datachain 0.7.3__py3-none-any.whl → 0.7.4__py3-none-any.whl

datachain/data_storage/metastore.py

@@ -685,13 +685,6 @@ class AbstractDBMetastore(AbstractMetastore):
             return None
         return reduce(lambda ds, version: ds.merge_versions(version), versions)
 
-    def _parse_datasets(self, rows) -> Iterator["DatasetRecord"]:
-        # grouping rows by dataset id
-        for _, g in groupby(rows, lambda r: r[0]):
-            dataset = self._parse_dataset(list(g))
-            if dataset:
-                yield dataset
-
     def _parse_list_dataset(self, rows) -> Optional[DatasetListRecord]:
         versions = [self.dataset_list_class.parse(*r) for r in rows]
         if not versions:

datachain/dataset.py

@@ -2,6 +2,7 @@ import builtins
 import json
 from dataclasses import dataclass, fields
 from datetime import datetime
+from functools import cached_property
 from typing import (
     Any,
     NewType,
@@ -11,6 +12,8 @@ from typing import (
 )
 from urllib.parse import urlparse
 
+import orjson
+
 from datachain.error import DatasetVersionNotFoundError
 from datachain.sql.types import NAME_TYPES_MAPPING, SQLType
 
@@ -178,7 +181,7 @@ class DatasetVersion:
     schema: dict[str, Union[SQLType, type[SQLType]]]
     num_objects: Optional[int]
     size: Optional[int]
-    preview: Optional[list[dict]]
+    _preview_data: Optional[Union[str, list[dict]]]
     sources: str = ""
     query_script: str = ""
     job_id: Optional[str] = None
@@ -199,7 +202,7 @@ class DatasetVersion:
         script_output: str,
         num_objects: Optional[int],
         size: Optional[int],
-        preview: Optional[str],
+        preview: Optional[Union[str, list[dict]]],
         schema: dict[str, Union[SQLType, type[SQLType]]],
         sources: str = "",
         query_script: str = "",
@@ -220,7 +223,7 @@ class DatasetVersion:
             schema,
             num_objects,
             size,
-            json.loads(preview) if preview else None,
+            preview,
             sources,
             query_script,
             job_id,
@@ -260,9 +263,17 @@ class DatasetVersion:
             for c_name, c_type in self.schema.items()
         }
 
+    @cached_property
+    def preview(self) -> Optional[list[dict]]:
+        if isinstance(self._preview_data, str):
+            return orjson.loads(self._preview_data)
+        return self._preview_data if self._preview_data else None
+
     @classmethod
     def from_dict(cls, d: dict[str, Any]) -> "DatasetVersion":
         kwargs = {f.name: d[f.name] for f in fields(cls) if f.name in d}
+        if not hasattr(kwargs, "_preview_data"):
+            kwargs["_preview_data"] = d.get("preview")
         return cls(**kwargs)
 
 

{datachain-0.7.3.dist-info → datachain-0.7.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.7.3
+Version: 0.7.4
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0

{datachain-0.7.3.dist-info → datachain-0.7.4.dist-info}/RECORD

@@ -5,7 +5,7 @@ datachain/cache.py,sha256=s0YHN7qurmQv-eC265TjeureK84TebWWAnL07cxchZQ,2997
 datachain/cli.py,sha256=1hiBClE1kbRyx0DK3uX5KMVa0ktbsG6TsFSNvoT2xxs,39399
 datachain/cli_utils.py,sha256=jrn9ejGXjybeO1ur3fjdSiAyCHZrX0qsLLbJzN9ErPM,2418
 datachain/config.py,sha256=g8qbNV0vW2VEKpX-dGZ9pAn0DAz6G2ZFcr7SAV3PoSM,4272
-datachain/dataset.py,sha256=-9uPdOn1uWkGucouhsFVGRIuFdWkCdUrhV0U9f6Ihgc,18218
+datachain/dataset.py,sha256=PKHaEXeYOL2gE5BaEmc9rzPJdDg5O9X8_7FvSh_Q9Vg,18614
 datachain/error.py,sha256=bxAAL32lSeMgzsQDEHbGTGORj-mPzzpCRvWDPueJNN4,1092
 datachain/job.py,sha256=Jt4sNutMHJReaGsj3r3scueN5aESLGfhimAa8pUP7Is,1271
 datachain/listing.py,sha256=TgKg25ZWAP5enzKgw2_2GUPJVdnQUh6uySHB5SJrUY4,7773
@@ -33,7 +33,7 @@ datachain/data_storage/__init__.py,sha256=cEOJpyu1JDZtfUupYucCDNFI6e5Wmp_Oyzq6rZ
 datachain/data_storage/db_engine.py,sha256=81Ol1of9TTTzD97ORajCnP366Xz2mEJt6C-kTUCaru4,3406
 datachain/data_storage/id_generator.py,sha256=lCEoU0BM37Ai2aRpSbwo5oQT0GqZnSpYwwvizathRMQ,4292
 datachain/data_storage/job.py,sha256=w-7spowjkOa1P5fUVtJou3OltT0L48P0RYWZ9rSJ9-s,383
-datachain/data_storage/metastore.py,sha256=S9pkbAi7yJlU_CTuhB-eTZgzZgkPMhJ5Br90AVLDXsQ,37922
+datachain/data_storage/metastore.py,sha256=VPq-Dl8P-RbZQMzn6vB9aXBPKUWPTwP8ypkaVfE-7PU,37661
 datachain/data_storage/schema.py,sha256=-QVlRvD0dfu-ZFUxylEoSnLJLnleMEjVlcAb2OGu-AY,9895
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
 datachain/data_storage/sqlite.py,sha256=nF-2B-n8YZh9cJlZv4XnbahAJDW6pvrp1h9L-140M7A,27538
@@ -117,9 +117,9 @@ datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
 datachain/toolkit/split.py,sha256=ZgDcrNiKiPXZmKD591_1z9qRIXitu5zwAsoVPB7ykiU,2508
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.7.3.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.7.3.dist-info/METADATA,sha256=E1-nP4rZghwCV5kSS09620YEJdwaTAiVpI5DmmRnZy0,18006
-datachain-0.7.3.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-datachain-0.7.3.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.7.3.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.7.3.dist-info/RECORD,,
+datachain-0.7.4.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.7.4.dist-info/METADATA,sha256=tr5ReyIE9nUfhvCwuGujJC1MmfO07A10N1sLfvOBcYQ,18006
+datachain-0.7.4.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+datachain-0.7.4.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.7.4.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.7.4.dist-info/RECORD,,