datachain 0.34.4__py3-none-any.whl → 0.34.6__py3-none-any.whl

datachain/lib/udf.py

@@ -160,9 +160,15 @@ class UDFBase(AbstractUDF):
         """
         Creates SHA hash of this UDF function. It takes into account function,
         inputs and outputs.
+
+        For function-based UDFs, hashes self._func.
+        For class-based UDFs, hashes the process method.
         """
+        # Hash user code: either _func (function-based) or process method (class-based)
+        func_to_hash = self._func if self._func else self.process
+
         parts = [
-            hash_callable(self._func),
+            hash_callable(func_to_hash),
             self.params.hash() if self.params else "",
             self.output.hash(),
         ]

datachain/query/dataset.py

@@ -982,18 +982,26 @@ class SQLUnion(Step):
 
         columns1, columns2 = _order_columns(q1.columns, q2.columns)
 
+        union_select = sqlalchemy.select(*columns1).union_all(
+            sqlalchemy.select(*columns2)
+        )
+        union_cte = union_select.cte()
+        regenerated = self.query1.catalog.warehouse._regenerate_system_columns(
+            union_cte
+        )
+        result_columns = tuple(regenerated.selected_columns)
+
         def q(*columns):
-            names = {c.name for c in columns}
-            col1 = [c for c in columns1 if c.name in names]
-            col2 = [c for c in columns2 if c.name in names]
-            res = sqlalchemy.select(*col1).union_all(sqlalchemy.select(*col2))
+            if not columns:
+                return regenerated
 
-            subquery = res.subquery()
-            return sqlalchemy.select(*subquery.c).select_from(subquery)
+            names = {c.name for c in columns}
+            selected = [c for c in result_columns if c.name in names]
+            return regenerated.with_only_columns(*selected)
 
         return step_result(
             q,
-            columns1,
+            result_columns,
             dependencies=self.query1.dependencies | self.query2.dependencies,
         )
 

datachain/query/utils.py

@@ -2,12 +2,16 @@ from typing import Optional, Union
 
 import sqlalchemy as sa
 
-ColT = Union[sa.Column, sa.ColumnElement, sa.TextClause, sa.Label]
+ColT = Union[sa.ColumnClause, sa.Column, sa.ColumnElement, sa.TextClause, sa.Label]
 
 
 def column_name(col: ColT) -> str:
     """Returns column name from column element."""
-    return col.name if isinstance(col, (sa.Column, sa.Label)) else str(col)
+    return (
+        col.name
+        if isinstance(col, (sa.ColumnClause, sa.Column, sa.Label))
+        else str(col)
+    )
 
 
 def get_query_column(query: sa.Select, name: str) -> Optional[ColT]:

{datachain-0.34.4.dist-info → datachain-0.34.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.34.4
+Version: 0.34.6
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.34.4.dist-info → datachain-0.34.6.dist-info}/RECORD

@@ -93,7 +93,7 @@ datachain/lib/settings.py,sha256=xBQEPZfgaYKhHIFLd0u5CBTYDcJS8ZHCm47x7GJErFU,766
 datachain/lib/signal_schema.py,sha256=NsL2ISnSRN-lKRpXzB9CtsUj2tVKcoAe73TaaZKMT-0,40774
 datachain/lib/tar.py,sha256=MLcVjzIgBqRuJacCNpZ6kwSZNq1i2tLyROc8PVprHsA,999
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
-datachain/lib/udf.py,sha256=DdUxGBo9Y7Jz6aTBKgwex7YfK1RNaGm1JUlXCqs7qnw,18122
+datachain/lib/udf.py,sha256=bU_7xj6Mz4SsajFJ6tmrZm9Ygoi1ESoOyh1Q00W2zX4,18389
 datachain/lib/udf_signature.py,sha256=Yz20iJ-WF1pijT3hvcDIKFzgWV9gFxZM73KZRx3NbPk,7560
 datachain/lib/utils.py,sha256=RLji1gHnfDXtJCnBo8BcNu1obndFpVsXJ_1Vb-FQ9Qo,4554
 datachain/lib/video.py,sha256=ddVstiMkfxyBPDsnjCKY0d_93bw-DcMqGqN60yzsZoo,6851
@@ -131,7 +131,7 @@ datachain/model/ultralytics/pose.py,sha256=pvoXrWWUSWT_UBaMwUb5MBHAY57Co2HFDPigF
 datachain/model/ultralytics/segment.py,sha256=v9_xDxd5zw_I8rXsbl7yQXgEdTs2T38zyY_Y4XGN8ok,3194
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=ocPeNgrJM6Y_6SYCx3O2cwlCFAhNMfoYgB99GP6A1Bg,4294
-datachain/query/dataset.py,sha256=RQLNc368vrKI6EdsugbXWFbJobl430yXV-Ks1i4sdfo,67893
+datachain/query/dataset.py,sha256=I55ubMnoWpjoc4Ntw8zbp-i-49w0I95J7hCk_OCU6IU,68110
 datachain/query/dispatch.py,sha256=pygp7xg3lUDKlYHhecKxW5fB3zOSX1fPJfZBU4dfijk,16067
 datachain/query/metrics.py,sha256=DOK5HdNVaRugYPjl8qnBONvTkwjMloLqAr7Mi3TjCO0,858
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
@@ -139,7 +139,7 @@ datachain/query/queue.py,sha256=v0UeK4ilmdiRoJ5OdjB5qpnHTYDxRP4vhVp5Iw_toaI,3512
 datachain/query/schema.py,sha256=qLpEyvnzKlNCOrThQiTNpUKTUEsVIHT9trt-0UMt6ko,6704
 datachain/query/session.py,sha256=gKblltJAVQAVSTswAgWGDgGbpmFlFzFVkIQojDCjgXM,6809
 datachain/query/udf.py,sha256=jqutTpvkT6eHl96ZEgYiiTMAhI7vmTQA6JH9y4WCibI,1405
-datachain/query/utils.py,sha256=a2PTBZ3qsG6XlUcp9XsoGiQfKkca4Q3m-VzFgiGQPAc,1230
+datachain/query/utils.py,sha256=K2yECxgc6ywcSV-XenzpFL9csZbtbRtoDn36_Sni2M0,1296
 datachain/remote/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/remote/studio.py,sha256=amjcV0B8qumsVBnxPQnt8oSrnfMK2vAdOurVMA9L_zA,16868
 datachain/sql/__init__.py,sha256=8D2omsBiATt8bjLjGo6jBEtaKEkOlnlNFWhVryHMDv0,388
@@ -165,9 +165,9 @@ datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
 datachain/toolkit/split.py,sha256=ktGWzY4kyzjWyR86dhvzw-Zhl0lVk_LOX3NciTac6qo,2914
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.34.4.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.34.4.dist-info/METADATA,sha256=pjivvNYJPbaTLyOpWYRJiaaoyC8k-LUaDl-dczGFUQc,13655
-datachain-0.34.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datachain-0.34.4.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.34.4.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.34.4.dist-info/RECORD,,
+datachain-0.34.6.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.34.6.dist-info/METADATA,sha256=Bp94LT21H__KZ3gAyTsqd-xt-oM-4o8qht42-wsf9CQ,13655
+datachain-0.34.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datachain-0.34.6.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.34.6.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.34.6.dist-info/RECORD,,