mirror of
https://github.com/github/spec-kit.git
synced 2026-07-07 06:35:06 +08:00
fix(extensions): use explicit UTF-8 encoding when reading manifest YAML (#2370)
* fix(extensions): use explicit UTF-8 encoding when reading manifest YAML On Windows, Python's open() defaults to the system locale encoding (e.g., GBK on Chinese Windows), which causes UnicodeDecodeError when extension.yml or preset.yml contains non-ASCII content such as Chinese characters in description fields. Add encoding='utf-8' to ExtensionManifest._load_yaml and PresetManifest._load_yaml so manifests are read consistently across platforms. Fixes #2325 * test(extensions,presets): add UTF-8 manifest regression tests for #2325 Positive: extension.yml/preset.yml with non-ASCII (Chinese + emoji) descriptions load correctly when written as UTF-8 bytes — fails on Windows without explicit encoding='utf-8'. Negative: files containing invalid UTF-8 bytes raise a clean error (ValidationError or UnicodeDecodeError), not a silent crash. * fix(extensions,presets): wrap I/O and decode errors as ValidationError Address remaining Copilot concerns on #2370: - Catch UnicodeDecodeError and OSError in both manifest loaders and re-raise as ValidationError / PresetValidationError so callers see a consistent error type, not a bare decode/IO traceback. - Validate that PresetManifest YAML root is a mapping (extensions.py already had this; presets.py was missing it). Treat None as {} for empty-file compatibility. - Tighten the negative regression tests to assert the specific message, and add a non-mapping-root test for PresetManifest matching the existing one for ExtensionManifest.
This commit is contained in:
@@ -139,12 +139,18 @@ class ExtensionManifest:
|
||||
def _load_yaml(self, path: Path) -> dict:
|
||||
"""Load YAML file safely."""
|
||||
try:
|
||||
with open(path, 'r') as f:
|
||||
with open(path, 'r', encoding='utf-8') as f:
|
||||
data = yaml.safe_load(f)
|
||||
except yaml.YAMLError as e:
|
||||
raise ValidationError(f"Invalid YAML in {path}: {e}")
|
||||
except FileNotFoundError:
|
||||
raise ValidationError(f"Manifest not found: {path}")
|
||||
except UnicodeDecodeError as e:
|
||||
raise ValidationError(
|
||||
f"Manifest is not valid UTF-8: {path} ({e.reason} at byte {e.start})"
|
||||
)
|
||||
except OSError as e:
|
||||
raise ValidationError(f"Could not read manifest {path}: {e}")
|
||||
if not isinstance(data, dict):
|
||||
raise ValidationError(
|
||||
f"Manifest must be a YAML mapping, got {type(data).__name__}: {path}"
|
||||
|
||||
@@ -136,12 +136,25 @@ class PresetManifest:
|
||||
def _load_yaml(self, path: Path) -> dict:
|
||||
"""Load YAML file safely."""
|
||||
try:
|
||||
with open(path, 'r') as f:
|
||||
return yaml.safe_load(f) or {}
|
||||
with open(path, 'r', encoding='utf-8') as f:
|
||||
data = yaml.safe_load(f)
|
||||
except yaml.YAMLError as e:
|
||||
raise PresetValidationError(f"Invalid YAML in {path}: {e}")
|
||||
except FileNotFoundError:
|
||||
raise PresetValidationError(f"Manifest not found: {path}")
|
||||
except UnicodeDecodeError as e:
|
||||
raise PresetValidationError(
|
||||
f"Manifest is not valid UTF-8: {path} ({e.reason} at byte {e.start})"
|
||||
)
|
||||
except OSError as e:
|
||||
raise PresetValidationError(f"Could not read manifest {path}: {e}")
|
||||
if data is None:
|
||||
return {}
|
||||
if not isinstance(data, dict):
|
||||
raise PresetValidationError(
|
||||
f"Manifest must be a YAML mapping, got {type(data).__name__}: {path}"
|
||||
)
|
||||
return data
|
||||
|
||||
def _validate(self):
|
||||
"""Validate manifest structure and required fields."""
|
||||
|
||||
Reference in New Issue
Block a user