mapchete-eo 2025.10.0__py2.py3-none-any.whl → 2025.11.0__py2.py3-none-any.whl

mapchete_eo/platforms/sentinel2/_mapper_registry.py

@@ -0,0 +1,89 @@
+from typing import List, Callable, Dict, Any, Optional
+
+from pystac import Item
+
+from mapchete_eo.platforms.sentinel2.metadata_parser.s2metadata import S2Metadata
+from mapchete_eo.platforms.sentinel2.types import DataArchive, MetadataArchive
+
+
+# decorators for mapper functions using the registry pattern #
+##############################################################
+ID_MAPPER_REGISTRY: Dict[Any, Callable[[Item], Item]] = {}
+STAC_METADATA_MAPPER_REGISTRY: Dict[Any, Callable[[Item], Item]] = {}
+S2METADATA_MAPPER_REGISTRY: Dict[Any, Callable[[Item], S2Metadata]] = {}
+
+MAPPER_REGISTRIES: Dict[str, Any] = {
+    "ID": ID_MAPPER_REGISTRY,
+    "STAC metadata": STAC_METADATA_MAPPER_REGISTRY,
+    "S2Metadata": S2METADATA_MAPPER_REGISTRY,
+}
+
+
+def _register_func(registry: Dict[str, Callable], key: Any, func: Callable):
+    if key in registry:
+        raise ValueError(f"{key} already registered in {registry}")
+    registry[key] = func
+
+
+def maps_item_id(from_collections: List[str]):
+    """
+    Decorator registering mapper to common ID.
+    """
+
+    def decorator(func):
+        # Use a tuple of the metadata as the key
+        # key = (path_type, version)
+        for collection in from_collections:
+            _register_func(registry=ID_MAPPER_REGISTRY, key=collection, func=func)
+        return func
+
+    return decorator
+
+
+def maps_stac_metadata(
+    from_collections: List[str], to_data_archives: Optional[List[DataArchive]] = None
+):
+    """
+    Decorator registering STAC metadata mapper.
+    """
+
+    def decorator(func):
+        # Use a tuple of the metadata as the key
+        for collection in from_collections:
+            if to_data_archives:
+                for data_archive in to_data_archives:
+                    _register_func(
+                        registry=STAC_METADATA_MAPPER_REGISTRY,
+                        key=(collection, data_archive),
+                        func=func,
+                    )
+            else:
+                _register_func(
+                    registry=STAC_METADATA_MAPPER_REGISTRY,
+                    key=collection,
+                    func=func,
+                )
+        return func
+
+    return decorator
+
+
+def creates_s2metadata(
+    from_collections: List[str], to_metadata_archives: List[MetadataArchive]
+):
+    """
+    Decorator registering S2Metadata creator.
+    """
+
+    def decorator(func):
+        # Use a tuple of the metadata as the key
+        for collection in from_collections:
+            for metadata_archive in to_metadata_archives:
+                _register_func(
+                    registry=S2METADATA_MAPPER_REGISTRY,
+                    key=(collection, metadata_archive),
+                    func=func,
+                )
+        return func
+
+    return decorator

mapchete_eo/platforms/sentinel2/brdf/correction.py

@@ -13,7 +13,7 @@ from rasterio.fill import fillnodata
 
 from mapchete_eo.exceptions import BRDFError
 from mapchete_eo.platforms.sentinel2.brdf.models import BRDFModels, get_model
-from mapchete_eo.platforms.sentinel2.metadata_parser import S2Metadata
+from mapchete_eo.platforms.sentinel2.metadata_parser.s2metadata import S2Metadata
 from mapchete_eo.platforms.sentinel2.types import (
     L2ABand,
     Resolution,

mapchete_eo/platforms/sentinel2/brdf/hls.py

@@ -16,7 +16,7 @@ from mapchete_eo.platforms.sentinel2.brdf.protocols import (
 )
 from mapchete_eo.platforms.sentinel2.brdf.config import L2ABandFParams, ModelParameters
 from mapchete_eo.platforms.sentinel2.brdf.sun_angle_arrays import get_sun_zenith_angles
-from mapchete_eo.platforms.sentinel2.metadata_parser import S2Metadata
+from mapchete_eo.platforms.sentinel2.metadata_parser.s2metadata import S2Metadata
 from mapchete_eo.platforms.sentinel2.types import L2ABand
 
 

mapchete_eo/platforms/sentinel2/brdf/models.py

@@ -12,7 +12,7 @@ from mapchete_eo.platforms.sentinel2.brdf.hls import HLS
 from mapchete_eo.platforms.sentinel2.brdf.ross_thick import RossThick
 
 # from mapchete_eo.platforms.sentinel2.brdf.hls2 import HLS2
-from mapchete_eo.platforms.sentinel2.metadata_parser import S2Metadata
+from mapchete_eo.platforms.sentinel2.metadata_parser.s2metadata import S2Metadata
 from mapchete_eo.platforms.sentinel2.types import L2ABand
 
 logger = logging.getLogger(__name__)

mapchete_eo/platforms/sentinel2/brdf/protocols.py

@@ -6,7 +6,7 @@ from mapchete.io.raster import ReferencedRaster
 import numpy as np
 from numpy.typing import DTypeLike
 
-from mapchete_eo.platforms.sentinel2.metadata_parser import S2Metadata
+from mapchete_eo.platforms.sentinel2.metadata_parser.s2metadata import S2Metadata
 from mapchete_eo.platforms.sentinel2.types import L2ABand
 
 

mapchete_eo/platforms/sentinel2/brdf/ross_thick.py

@@ -14,7 +14,7 @@ from mapchete_eo.platforms.sentinel2.brdf.protocols import (
 )
 from mapchete_eo.platforms.sentinel2.brdf.config import L2ABandFParams, ModelParameters
 from mapchete_eo.platforms.sentinel2.brdf.hls import _get_viewing_angles
-from mapchete_eo.platforms.sentinel2.metadata_parser import S2Metadata
+from mapchete_eo.platforms.sentinel2.metadata_parser.s2metadata import S2Metadata
 from mapchete_eo.platforms.sentinel2.types import L2ABand
 
 

mapchete_eo/platforms/sentinel2/brdf/sun_angle_arrays.py

@@ -3,7 +3,7 @@ from typing import Tuple
 from fiona.transform import transform
 import numpy as np
 
-from mapchete_eo.platforms.sentinel2.metadata_parser import S2Metadata
+from mapchete_eo.platforms.sentinel2.metadata_parser.s2metadata import S2Metadata
 
 
 def get_sun_zenith_angles(s2_metadata: S2Metadata) -> np.ndarray:

mapchete_eo/platforms/sentinel2/config.py

@@ -1,18 +1,19 @@
 from __future__ import annotations
 
-from typing import List, Optional, Union
+from typing import List, Optional, Union, Dict, Any
+import warnings
 
 from mapchete.path import MPathLike
-from pydantic import (
-    BaseModel,
-    ValidationError,
-    field_validator,
-)
+from pydantic import BaseModel, ValidationError, field_validator, model_validator
 
 from mapchete_eo.base import BaseDriverConfig
 from mapchete_eo.io.path import ProductPathGenerationMethod
-from mapchete_eo.platforms.sentinel2.archives import ArchiveClsFromString, AWSL2ACOGv1
 from mapchete_eo.platforms.sentinel2.brdf.config import BRDFModels
+from mapchete_eo.platforms.sentinel2.preconfigured_sources import (
+    KNOWN_SOURCES,
+    DEPRECATED_ARCHIVES,
+)
+from mapchete_eo.platforms.sentinel2.source import Sentinel2Source
 from mapchete_eo.platforms.sentinel2.types import (
     CloudType,
     ProductQIMaskResolution,
@@ -23,6 +24,9 @@ from mapchete_eo.search.config import StacSearchConfig
 from mapchete_eo.types import TimeRange
 
 
+default_source = Sentinel2Source.model_validate(KNOWN_SOURCES["EarthSearch"])
+
+
 class BRDFModelConfig(BaseModel):
     model: BRDFModels = BRDFModels.HLS
     bands: List[str] = ["blue", "green", "red", "nir"]
@@ -47,7 +51,7 @@ class BRDFSCLClassConfig(BRDFModelConfig):
                 out.append(value)
             elif isinstance(value, str):
                 out.append(SceneClassification[value])
-            else:
+            else:  # pragma: no cover
                 raise ValidationError("value must be mappable to SceneClassification")
         return out
 
@@ -107,10 +111,18 @@ class CacheConfig(BaseModel):
 class Sentinel2DriverConfig(BaseDriverConfig):
     format: str = "Sentinel-2"
     time: Union[TimeRange, List[TimeRange]]
-    archive: ArchiveClsFromString = AWSL2ACOGv1
-    cat_baseurl: Optional[MPathLike] = None
+
+    # new
+    source: List[Sentinel2Source] = [default_source]
+
+    # deprecated
+    # for backwards compatibility, archive should be converted to
+    # catalog & data_archive
+    # archive: ArchiveClsFromString = AWSL2ACOGv1
+    # cat_baseurl: Optional[MPathLike] = None
     search_index: Optional[MPathLike] = None
-    max_cloud_cover: float = 100.0
+
+    # custom params
     stac_config: StacSearchConfig = StacSearchConfig()
     first_granule_only: bool = False
     utm_zone: Optional[int] = None
@@ -118,6 +130,54 @@ class Sentinel2DriverConfig(BaseDriverConfig):
     brdf: Optional[BRDFConfig] = None
     cache: Optional[CacheConfig] = None
 
+    @model_validator(mode="before")
+    def deprecated_values(cls, values: Dict[str, Any]) -> Dict[str, Any]:
+        archive = values.pop("archive", None)
+        if archive:
+            warnings.warn(
+                "'archive' will be deprecated soon. Please use 'source'.",
+                category=DeprecationWarning,
+                stacklevel=2,
+            )
+            if values.get("source") is None:
+                values["source"] = DEPRECATED_ARCHIVES[archive]
+
+        cat_baseurl = values.pop("cat_baseurl", None)
+        if cat_baseurl:  # pragma: no cover
+            warnings.warn(
+                "'cat_baseurl' will be deprecated soon. Please use 'catalog_type=static' in the source.",
+                category=DeprecationWarning,
+                stacklevel=2,
+            )
+            if values.get("source", []):
+                raise ValueError(
+                    "deprecated cat_baseurl field found alongside sources."
+                )
+            values["source"] = [dict(collection=cat_baseurl, catalog_type="static")]
+
+        # add default source if necessary
+        sources = values.get("source", [])
+        if not sources:
+            values["source"] = [default_source.model_dump(exclude_none=True)]
+
+        max_cloud_cover = values.pop("max_cloud_cover", None)
+        if max_cloud_cover:  # pragma: no cover
+            warnings.warn(
+                "'max_cloud_cover' will be deprecated soon. Please use 'eo:cloud_cover<=...' in the source 'query' field.",
+                category=DeprecationWarning,
+                stacklevel=2,
+            )
+            updated_sources = []
+            for source in values.get("source", []):
+                if source.get("query") is not None:
+                    raise ValueError(
+                        f"deprecated max_cloud_cover is set but also a query field is given in {source}"
+                    )
+                source["query"] = f"eo:cloud_cover<={max_cloud_cover}"
+                updated_sources.append(source)
+            values["source"] = updated_sources
+        return values
+
 
 class MaskConfig(BaseModel):
     # mask by footprint geometry
@@ -160,7 +220,7 @@ class MaskConfig(BaseModel):
                 out.append(value)
             elif isinstance(value, str):
                 out.append(SceneClassification[value])
-            else:
+            else:  # pragma: no cover
                 raise ValidationError("value must be mappable to SceneClassification")
         return out
 
@@ -175,7 +235,7 @@ class MaskConfig(BaseModel):
         elif isinstance(config, dict):
             return MaskConfig(**config)
 
-        else:
+        else:  # pragma: no cover
             raise TypeError(
                 f"mask configuration should either be a dictionary or a MaskConfig object, not {config}"
             )

mapchete_eo/platforms/sentinel2/driver.py

@@ -1,16 +1,11 @@
 from typing import Optional, List, Tuple
 
-from mapchete.geometry import reproject_geometry
-from mapchete.path import MPath
 from mapchete.types import NodataVal
 from rasterio.enums import Resampling
 
 from mapchete_eo import base
-from mapchete_eo.archives.base import Archive
 from mapchete_eo.platforms.sentinel2.config import Sentinel2DriverConfig
 from mapchete_eo.platforms.sentinel2.preprocessing_tasks import parse_s2_product
-from mapchete_eo.search.stac_static import STACStaticCatalog
-from mapchete_eo.settings import mapchete_eo_settings
 from mapchete_eo.types import MergeMethod
 
 METADATA: dict = {
@@ -42,37 +37,3 @@ class InputData(base.InputData):
     driver_config_model = Sentinel2DriverConfig
     params: Sentinel2DriverConfig
     input_tile_cls = Sentinel2Cube
-
-    def set_archive(self, base_dir: MPath):
-        if self.params.cat_baseurl:
-            self.archive = Archive(
-                catalog=STACStaticCatalog(
-                    baseurl=MPath(self.params.cat_baseurl).absolute_path(
-                        base_dir=base_dir
-                    ),
-                ),
-                area=self.bbox(mapchete_eo_settings.default_catalog_crs),
-                time=self.time,
-                search_kwargs=dict(max_cloud_cover=self.params.max_cloud_cover),
-            )
-        elif self.params.archive:
-            catalog_area = reproject_geometry(
-                self.area,
-                src_crs=self.crs,
-                dst_crs=mapchete_eo_settings.default_catalog_crs,
-            )
-            self.archive = self.params.archive(
-                time=self.time,
-                bounds=catalog_area.bounds,
-                area=catalog_area,
-                search_kwargs=dict(
-                    search_index=(
-                        MPath(self.params.search_index).absolute_path(base_dir=base_dir)
-                        if self.params.search_index
-                        else None
-                    ),
-                    max_cloud_cover=self.params.max_cloud_cover,
-                ),
-            )
-        else:
-            raise ValueError("either 'archive' or 'cat_baseurl' or both is required.")

mapchete_eo/platforms/sentinel2/metadata_parser/__init__.py

@@ -0,0 +1,6 @@
+from mapchete_eo.platforms.sentinel2.metadata_parser.s2metadata import (
+    S2Metadata,
+    S2MetadataPathMapper,
+)
+
+__all__ = ["S2Metadata", "S2MetadataPathMapper"]

mapchete_eo/platforms/sentinel2/{path_mappers → metadata_parser}/base.py

@@ -11,7 +11,7 @@ from mapchete_eo.platforms.sentinel2.types import (
 )
 
 
-class S2PathMapper(ABC):
+class S2MetadataPathMapper(ABC):
     """
     Abstract class to help mapping asset paths from metadata.xml to their
     locations of various data archives.

mapchete_eo/platforms/sentinel2/{path_mappers/metadata_xml.py → metadata_parser/default_path_mapper.py}

@@ -11,7 +11,7 @@ from typing import Optional
 from mapchete.path import MPath
 
 from mapchete_eo.io import open_xml
-from mapchete_eo.platforms.sentinel2.path_mappers.base import S2PathMapper
+from mapchete_eo.platforms.sentinel2.metadata_parser.base import S2MetadataPathMapper
 from mapchete_eo.platforms.sentinel2.processing_baseline import ProcessingBaseline
 from mapchete_eo.platforms.sentinel2.types import (
     BandQI,
@@ -23,7 +23,7 @@ from mapchete_eo.platforms.sentinel2.types import (
 logger = logging.getLogger(__name__)
 
 
-class XMLMapper(S2PathMapper):
+class XMLMapper(S2MetadataPathMapper):
     def __init__(
         self, metadata_xml: MPath, xml_root: Optional[Element] = None, **kwargs
     ):

mapchete_eo/platforms/sentinel2/metadata_parser/models.py

@@ -0,0 +1,78 @@
+from __future__ import annotations
+
+import logging
+import warnings
+from typing import Dict
+
+import numpy as np
+import numpy.ma as ma
+from pydantic import BaseModel
+from mapchete.io.raster import ReferencedRaster
+from rasterio.fill import fillnodata
+
+from mapchete_eo.exceptions import CorruptedProductMetadata
+from mapchete_eo.platforms.sentinel2.types import (
+    SunAngle,
+    ViewAngle,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class SunAngleData(BaseModel):
+    model_config = dict(arbitrary_types_allowed=True)
+    raster: ReferencedRaster
+    mean: float
+
+
+class SunAnglesData(BaseModel):
+    azimuth: SunAngleData
+    zenith: SunAngleData
+
+    def get_angle(self, angle: SunAngle) -> SunAngleData:
+        if angle == SunAngle.azimuth:
+            return self.azimuth
+        elif angle == SunAngle.zenith:
+            return self.zenith
+        else:
+            raise KeyError(f"unknown angle: {angle}")
+
+
+class ViewingIncidenceAngle(BaseModel):
+    model_config = dict(arbitrary_types_allowed=True)
+    detectors: Dict[int, ReferencedRaster]
+    mean: float
+
+    def merge_detectors(
+        self, fill_edges: bool = True, smoothing_iterations: int = 3
+    ) -> ReferencedRaster:
+        if not self.detectors:
+            raise CorruptedProductMetadata("no viewing incidence angles available")
+        sample = next(iter(self.detectors.values()))
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", category=RuntimeWarning)
+            merged = np.nanmean(
+                np.stack([raster.data for raster in self.detectors.values()]), axis=0
+            )
+        if fill_edges:
+            merged = fillnodata(
+                ma.masked_invalid(merged), smoothing_iterations=smoothing_iterations
+            )
+        return ReferencedRaster.from_array_like(
+            array_like=ma.masked_invalid(merged),
+            transform=sample.transform,
+            crs=sample.crs,
+        )
+
+
+class ViewingIncidenceAngles(BaseModel):
+    azimuth: ViewingIncidenceAngle
+    zenith: ViewingIncidenceAngle
+
+    def get_angle(self, angle: ViewAngle) -> ViewingIncidenceAngle:
+        if angle == ViewAngle.azimuth:
+            return self.azimuth
+        elif angle == ViewAngle.zenith:
+            return self.zenith
+        else:
+            raise KeyError(f"unknown angle: {angle}")