core-lens 0.1.dev151__tar.gz → 0.1.dev153__tar.gz

{core_lens-0.1.dev151 → core_lens-0.1.dev153}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: core-lens
-Version: 0.1.dev151
+Version: 0.1.dev153
 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.dev151 → core_lens-0.1.dev153}/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.dev151'
-__version_tuple__ = version_tuple = (0, 1, 'dev151')
+__version__ = version = '0.1.dev153'
+__version_tuple__ = version_tuple = (0, 1, 'dev153')
 
 __commit_id__ = commit_id = None

{core_lens-0.1.dev151 → core_lens-0.1.dev153}/src/core_lens/base/entity.py

@@ -474,7 +474,22 @@ class BaseEntity(ABC):
         if attr_kwargs:
             filter_expr = pl.lit(True)
             for col, val in attr_kwargs.items():
-                filter_expr = filter_expr & (pl.col(col) == val)
+                dtype = schema[col]
+                is_list_col = isinstance(dtype, pl.List) or dtype == pl.List
+                is_val_list = isinstance(val, (list, tuple, set))
+
+                if is_list_col:
+                    if is_val_list:
+                        filter_expr = filter_expr & (
+                            pl.col(col).list.set_intersection(list(val)).list.len() > 0
+                        )
+                    else:
+                        filter_expr = filter_expr & pl.col(col).list.contains(val)
+                else:
+                    if is_val_list:
+                        filter_expr = filter_expr & pl.col(col).is_in(list(val))
+                    else:
+                        filter_expr = filter_expr & (pl.col(col) == val)
             lf = lf.filter(filter_expr)
 
         if not entity_kwargs:

{core_lens-0.1.dev151 → core_lens-0.1.dev153}/src/core_lens/base/result.py

@@ -174,7 +174,7 @@ class Result:
         geo_lf = self.entity.geometry_lazy
         if len(key_cols) == 1 and keys_df.height < 50000:
             key = key_cols[0]
-            geo_lf = geo_lf.filter(pl.col(key).is_in(keys_df[key]))
+            geo_lf = geo_lf.filter(pl.col(key).is_in(keys_df[key].to_list()))
         else:
             geo_lf = geo_lf.join(keys_df.lazy(), on=key_cols, how="semi")
 

{core_lens-0.1.dev151 → core_lens-0.1.dev153}/src/core_lens/utils/polars_utils.py

@@ -146,7 +146,7 @@ def scan_with_key_filter(
         # predicate pushdown in the Parquet reader, avoiding a full table scan.
         # The literal tree RAM issue only occurs with hundreds of thousands of keys.
         key = key_cols[0]
-        lf = lf.filter(pl.col(key).is_in(kv_df[key]))
+        lf = lf.filter(pl.col(key).is_in(kv_df[key].to_list()))
     else:
         # Fallback to semi-join for massive key arrays (e.g. state-wide scopes)
         lf = lf.join(kv_df.lazy(), on=key_cols, how="semi")