fix(python): preserve typed blob projection sources

This commit is contained in:
Gatefixer
2026-08-06 09:12:57 +00:00
parent 0d582eb612
commit 024bf9f569
5 changed files with 31 additions and 3 deletions
+4 -2
View File
@@ -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:
+1
View File
@@ -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: ...
+4
View File
@@ -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()
+14 -1
View File
@@ -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(
+8
View File
@@ -130,6 +130,14 @@ impl PyExpr {
// ── utilities ────────────────────────────────────────────────────────────
/// Return the referenced column name for a bare column expression.
fn column_name(&self) -> Option<String> {
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<String> {
lancedb::expr::expr_to_sql_string(&self.0).map_err(|e| PyValueError::new_err(e.to_string()))