core-lens 0.1.dev183__tar.gz → 0.1.dev184__tar.gz

{core_lens-0.1.dev183 → core_lens-0.1.dev184}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: core-lens
-Version: 0.1.dev183
+Version: 0.1.dev184
 Summary: Query, analyse, and visualise CoreStack's microwatershed and Earth science data through a clean, composable Python API.
 Project-URL: Homepage, https://github.com/ApoorvaKashyap/core-lens
 Project-URL: Issues, https://github.com/ApoorvaKashyap/core-lens/issues

{core_lens-0.1.dev183 → core_lens-0.1.dev184}/src/core_lens/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.1.dev183'
-__version_tuple__ = version_tuple = (0, 1, 'dev183')
+__version__ = version = '0.1.dev184'
+__version_tuple__ = version_tuple = (0, 1, 'dev184')
 
 __commit_id__ = commit_id = None

{core_lens-0.1.dev183 → core_lens-0.1.dev184}/src/core_lens/aoi.py

@@ -20,7 +20,7 @@ from loguru import logger
 
 from core_lens.base.entity import BaseEntity, EntityValidationError
 from core_lens.utils.paths import is_cloud_uri
-from core_lens.utils.polars_utils import cached_read_schema
+from core_lens.utils.polars_utils import cached_read_schema, parquet_scan_path
 
 if TYPE_CHECKING:
     from core_lens.base.view import View
@@ -225,7 +225,9 @@ def _cached_resolve_boundary(
     geom_col = schema.geometry_col
     static_path = candidate._resolve(candidate.static_path)
 
-    lf = pl.scan_parquet(static_path, storage_options=storage_options or None)
+    lf = pl.scan_parquet(
+        parquet_scan_path(static_path), storage_options=storage_options or None
+    )
     filter_expr = pl.lit(True)
     schema_types = cached_read_schema(static_path, storage_options)
     for col, val in entity_kwargs.items():

{core_lens-0.1.dev183 → core_lens-0.1.dev184}/src/core_lens/base/entity.py

@@ -29,7 +29,7 @@ from core_lens.utils.spatial import (
     build_bbox_index,
     exact_spatial_filter,
 )
-from core_lens.utils.polars_utils import cached_read_schema
+from core_lens.utils.polars_utils import cached_read_schema, parquet_scan_path
 
 if TYPE_CHECKING:
     import shapely
@@ -475,7 +475,7 @@ class BaseEntity(ABC):
                 )
 
         # --- Combine attribute and spatial filters into a single lazy pipeline ---
-        lf = pl.scan_parquet(static)
+        lf = pl.scan_parquet(parquet_scan_path(static))
 
         if attr_kwargs:
             filter_expr = pl.lit(True)

{core_lens-0.1.dev183 → core_lens-0.1.dev184}/src/core_lens/utils/polars_utils.py

@@ -7,6 +7,8 @@ import functools
 
 import polars as pl
 
+import os
+
 _GPU_AVAILABLE: bool | None = None  # None = not yet probed
 
 
@@ -16,9 +18,34 @@ def _so_key(storage_options: dict[str, Any] | None) -> tuple[tuple[str, Any], ..
     return tuple(sorted(storage_options.items()))
 
 
+def parquet_scan_path(path: str) -> str:
+    """Return a glob-safe path for ``pl.scan_parquet``.
+
+    When *path* is a directory polars will reject it if the directory contains
+    files with mixed extensions (e.g. a ``data_dictionary.csv`` sitting
+    alongside Hive-partitioned ``.parquet`` files).  This helper coerces a bare
+    directory to ``<path>/**/*.parquet`` so only Parquet files are matched.
+
+    Args:
+        path (str): Filesystem path or cloud URI to a Parquet file or directory.
+
+    Returns:
+        str: The original path if it already points to a file, otherwise
+        ``<path>/**/*.parquet``.
+    """
+    if os.path.isdir(path):
+        return os.path.join(path, "**", "*.parquet")
+    return path
+
+
 @functools.cache
 def _cached_schema_internal(path: str, so_key: tuple[tuple[str, Any], ...]) -> Any:
-    return pl.scan_parquet(path, storage_options=dict(so_key) or None).collect_schema()
+    # Coerce bare directory paths to a *.parquet glob so polars doesn't raise
+    # InvalidOperationError when the directory contains mixed-extension files
+    # (e.g. data_dictionary.csv alongside Hive-partitioned .parquet files).
+    return pl.scan_parquet(
+        parquet_scan_path(path), storage_options=dict(so_key) or None
+    ).collect_schema()
 
 
 def cached_read_schema(path: str, storage_options: dict[str, Any] | None = None) -> Any:

{core_lens-0.1.dev183 → core_lens-0.1.dev184}/src/core_lens/utils/spatial.py

@@ -12,6 +12,7 @@ import shapely
 from loguru import logger
 
 from core_lens.utils.paths import is_cloud_uri, path_exists, resolve_fs_and_path
+from core_lens.utils.polars_utils import parquet_scan_path
 
 if TYPE_CHECKING:
     pass
@@ -361,7 +362,7 @@ def exact_spatial_filter(
 
     # Build a lazy scan and push down an inner join to load only required geometries.
     full_df = (
-        pl.scan_parquet(static_path)
+        pl.scan_parquet(parquet_scan_path(static_path))
         .select(key_cols + [geometry_col])
         .join(candidates.select(key_cols).lazy(), on=key_cols, how="semi")
         .collect()
@@ -684,7 +685,7 @@ def point_in_entities(
         static_path: str = entity._resolve(entity.static_path)
 
         geom_df = (
-            pl.scan_parquet(static_path)
+            pl.scan_parquet(parquet_scan_path(static_path))
             .select(key_cols + [geom_col])
             .join(candidates.select(key_cols).lazy(), on=key_cols, how="semi")
             .collect()