diff --git a/python/python/lancedb/_blob.py b/python/python/lancedb/_blob.py index 926769f48..5b4c0c343 100644 --- a/python/python/lancedb/_blob.py +++ b/python/python/lancedb/_blob.py @@ -270,7 +270,8 @@ def _iter_projection_pairs( if isinstance(expr, str): yield name, expr elif isinstance(expr, Expr): - yield name, expr.to_sql() + source = expr._column_name() + yield name, source if source is not None else expr.to_sql() return for column in projection: if isinstance(column, str): @@ -280,7 +281,8 @@ def _iter_projection_pairs( if isinstance(expr, str): yield name, expr elif isinstance(expr, Expr): - yield name, expr.to_sql() + source = expr._column_name() + yield name, source if source is not None else expr.to_sql() def _set_blob_column(tbl: pa.Table, output_name: str, blobs: pa.Array) -> pa.Table: diff --git a/python/python/lancedb/_lancedb.pyi b/python/python/lancedb/_lancedb.pyi index 47e727f99..9ba991322 100644 --- a/python/python/lancedb/_lancedb.pyi +++ b/python/python/lancedb/_lancedb.pyi @@ -87,6 +87,7 @@ class PyExpr: def contains(self, substr: "PyExpr") -> "PyExpr": ... def isin(self, values: List["PyExpr"]) -> "PyExpr": ... def cast(self, data_type: pa.DataType) -> "PyExpr": ... + def column_name(self) -> Optional[str]: ... def to_sql(self) -> str: ... def expr_col(name: str) -> PyExpr: ... diff --git a/python/python/lancedb/expr.py b/python/python/lancedb/expr.py index e8b2d63a4..752bb2fa0 100644 --- a/python/python/lancedb/expr.py +++ b/python/python/lancedb/expr.py @@ -248,6 +248,10 @@ class Expr: # ── utilities ──────────────────────────────────────────────────────────── + def _column_name(self) -> str | None: + """Return the source name when this is a bare column expression.""" + return self._inner.column_name() + def to_sql(self) -> str: """Render the expression as a SQL string (useful for debugging).""" return self._inner.to_sql() diff --git a/python/python/tests/test_blob.py b/python/python/tests/test_blob.py index b205c20a6..fc8dd0296 100644 --- a/python/python/tests/test_blob.py +++ b/python/python/tests/test_blob.py @@ -8,7 +8,12 @@ import pyarrow.compute as pc import pytest import lancedb -from lancedb._blob import read_row_ids_from_hits, stash_auto_row_ids +from lancedb._blob import ( + blob_v2_projection_sources, + read_row_ids_from_hits, + stash_auto_row_ids, +) +from lancedb.expr import col from lancedb.index import FTS from lancedb.schema import blob_column_paths, blob_v2_column_paths @@ -70,6 +75,14 @@ def test_blob_v2_column_paths_include_list_children(): ] +def test_blob_v2_projection_sources_use_typed_column_name(): + schema = pa.schema([lancedb.blob("blob")]) + + assert blob_v2_projection_sources(schema, {"blob_alias": col("blob")}) == { + "blob_alias": "blob" + } + + def _legacy_v1_table(name): db = lancedb.connect("memory:///") schema = pa.schema( diff --git a/python/src/expr.rs b/python/src/expr.rs index 242e88b05..6ef91ed10 100644 --- a/python/src/expr.rs +++ b/python/src/expr.rs @@ -130,6 +130,14 @@ impl PyExpr { // ── utilities ──────────────────────────────────────────────────────────── + /// Return the referenced column name for a bare column expression. + fn column_name(&self) -> Option { + match &self.0 { + DfExpr::Column(column) if column.relation.is_none() => Some(column.name.clone()), + _ => None, + } + } + /// Render the expression as a SQL string (useful for debugging). fn to_sql(&self) -> PyResult { lancedb::expr::expr_to_sql_string(&self.0).map_err(|e| PyValueError::new_err(e.to_string()))