drop owner_id and owner_name signals

src/datachain/catalog/catalog.py

@@ -544,8 +544,6 @@ def find_column_to_str(  # noqa: PLR0911
         )
     if column == "name":
         return posixpath.basename(row[field_lookup["path"]]) or ""
-    if column == "owner":
-        return row[field_lookup["owner_name"]] or ""
     if column == "path":
         is_dir = row[field_lookup["dir_type"]] == DirType.DIR
         path = row[field_lookup["path"]]
@@ -735,8 +733,6 @@ def enlist_source(
             Column("is_latest", Boolean),
             Column("last_modified", DateTime(timezone=True)),
             Column("size", Int64),
-            Column("owner_name", String),
-            Column("owner_id", String),
             Column("location", JSON),
             Column("source", String),
         ]
@@ -2187,8 +2183,6 @@ def find(
                 field_set.add("path")
             elif column == "name":
                 field_set.add("path")
-            elif column == "owner":
-                field_set.add("owner_name")
             elif column == "path":
                 field_set.add("dir_type")
                 field_set.add("path")

src/datachain/cli.py

@@ -23,7 +23,7 @@
 
 TTL_HUMAN = "4h"
 TTL_INT = 4 * 60 * 60
-FIND_COLUMNS = ["du", "name", "owner", "path", "size", "type"]
+FIND_COLUMNS = ["du", "name", "path", "size", "type"]
 
 
 def human_time_type(value_str: str, can_be_none: bool = False) -> Optional[int]:
@@ -578,9 +578,8 @@ def _node_data_to_ls_values(row, long_format=False):
     value = name + ending
     if long_format:
         last_modified = row[2]
-        owner_name = row[3]
         timestamp = last_modified if not is_dir else None
-        return long_line_str(value, timestamp, owner_name)
+        return long_line_str(value, timestamp)
     return value
 
 
@@ -598,15 +597,15 @@ def _ls_urls_flat(
         if client_cls.is_root_url(source):
             buckets = client_cls.ls_buckets(**catalog.client_config)
             if long:
-                values = (long_line_str(b.name, b.created, "") for b in buckets)
+                values = (long_line_str(b.name, b.created) for b in buckets)
             else:
                 values = (b.name for b in buckets)
             yield source, values
         else:
             found = False
             fields = ["name", "dir_type"]
             if long:
-                fields.extend(["last_modified", "owner_name"])
+                fields.append("last_modified")
             for data_source, results in catalog.ls([source], fields=fields, **kwargs):
                 values = (_node_data_to_ls_values(r, long) for r in results)
                 found = True
@@ -622,7 +621,7 @@ def ls_indexed_storages(catalog: "Catalog", long: bool = False) -> Iterator[str]
     if long:
         for uri in storage_uris:
             # TODO: add Storage.created so it can be used here
-            yield long_line_str(uri, None, "")
+            yield long_line_str(uri, None)
     else:
         yield from storage_uris
 
@@ -693,7 +692,6 @@ def ls_remote(
                 entry = long_line_str(
                     row["name"] + ("/" if row["dir_type"] else ""),
                     row["last_modified"],
-                    row["owner_name"],
                 )
                 print(format_ls_entry(entry))
         else:

src/datachain/client/s3.py

@@ -119,8 +119,6 @@ def _entry_from_boto(self, v, bucket, versions=False):
             is_latest=v.get("IsLatest", True),
             last_modified=v.get("LastModified", ""),
             size=v["Size"],
-            owner_name=v.get("Owner", {}).get("DisplayName", ""),
-            owner_id=v.get("Owner", {}).get("ID", ""),
         )
 
     async def _fetch_dir(
@@ -165,8 +163,6 @@ def convert_info(self, v: dict[str, Any], path: str) -> Entry:
             is_latest=v.get("IsLatest", True),
             last_modified=v.get("LastModified", ""),
             size=v["size"],
-            owner_name=v.get("Owner", {}).get("DisplayName", ""),
-            owner_id=v.get("Owner", {}).get("ID", ""),
         )
 
     def info_to_file(self, v: dict[str, Any], path: str) -> File:

src/datachain/data_storage/warehouse.py

@@ -629,8 +629,6 @@ def with_default(column):
             with_default(dr.c.is_latest),
             dr.c.last_modified,
             with_default(dr.c.size),
-            with_default(dr.c.owner_name),
-            with_default(dr.c.owner_id),
             with_default(dr.c.sys__rand),
             dr.c.location,
             de.c.source,

src/datachain/node.py

@@ -55,8 +55,6 @@ class Node:
     is_latest: bool = True
     last_modified: Optional[datetime] = None
     size: int = 0
-    owner_name: str = ""
-    owner_id: str = ""
     location: Optional[str] = None
     source: StorageURI = StorageURI("")
     dir_type: int = DirType.FILE
@@ -149,8 +147,6 @@ class Entry:
     is_latest: bool = True
     last_modified: Optional[datetime] = None
     size: int = 0
-    owner_name: str = ""
-    owner_id: str = ""
     location: Optional[str] = None
 
     @classmethod
@@ -211,9 +207,9 @@ def full_path(self) -> str:
 TIME_FMT = "%Y-%m-%d %H:%M"
 
 
-def long_line_str(name: str, timestamp: Optional[datetime], owner: str) -> str:
+def long_line_str(name: str, timestamp: Optional[datetime]) -> str:
     if timestamp is None:
         time = "-"
     else:
         time = timestamp.strftime(TIME_FMT)
-    return f"{owner: <19} {time: <19} {name}"
+    return f"{time: <19} {name}"

src/datachain/query/builtins.py

@@ -22,8 +22,6 @@ def load_tar(raw):
         C.source,
         C.path,
         C.size,
-        C.owner_name,
-        C.owner_id,
         C.is_latest,
         C.last_modified,
         C.version,
@@ -36,8 +34,6 @@ def index_tar(
     source,
     parent_path,
     size,
-    owner_name,
-    owner_id,
     is_latest,
     last_modified,
     version,
@@ -49,8 +45,6 @@ def index_tar(
         source=source,
         path=parent_path,
         size=size,
-        owner_name=owner_name,
-        owner_id=owner_id,
         is_latest=bool(is_latest),
         last_modified=last_modified,
         version=version,

src/datachain/query/schema.py

@@ -222,8 +222,6 @@ class DatasetRow:
         "path": String,
         "size": Int64,
         "location": JSON,
-        "owner_name": String,
-        "owner_id": String,
         "is_latest": Boolean,
         "last_modified": DateTime,
         "version": String,
@@ -236,8 +234,6 @@ def create(
         source: str = "",
         size: int = 0,
         location: Optional[dict[str, Any]] = None,
-        owner_name: str = "",
-        owner_id: str = "",
         is_latest: bool = True,
         last_modified: Optional[datetime] = None,
         version: str = "",
@@ -248,8 +244,6 @@ def create(
         int,
         Optional[str],
         int,
-        str,
-        str,
         bool,
         datetime,
         str,
@@ -266,8 +260,6 @@ def create(
             path,
             size,
             location,
-            owner_name,
-            owner_id,
             is_latest,
             last_modified,
             version,

src/datachain/utils.py

@@ -340,8 +340,6 @@ def show_df(
                 "etag",
                 "is_latest",
                 "last_modified",
-                "owner_id",
-                "owner_name",
                 "size",
                 "version",
             ],

tests/conftest.py

@@ -583,8 +583,6 @@ def dataset_rows():
             "is_latest": True,
             "name": f"dql_1m_meta_text_emd.parquet_3_{i}_0.snappy.parquet",
             "etag": f"72b35c8e9b8eed1636c91eb94241c2f8-{i}",
-            "owner_id": "owner",
-            "owner_name": "aws-iterative-sandbox",
             "last_modified": "2024-02-23T10:42:31.842944+00:00",
             "size": 49807360,
             "sys__rand": 12123123123,

tests/data.py

@@ -13,8 +13,6 @@
         is_latest=True,
         last_modified=datetime(2023, 2, 27, 18, 28, 54, tzinfo=utc),
         size=13,
-        owner_name="webfile",
-        owner_id="75aa57f09aa0c8caeab4f8c24e99d10f8e7faeebf76c078efc7c6caea54ba06a",
     ),
     Entry.from_file(
         path="cats/cat1",
@@ -23,8 +21,6 @@
         is_latest=True,
         last_modified=datetime(2023, 2, 27, 18, 28, 54, tzinfo=utc),
         size=4,
-        owner_name="webfile",
-        owner_id="75aa57f09aa0c8caeab4f8c24e99d10f8e7faeebf76c078efc7c6caea54ba06a",
     ),
     Entry.from_file(
         path="cats/cat2",
@@ -33,8 +29,6 @@
         is_latest=True,
         last_modified=datetime(2023, 2, 27, 18, 28, 54, tzinfo=utc),
         size=4,
-        owner_name="webfile",
-        owner_id="75aa57f09aa0c8caeab4f8c24e99d10f8e7faeebf76c078efc7c6caea54ba06a",
     ),
     Entry.from_file(
         path="dogs/dog1",
@@ -43,8 +37,6 @@
         is_latest=True,
         last_modified=datetime(2023, 2, 27, 18, 28, 54, tzinfo=utc),
         size=4,
-        owner_name="webfile",
-        owner_id="75aa57f09aa0c8caeab4f8c24e99d10f8e7faeebf76c078efc7c6caea54ba06a",
     ),
     Entry.from_file(
         path="dogs/dog2",
@@ -53,8 +45,6 @@
         is_latest=True,
         last_modified=datetime(2023, 2, 27, 18, 28, 54, tzinfo=utc),
         size=3,
-        owner_name="webfile",
-        owner_id="75aa57f09aa0c8caeab4f8c24e99d10f8e7faeebf76c078efc7c6caea54ba06a",
     ),
     Entry.from_file(
         path="dogs/dog3",
@@ -63,8 +53,6 @@
         is_latest=True,
         last_modified=datetime(2023, 2, 27, 18, 28, 54, tzinfo=utc),
         size=4,
-        owner_name="webfile",
-        owner_id="75aa57f09aa0c8caeab4f8c24e99d10f8e7faeebf76c078efc7c6caea54ba06a",
     ),
     Entry.from_file(
         path="dogs/others/dog4",
@@ -73,8 +61,6 @@
         is_latest=True,
         last_modified=datetime(2023, 2, 27, 18, 28, 54, tzinfo=utc),
         size=4,
-        owner_name="webfile",
-        owner_id="75aa57f09aa0c8caeab4f8c24e99d10f8e7faeebf76c078efc7c6caea54ba06a",
     ),
 ]
 
@@ -90,8 +76,6 @@
         is_latest=True,
         last_modified=datetime(2023, 2, 27, 18, 28, 54, tzinfo=utc),
         size=4,
-        owner_name="webfile",
-        owner_id="75aa57f09aa0c8caeab4f8c24e99d10f8e7faeebf76c078efc7c6caea54ba06a",
     ),
     Entry.from_file(
         path="dogs/others",
@@ -100,8 +84,6 @@
         is_latest=True,
         last_modified=datetime(2023, 2, 27, 18, 28, 54, tzinfo=utc),
         size=4,
-        owner_name="webfile",
-        owner_id="75aa57f09aa0c8caeab4f8c24e99d10f8e7faeebf76c078efc7c6caea54ba06a",
     ),
     Entry.from_file(
         path="dogs/",
@@ -110,7 +92,5 @@
         is_latest=True,
         last_modified=datetime(2023, 2, 27, 18, 28, 54, tzinfo=utc),
         size=4,
-        owner_name="webfile",
-        owner_id="75aa57f09aa0c8caeab4f8c24e99d10f8e7faeebf76c078efc7c6caea54ba06a",
     ),
 ]

tests/func/test_catalog.py

@@ -146,8 +146,6 @@ def test_find_names_columns(cloud_test_catalog, cloud_type):
     src_uri = cloud_test_catalog.src_uri
     catalog = cloud_test_catalog.catalog
 
-    owner = "webfile" if cloud_type == "s3" else ""
-
     src_uri_path = src_uri
     if cloud_type == "file":
         src_uri_path = LocalFileSystem._strip_protocol(src_uri)
@@ -156,14 +154,14 @@ def test_find_names_columns(cloud_test_catalog, cloud_type):
         catalog.find(
             [src_uri],
             names=["*cat*"],
-            columns=["du", "name", "owner", "path", "size", "type"],
+            columns=["du", "name", "path", "size", "type"],
         )
     ) == {
         "\t".join(columns)
         for columns in [
-            ["8", "cats", "", f"{src_uri_path}/cats/", "0", "d"],
-            ["4", "cat1", owner, f"{src_uri_path}/cats/cat1", "4", "f"],
-            ["4", "cat2", owner, f"{src_uri_path}/cats/cat2", "4", "f"],
+            ["8", "cats", f"{src_uri_path}/cats/", "0", "d"],
+            ["4", "cat1", f"{src_uri_path}/cats/cat1", "4", "f"],
+            ["4", "cat2", f"{src_uri_path}/cats/cat2", "4", "f"],
         ]
     }
 

tests/func/test_dataset_query.py

@@ -506,7 +506,7 @@ def test_mutate(cloud_test_catalog, save):
     else:
         result = q.db_results(row_factory=lambda c, v: dict(zip(c, v)))
     assert len(result) == 4
-    assert len(result[0]) == 17
+    assert len(result[0]) == 15
     cols = {"size10x", "size1000x", "s2", "s3", "s4"}
     new_data = [[v for k, v in r.items() if k in cols] for r in result]
     assert new_data == [