diff --git a/.github/workflows/test-runner.yml b/.github/workflows/test-runner.yml index 7ed5ee5..efafbaf 100644 --- a/.github/workflows/test-runner.yml +++ b/.github/workflows/test-runner.yml @@ -16,7 +16,7 @@ jobs: runs-on: ubuntu-latest strategy: matrix: - python-version: ["3.8", "3.9", "3.10", "3.11", "3.12", "3.13"] + python-version: ["3.10", "3.11", "3.12", "3.13"] steps: - uses: actions/checkout@v6 diff --git a/CHANGELOG.md b/CHANGELOG.md index d7be189..a0d1aef 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -10,11 +10,25 @@ The format is (loosely) based on [Keep a Changelog](http://keepachangelog.com/) ### Changed -### Fixed +### Fixed ### Removed -### Updated +## [v4.5.0] - 2026-07-30 + +### Added + +- Added an opt-in `validate_geometry` flag to `FastValidator`. When enabled, it performs pure-Python spatial checks to ensure coordinates fall within global WGS84 bounds and detects improper antimeridian crossings in Polygons/MultiPolygons. +- Added a strict 5000-vertex limit to the new geometry validation rings. This acts as a safeguard to prevent CPU exhaustion or thread lockups when processing excessively complex coastal or generated polygons. +- Added pure-Python checks to `FastValidator` that ensure an item's `start_datetime` is never strictly after its `end_datetime`. [#304](https://github.com/stac-utils/stac-validator/pull/304) + +### Changed + +- Completely refactored the fallback logic in `fast_validator` to remove the heavy `python-jsonschema` dependency block. If the dynamic `allOf` schema compiler fails (often caused by internal reference collisions in the `storage` or `file` extensions), the validator now gracefully compiles the base schema and compatible extensions individually, cleanly skipping incompatible extensions to maintain blazing-fast API ingestion speeds. [#304](https://github.com/stac-utils/stac-validator/pull/304) + +### Fixed + +- Fixed a fatal `KeyError: 'definitions'` crash in `fast_validator` caused by complex STAC extensions attempting to resolve local `$ref` pointers (like `#/definitions/links`) against an empty synthetic root. [#304](https://github.com/stac-utils/stac-validator/pull/304) ## [v4.4.0] - 2026-05-11 @@ -460,7 +474,9 @@ The format is (loosely) based on [Keep a Changelog](http://keepachangelog.com/) - With the newest version - 1.0.0-beta.2 - items will run through jsonchema validation before the PySTAC validation. The reason for this is that jsonschema will give more informative error messages. This should be addressed better in the future. This is not the case with the --recursive option as time can be a concern here with larger collections. - Logging. Various additions were made here depending on the options selected. This was done to help assist people to update their STAC collections. -[Unreleased]: https://github.com/sparkgeo/stac-validator/compare/v4.3.0..main +[Unreleased]: https://github.com/sparkgeo/stac-validator/compare/v4.5.0..main +[v4.5.0]: https://github.com/sparkgeo/stac-validator/compare/v4.4.0..v4.5.0 +[v4.4.0]: https://github.com/sparkgeo/stac-validator/compare/v4.3.0..v4.4.0 [v4.3.0]: https://github.com/sparkgeo/stac-validator/compare/v4.2.2..v4.3.0 [v4.2.2]: https://github.com/sparkgeo/stac-validator/compare/v4.2.1..v4.2.2 [v4.2.1]: https://github.com/sparkgeo/stac-validator/compare/v4.2.0..v4.2.1 diff --git a/pyproject.toml b/pyproject.toml index 128a49f..1aeab9e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "stac_valid" -version = "4.4.0" +version = "4.5.0" description = "A package to validate STAC files" authors = [ {name = "Jonathan Healy", email = "jon@healy-hyperspatial.dev"}, diff --git a/stac_validator/fast_validator.py b/stac_validator/fast_validator.py index f4f3a16..5e6bef7 100644 --- a/stac_validator/fast_validator.py +++ b/stac_validator/fast_validator.py @@ -110,6 +110,7 @@ def get_validator(stac_type: str, stac_version: str, extensions: List[str]): else: raise ValueError(f"Unknown STAC type for validation: {stac_type}") + # Try to compile with all extensions using allOf schema_fragments: List[Dict[str, str]] = [{"$ref": base_uri}] for ext in extensions: schema_fragments.append({"$ref": ext}) @@ -119,31 +120,69 @@ def get_validator(stac_type: str, stac_version: str, extensions: List[str]): } try: - validator = fastjsonschema.compile( + # TIER 1: Try compiling everything dynamically using allOf (Maximum Speed) + compiled_validator = fastjsonschema.compile( dynamic_schema, handlers={"http": fetch_schema, "https": fetch_schema} ) + + def validator(data: Dict[str, Any]) -> None: + old_limit = sys.getrecursionlimit() + sys.setrecursionlimit(10000) + try: + compiled_validator(data) + finally: + sys.setrecursionlimit(old_limit) + except Exception: - # FALLBACK: Some schemas (like Item Assets) cause fastjsonschema to generate invalid python code. - # We fall back to the standard jsonschema library. - click.secho( - " [Fallback] fastjsonschema compile failed. Using python-jsonschema.", - fg="yellow", - dim=True, + # TIER 2: allOf compilation failed (e.g., storage extension reference collisions). + # Compile base and compatible extensions separately. Skip broken ones to maintain API speed. + base_validator = fastjsonschema.compile( + {"$ref": base_uri}, + handlers={"http": fetch_schema, "https": fetch_schema}, ) - import jsonschema - - # Create a validator using the same custom logic - def fallback_validator(data: Dict[str, Any]) -> None: - # We need a resolver to handle the remote $refs - resolver = jsonschema.RefResolver( - base_uri="", - referrer=dynamic_schema, - handlers={"http": fetch_schema, "https": fetch_schema}, + + ext_validators = [] + skipped_extensions = [] + + for ext in extensions: + try: + ext_val = fastjsonschema.compile( + {"$ref": ext}, + handlers={"http": fetch_schema, "https": fetch_schema}, + ) + ext_validators.append(ext_val) + except Exception: + # Skip extensions that fastjsonschema cannot compile + skipped_extensions.append(ext) + + # Only print warnings if running in CLI mode, keep the API quiet + if skipped_extensions and not QUIET_MODE: + click.secho( + f" [Warning] Skipped {len(skipped_extensions)} extension(s) for speed (fastjsonschema compile failed):", + fg="yellow", + dim=True, + ) + for ext in skipped_extensions: + click.secho(f" - {ext}", fg="yellow", dim=True) + click.secho( + " For strict validation of all extensions, use: stac-valid validate ", + fg="yellow", + dim=True, ) - jsonschema.validate(data, dynamic_schema, resolver=resolver) - validator = fallback_validator + def multi_validator(data: Dict[str, Any]) -> None: + old_limit = sys.getrecursionlimit() + sys.setrecursionlimit(10000) + try: + base_validator(data) + for ext_val in ext_validators: + ext_val(data) + finally: + sys.setrecursionlimit(old_limit) + + validator = multi_validator + # Cache the resulting validator so future items use it instantly VALIDATOR_CACHE[cache_key] = validator return validator, False @@ -155,6 +194,7 @@ def __init__( quiet: bool = False, verbose: bool = False, limit: Optional[int] = None, + validate_geometry: bool = False, ): global QUIET_MODE self.stac_file = stac_file @@ -162,9 +202,79 @@ def __init__( self.valid = True self.verbose = verbose self.limit = limit + self.validate_geometry = validate_geometry self.message: List[Dict[str, Any]] = [] QUIET_MODE = quiet + def _validate_datetime_range(self, data: Dict[str, Any]) -> None: + """Ensures start_datetime is not strictly after end_datetime per STAC Spec. + + Uses lexicographical string comparison since RFC 3339 timestamps sort + chronologically when compared as strings. This avoids datetime parsing + issues in Python 3.8/3.9 with non-standard ISO 8601 formats. + """ + if data.get("type") != "Feature": + return + + properties = data.get("properties", {}) + start_str = properties.get("start_datetime") + end_str = properties.get("end_datetime") + + if start_str and end_str: + # RFC 3339 timestamps sort lexicographically, so we can compare as strings + # This avoids datetime.fromisoformat() parsing issues in Python 3.8/3.9 + if start_str > end_str: + raise ValueError( + f"Logical Error: start_datetime ({start_str}) cannot be strictly after end_datetime ({end_str})" + ) + + def _validate_geometry(self, data: Dict[str, Any]) -> None: + """Lightweight topology check for global bounds and antimeridian crossings.""" + if data.get("type") != "Feature": + return + + geometry = data.get("geometry") + if not geometry: + return + + geom_type = geometry.get("type") + coords = geometry.get("coordinates") + if not coords or geom_type not in ("Polygon", "MultiPolygon"): + return + + def check_bounds(c: list): + if not c: + return + if isinstance(c[0], (int, float)): + if not (-180 <= c[0] <= 180) or not (-90 <= c[1] <= 90): + raise ValueError(f"Geometry out of global WGS84 bounds: {c}") + else: + for sub in c: + check_bounds(sub) + + check_bounds(coords) + + def check_rings(rings: list): + max_vertices = int(os.environ.get("MAX_TOPOLOGY_VERTICES", 5000)) + for ring in rings: + if len(ring) < 4: + raise ValueError("Polygon ring must have at least 4 coordinates.") + if len(ring) > max_vertices: + raise ValueError( + f"Geometry exceeds maximum allowed vertices ({max_vertices}). Found {len(ring)}." + ) + for i in range(len(ring) - 1): + if abs(ring[i][0] - ring[i + 1][0]) > 180: + raise ValueError( + f"Improper antimeridian crossing between {ring[i][0]} and {ring[i + 1][0]}" + ) + + if geom_type == "Polygon": + check_rings(coords) + elif geom_type == "MultiPolygon": + for poly in coords: + check_rings(poly) + def _limit_reached(self, results: List[Dict]) -> bool: return self.limit is not None and len(results) >= self.limit @@ -416,6 +526,10 @@ def run(self): t2 = time.perf_counter() try: validator(item) + # Run logical firewalls + self._validate_datetime_range(item) + if self.validate_geometry: + self._validate_geometry(item) t3 = time.perf_counter() exec_time = (t3 - t2) * 1000 total_exec_ms += exec_time @@ -445,6 +559,20 @@ def run(self): error_registry[error_msg].append(item_id) status_text = click.style("❌ INVALID", fg="red") + except ValueError as e: + t3 = time.perf_counter() + exec_time = (t3 - t2) * 1000 + total_exec_ms += exec_time + invalid_count += 1 + self.valid = False + + # Logical validation errors (datetime range, geometry) + error_msg = str(e) + if error_msg not in error_registry: + error_registry[error_msg] = [] + error_registry[error_msg].append(item_id) + status_text = click.style("❌ INVALID", fg="red") + except Exception as e: t3 = time.perf_counter() exec_time = (t3 - t2) * 1000 @@ -649,6 +777,10 @@ def run_dict(self, stac_dict: Dict[str, Any], source_name: str = "in-memory"): t2 = time.perf_counter() try: validator(item) + # Run logical firewalls + self._validate_datetime_range(item) + if self.validate_geometry: + self._validate_geometry(item) t3 = time.perf_counter() total_exec_ms += (t3 - t2) * 1000 valid_count += 1 @@ -663,6 +795,15 @@ def run_dict(self, stac_dict: Dict[str, Any], source_name: str = "in-memory"): if error_msg not in error_registry: error_registry[error_msg] = [] error_registry[error_msg].append(item_id) + except ValueError as e: + t3 = time.perf_counter() + total_exec_ms += (t3 - t2) * 1000 + invalid_count += 1 + self.valid = False + error_msg = str(e) + if error_msg not in error_registry: + error_registry[error_msg] = [] + error_registry[error_msg].append(item_id) except Exception as e: t3 = time.perf_counter() total_exec_ms += (t3 - t2) * 1000