Spaces:
Paused
Paused
| """ | |
| GeoTIFF/TIFF validation and metadata extraction using Rasterio. | |
| Phase 3 (P0 — PS requirement: "Input upload and compatibility checking", | |
| GeoTIFF/TIFF input support). | |
| Kept deliberately simple: open with rasterio, pull out what the agent | |
| and evidence engine will need later (dimensions, band count, CRS, | |
| bounds, nodata). No reprojection, no resampling — that is out of scope | |
| for upload-time validation and belongs in Phase 4+ preprocessing steps | |
| that run per-task (e.g. co-registration checks for optical+SAR). | |
| """ | |
| from __future__ import annotations | |
| from dataclasses import dataclass | |
| from pathlib import Path | |
| from typing import Optional | |
| import rasterio | |
| from rasterio.errors import RasterioIOError | |
| class InvalidImageError(ValueError): | |
| """Raised when a file cannot be validated as a usable raster.""" | |
| class RasterMetadata: | |
| format: str | |
| driver: str | |
| width: int | |
| height: int | |
| band_count: int | |
| dtype: str | |
| crs: Optional[str] | |
| bounds: Optional[tuple] | |
| is_geospatial: bool | |
| nodata: Optional[float] | |
| # PS: "Supported formats: GeoTIFF or TIFF for geospatial imagery. PNG and | |
| # JPEG inputs may be accepted only for the prescribed public benchmark | |
| # datasets." We accept both but flag is_geospatial accordingly — PNG/JPEG | |
| # will not carry a CRS/transform and downstream geospatial features | |
| # (map overlay, bounds) must degrade gracefully for those. | |
| GEOSPATIAL_EXTENSIONS = {".tif", ".tiff"} | |
| BENCHMARK_EXTENSIONS = {".png", ".jpg", ".jpeg"} | |
| def validate_and_extract(path: Path) -> RasterMetadata: | |
| """ | |
| Open `path` with Rasterio and extract metadata. | |
| Raises InvalidImageError on anything Rasterio can't open, or on | |
| basic sanity-check failures (zero-size raster, no bands). | |
| """ | |
| ext = path.suffix.lower() | |
| if ext not in GEOSPATIAL_EXTENSIONS | BENCHMARK_EXTENSIONS: | |
| raise InvalidImageError( | |
| f"Unsupported file extension '{ext}'. Expected GeoTIFF/TIFF " | |
| f"({', '.join(sorted(GEOSPATIAL_EXTENSIONS))}) or a benchmark " | |
| f"image ({', '.join(sorted(BENCHMARK_EXTENSIONS))})." | |
| ) | |
| try: | |
| with rasterio.open(path) as src: | |
| if src.width == 0 or src.height == 0: | |
| raise InvalidImageError("Raster has zero width or height.") | |
| if src.count == 0: | |
| raise InvalidImageError("Raster has no bands.") | |
| crs = src.crs.to_string() if src.crs else None | |
| bounds = tuple(src.bounds) if src.crs else None | |
| return RasterMetadata( | |
| format="GeoTIFF/TIFF" if ext in GEOSPATIAL_EXTENSIONS else "benchmark-image", | |
| driver=src.driver, | |
| width=src.width, | |
| height=src.height, | |
| band_count=src.count, | |
| dtype=str(src.dtypes[0]) if src.dtypes else "unknown", | |
| crs=crs, | |
| bounds=bounds, | |
| is_geospatial=crs is not None, | |
| nodata=src.nodata, | |
| ) | |
| except RasterioIOError as exc: | |
| raise InvalidImageError(f"Could not open file as a raster: {exc}") from exc | |