giga-spatial 0.6.5__py3-none-any.whl → 0.6.6__py3-none-any.whl

gigaspatial/handlers/base.py

@@ -1,4 +1,5 @@
 from abc import ABC, abstractmethod
+from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any, List, Optional, Union, Tuple, Callable, Iterable
 import pandas as pd
@@ -13,7 +14,6 @@ from gigaspatial.core.io.data_store import DataStore
 from gigaspatial.core.io.local_data_store import LocalDataStore
 from gigaspatial.core.io.readers import read_dataset
 from gigaspatial.processing.tif_processor import TifProcessor
-from dataclasses import dataclass, field
 
 
 @dataclass
@@ -584,6 +584,8 @@ class BaseHandler(ABC):
             bool: True if data is available after this operation
         """
         try:
+            data_units = None
+            data_paths = None
             # Resolve what data units are needed
             if hasattr(self.config, "get_relevant_data_units"):
                 data_units = self.config.get_relevant_data_units(source, **kwargs)
@@ -606,11 +608,29 @@ class BaseHandler(ABC):
                 if not missing_paths:
                     self.logger.info("All required data is already available")
                     return True
-
-            # Download missing or all data
-            if hasattr(self.config, "get_relevant_data_units"):
-                data_units = self.config.get_relevant_data_units(source, **kwargs)
-                self.downloader.download_data_units(data_units, **kwargs)
+            else:
+                # If force_download, treat all as missing
+                missing_paths = data_paths
+
+            if not missing_paths:
+                self.logger.info("No missing data to download.")
+                return True
+
+            # Download logic
+            if data_units is not None:
+                # Map data_units to their paths and select only those that are missing
+                unit_to_path = dict(zip(data_units, data_paths))
+                if force_download:
+                    # Download all units if force_download
+                    self.downloader.download_data_units(data_units, **kwargs)
+                else:
+                    missing_units = [
+                        unit
+                        for unit, path in unit_to_path.items()
+                        if path in missing_paths
+                    ]
+                    if missing_units:
+                        self.downloader.download_data_units(missing_units, **kwargs)
             else:
                 self.downloader.download(source, **kwargs)
 

gigaspatial/handlers/boundaries.py

@@ -291,6 +291,56 @@ class AdminBoundaries(BaseModel):
                 country_code, admin_level, "geoBoundaries"
             )
 
+    @classmethod
+    def from_global_country_boundaries(cls, scale: str = "medium") -> "AdminBoundaries":
+        """
+        Load global country boundaries from Natural Earth Data.
+
+        Args:
+            scale (str): One of 'large', 'medium', 'small'.
+                - 'large'  -> 10m
+                - 'medium' -> 50m
+                - 'small'  -> 110m
+        Returns:
+            AdminBoundaries: All country boundaries at admin_level=0
+        """
+        scale_map = {
+            "large": "10m",
+            "medium": "50m",
+            "small": "110m",
+        }
+        if scale not in scale_map:
+            raise ValueError(
+                f"Invalid scale '{scale}'. Choose from 'large', 'medium', 'small'."
+            )
+        scale_folder = scale_map[scale]
+        url = f"https://naciscdn.org/naturalearth/{scale_folder}/cultural/ne_{scale_folder}_admin_0_countries.zip"
+        cls.logger.info(f"Loading Natural Earth global country boundaries from {url}")
+        try:
+            gdf = gpd.read_file(url)
+            # Map fields to AdminBoundary schema
+            boundaries = []
+            for _, row in gdf.iterrows():
+                iso_a3 = row.get("ISO_A3_EH") or row.get("ISO_A3") or row.get("ADM0_A3")
+                name = row.get("NAME") or row.get("ADMIN") or row.get("SOVEREIGNT")
+                geometry = row.get("geometry")
+                if not iso_a3 or not name or geometry is None:
+                    continue
+                boundary = AdminBoundary(
+                    id=iso_a3,
+                    name=name,
+                    geometry=geometry,
+                    country_code=iso_a3,
+                )
+                boundaries.append(boundary)
+            cls.logger.info(
+                f"Loaded {len(boundaries)} country boundaries from Natural Earth."
+            )
+            return cls(boundaries=boundaries, level=0)
+        except Exception as e:
+            cls.logger.error(f"Failed to load Natural Earth global boundaries: {e}")
+            raise
+
     @classmethod
     def create(
         cls,

gigaspatial/handlers/ghsl.py

@@ -597,7 +597,7 @@ class GHSLDataReader(BaseHandlerReader):
         logger: Optional[logging.Logger] = None,
     ):
         """
-        Initialize the downloader.
+        Initialize the reader.
 
         Args:
             config: Configuration for the GHSL dataset, either as a GHSLDataConfig object or a dictionary of parameters
@@ -804,7 +804,7 @@ class GHSLDataHandler(BaseHandler):
         return pd.concat(
             [tp.to_dataframe() for tp in tif_processors], ignore_index=True
         )
-    
+
     def load_into_geodataframe(
         self,
         source: Union[
@@ -817,7 +817,7 @@ class GHSLDataHandler(BaseHandler):
         ],
         ensure_available: bool = True,
         **kwargs,
-    ) -> pd.DataFrame:
+    ) -> gpd.GeoDataFrame:
         """
         Load GHSL data into a geopandas GeoDataFrame.
 
@@ -835,3 +835,15 @@ class GHSLDataHandler(BaseHandler):
         return pd.concat(
             [tp.to_geodataframe() for tp in tif_processors], ignore_index=True
         )
+
+    def get_available_data_info(
+        self,
+        source: Union[
+            str,  # country
+            List[Union[tuple, Point]],  # points
+            BaseGeometry,  # geometry
+            gpd.GeoDataFrame,  # geodataframe
+        ],
+        **kwargs,
+    ) -> dict:
+        return super().get_available_data_info(source, file_ext=".tif", **kwargs)