rr.AnnotationContext([
+            rr.AnnotationInfo(id=0, label="Background"),
+            rr.AnnotationInfo(id=1, label="Person", color=(0, 0, 0)),
+        ]),
         static=True,
     )
     rr.log("person", rr.ViewCoordinates.RIGHT_HAND_Y_DOWN, static=True)

examples/python/open_photogrammetry_format/main.py

@@ -157,27 +157,21 @@ def log_calibrated_cameras(self, jpeg_quality: int | None) -> None:
             # https://pix4d.github.io/opf-spec/specification/calibrated_cameras.html#calibrated-camera
             omega, phi, kappa = tuple(np.deg2rad(a) for a in calib_camera.orientation_deg)
             rot = (
-                np.array(
-                    [
-                        [1, 0, 0],
-                        [0, np.cos(omega), -np.sin(omega)],
-                        [0, np.sin(omega), np.cos(omega)],
-                    ]
-                )
-                @ np.array(
-                    [
-                        [np.cos(phi), 0, np.sin(phi)],
-                        [0, 1, 0],
-                        [-np.sin(phi), 0, np.cos(phi)],
-                    ]
-                )
-                @ np.array(
-                    [
-                        [np.cos(kappa), -np.sin(kappa), 0],
-                        [np.sin(kappa), np.cos(kappa), 0],
-                        [0, 0, 1],
-                    ]
-                )
+                np.array([
+                    [1, 0, 0],
+                    [0, np.cos(omega), -np.sin(omega)],
+                    [0, np.sin(omega), np.cos(omega)],
+                ])
+                @ np.array([
+                    [np.cos(phi), 0, np.sin(phi)],
+                    [0, 1, 0],
+                    [-np.sin(phi), 0, np.cos(phi)],
+                ])
+                @ np.array([
+                    [np.cos(kappa), -np.sin(kappa), 0],
+                    [np.sin(kappa), np.cos(kappa), 0],
+                    [0, 0, 1],
+                ])
             )
 
             rr.log(entity, rr.Transform3D(translation=calib_camera.position, mat3x3=rot))

examples/python/raw_mesh/download_dataset.py

@@ -93,7 +93,7 @@ def download(url: str, path: Path) -> None:
             resp = requests.get(url)
             resp.raise_for_status()
             os.makedirs(path.parent, exist_ok=True)
-            with open(path, "wb") as f:
+            with open(path, "wb", encoding="utf8") as f:
                 f.write(resp.content)
 
     name = name.lower()

rerun_py/docs/gen_common_index.py

@@ -50,7 +50,7 @@ def all_archetypes() -> list[str]:
     pattern = r'"([^"]*)"'
 
     # Open the file for reading
-    with open(file_path) as file:
+    with open(file_path, encoding="utf8") as file:
         # Read the file line by line
         for line in file:
             # Use re.findall to find all quoted strings in the line

rerun_py/pyproject.toml

@@ -51,6 +51,11 @@ rerun = "rerun_bindings:main"
 # This is needed because otherwise ruff will not be able to trim whitespaces in (codegened) docstrings.
 unsafe-fixes = true
 
+# Allow preview lints to be enabled (like `PLW1514` to force `encoding` on open).
+preview = true
+# But we only want to opt-in to certain preview rules!
+lint.explicit-preview-rules = true
+
 extend-exclude = [
   # Automatically generated test artifacts
   "venv/",
@@ -101,13 +106,18 @@ lint.ignore = [
 
 line-length = 120
 lint.select = [
-  "D",   # pydocstyle codes https://www.pydocstyle.org/en/latest/error_codes.html
-  "E",   # pycodestyle error codes: https://pycodestyle.pycqa.org/en/latest/intro.html#error-codes
-  "F",   # Flake8 error codes https://flake8.pycqa.org/en/latest/user/error-codes.html
-  "I",   # Isort
-  "TID", # flake8-tidy-imports
-  "W",   # pycodestyle warning codes: https://pycodestyle.pycqa.org/en/latest/intro.html#error-codes
-  "UP",  # pyupgrade (ensures idomatic code for supported python version)
+  "D",       # pydocstyle codes https://www.pydocstyle.org/en/latest/error_codes.html
+  "E",       # pycodestyle error codes: https://pycodestyle.pycqa.org/en/latest/intro.html#error-codes
+  "F",       # Flake8 error codes https://flake8.pycqa.org/en/latest/user/error-codes.html
+  "I",       # Isort
+  "TID",     # flake8-tidy-imports
+  "W",       # pycodestyle warning codes: https://pycodestyle.pycqa.org/en/latest/intro.html#error-codes
+  "UP",      # pyupgrade (ensures idomatic code for supported python version)
+  "PLW1514", # Force setting `encoding` for open calls. This is in order to prevent issues when opening utf8 files on windows where the default encoding may depend on the active locale. https://docs.astral.sh/ruff/rules/unspecified-encoding/
+]
+
+lint.unfixable = [
+  "PLW1514", # Automatic fix for `encoding` doesn't do what we want - it queries the locale for the preferred encoding which is exactly what we want to avoid.
 ]
 
 [tool.ruff.lint.per-file-ignores]