floe-python 0.8.4__tar.gz → 0.8.5__tar.gz

{floe_python-0.8.4 → floe_python-0.8.5}/CHANGELOG.md

@@ -2,6 +2,13 @@
 
 All notable changes to Floe are documented in this file.
 
+## v0.8.5
+
+- **An output column name collision now fails `floe validate`, not the run (#1080).** A column with an explicit
+  `source` keeps its `name`; a column without one is normalised. When the two end on the same output name,
+  `floe validate` passed and `floe run` then failed. Validate now rejects it, and the message names the two
+  columns as written instead of their normalised sources.
+
 ## v0.8.4
 
 - **Columns that normalise to the same name now fail `floe validate`, not the run (#1005).** With

{floe_python-0.8.4 → floe_python-0.8.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: floe-python
-Version: 0.8.4
+Version: 0.8.5
 Summary: Floe: a data-contract runtime for file ingestion
 License-File: LICENSE
 Requires-Python: >=3.11

{floe_python-0.8.4 → floe_python-0.8.5}/context/coding-standards.md

@@ -32,7 +32,8 @@ Context: `context/architecture.md` and `context/decisions/python-core-for-olf.md
 
 - No per-row Python loops on data. Use Polars or DuckDB expressions.
 - Keep memory bounded by the chunk or the batch, not the table: read in chunks, and let DuckDB
-  do anything that scans the target table (merges, unique checks against history).
+  do the merges. Unique checks against history semi-join each chunk with Polars against a local
+  cache of the target's key columns.
 
 ## Comments
 

{floe_python-0.8.4 → floe_python-0.8.5}/context/decisions/python-core-for-olf.md

@@ -69,6 +69,11 @@ gates below pass.
 | `merge_scd1` / `merge_scd2` | Chunks staged as Parquet, then one DuckDB `MERGE INTO` (merge-on-read, positional deletes). SCD2 sends each changed row twice: once to close the current version, once to insert the new one. | Spills to disk |
 | `unique` vs target history | DuckDB anti-join between staged keys and the table's key columns | Spills to disk |
 
+> **Note (2026-10-29, #1084):** the `unique` row above is no longer how the check runs. Since #1057
+> the target's key columns are cached locally once per entity, and each chunk semi-joins against that
+> cache with Polars (`src/floe/iceberg/unique.py`). DuckDB runs the merges only. The G6 result below
+> was measured with the DuckDB anti-join.
+
 Re-running an SCD1 merge with the same batch leaves the table unchanged, and an SCD2 batch with
 no changes adds no versions. Only `append` needs the retry guard.
 

{floe_python-0.8.4 → floe_python-0.8.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "floe-python"
-version = "0.8.4"
+version = "0.8.5"
 description = "Floe: a data-contract runtime for file ingestion"
 requires-python = ">=3.11"
 dependencies = [

{floe_python-0.8.4 → floe_python-0.8.5}/src/floe/checks/normalize.py

@@ -94,12 +94,12 @@ def output_column_mapping(
     targets: dict[str, str] = {}
     mapping: dict[str, str] = {}
     for column, target in zip(columns, output_names(columns, strategy), strict=True):
-        source = normalize_name(column.source or column.name, strategy)
         if target in targets:
             raise FloeConfigError(
-                f"output column name collision: {targets[target]} and {source} -> {target}"
+                f"output column name collision: {targets[target]} and {column.name} -> {target}"
             )
-        targets[target] = source
+        targets[target] = column.name
+        source = normalize_name(column.source or column.name, strategy)
         if source != target:
             mapping[source] = target
     return mapping

{floe_python-0.8.4 → floe_python-0.8.5}/src/floe/config/validate.py

@@ -6,6 +6,7 @@ from floe import __version__
 from floe.checks.cast import decimal_type
 from floe.checks.normalize import (
     normalize_name,
+    output_column_mapping,
     output_names,
     resolve_strategy,
     source_names,
@@ -416,7 +417,9 @@ def validate_schema(entity: EntityConfig, version: str) -> None:
             f"(allowed: {', '.join(NORMALIZE_STRATEGIES)})",
         )
     try:
-        source_names(schema.columns, resolve_strategy(schema))
+        resolved = resolve_strategy(schema)
+        source_names(schema.columns, resolved)
+        output_column_mapping(schema.columns, resolved)
     except FloeConfigError as err:
         raise _fail(entity, str(err)) from err
     mismatch = schema.mismatch

{floe_python-0.8.4 → floe_python-0.8.5}/tests/unit/config/test_validate.py

@@ -194,6 +194,17 @@ def test_columns_that_normalise_to_one_name_fail_validation(
     assert str(err.value) == f"entity.name=orders column source collision: {message}"
 
 
+def test_output_column_name_collision_fails_validation(tmp_path: Path) -> None:
+    columns = "[{name: a, source: X, type: string}, {name: A, type: string}]"
+    schema = f"{{columns: {columns}, normalize_columns: {{enabled: true}}}}"
+    with pytest.raises(FloeConfigError) as err:
+        check(tmp_path, schema)
+    assert (
+        str(err.value)
+        == "entity.name=orders output column name collision: a and A -> a"
+    )
+
+
 def test_valid_spellings(tmp_path: Path) -> None:
     check(
         tmp_path,

{floe_python-0.8.4 → floe_python-0.8.5}/uv.lock

@@ -450,7 +450,7 @@ wheels = [
 
 [[package]]
 name = "floe-python"
-version = "0.8.4"
+version = "0.8.5"
 source = { editable = "." }
 dependencies = [
     { name = "boto3" },