datachain 0.18.7__py3-none-any.whl → 0.18.9__py3-none-any.whl

datachain/lib/file.py

@@ -81,14 +81,28 @@ class FileExporter(NodesThreadPool):
 
 
 class VFileError(DataChainError):
-    def __init__(self, file: "File", message: str, vtype: str = ""):
+    def __init__(self, message: str, source: str, path: str, vtype: str = ""):
+        self.message = message
+        self.source = source
+        self.path = path
+        self.vtype = vtype
+
         type_ = f" of vtype '{vtype}'" if vtype else ""
-        super().__init__(f"Error in v-file '{file.path}'{type_}: {message}")
+        super().__init__(f"Error in v-file '{source}/{path}'{type_}: {message}")
+
+    def __reduce__(self):
+        return self.__class__, (self.message, self.source, self.path, self.vtype)
 
 
 class FileError(DataChainError):
-    def __init__(self, file: "File", message: str):
-        super().__init__(f"Error in file {file.get_uri()}: {message}")
+    def __init__(self, message: str, source: str, path: str):
+        self.message = message
+        self.source = source
+        self.path = path
+        super().__init__(f"Error in file '{source}/{path}': {message}")
+
+    def __reduce__(self):
+        return self.__class__, (self.message, self.source, self.path)
 
 
 class VFile(ABC):
@@ -114,18 +128,20 @@ class TarVFile(VFile):
     def open(cls, file: "File", location: list[dict]):
         """Stream file from tar archive based on location in archive."""
         if len(location) > 1:
-            raise VFileError(file, "multiple 'location's are not supported yet")
+            raise VFileError(
+                "multiple 'location's are not supported yet", file.source, file.path
+            )
 
         loc = location[0]
 
         if (offset := loc.get("offset", None)) is None:
-            raise VFileError(file, "'offset' is not specified")
+            raise VFileError("'offset' is not specified", file.source, file.path)
 
         if (size := loc.get("size", None)) is None:
-            raise VFileError(file, "'size' is not specified")
+            raise VFileError("'size' is not specified", file.source, file.path)
 
         if (parent := loc.get("parent", None)) is None:
-            raise VFileError(file, "'parent' is not specified")
+            raise VFileError("'parent' is not specified", file.source, file.path)
 
         tar_file = File(**parent)
         tar_file._set_stream(file._catalog)
@@ -145,14 +161,18 @@ class VFileRegistry:
     @classmethod
     def resolve(cls, file: "File", location: list[dict]):
         if len(location) == 0:
-            raise VFileError(file, "'location' must not be list of JSONs")
+            raise VFileError(
+                "'location' must not be list of JSONs", file.source, file.path
+            )
 
         if not (vtype := location[0].get("vtype", "")):
-            raise VFileError(file, "vtype is not specified")
+            raise VFileError("vtype is not specified", file.source, file.path)
 
         reader = cls._vtype_readers.get(vtype, None)
         if not reader:
-            raise VFileError(file, "reader not registered", vtype)
+            raise VFileError(
+                "reader not registered", file.source, file.path, vtype=vtype
+            )
 
         return reader.open(file, location)
 

datachain/lib/image.py

@@ -19,7 +19,7 @@ def image_info(file: Union[File, ImageFile]) -> Image:
     try:
         img = file.as_image_file().read()
     except Exception as exc:
-        raise FileError(file, "unable to open image file") from exc
+        raise FileError("unable to open image file", file.source, file.path) from exc
 
     return Image(
         width=img.width,

datachain/lib/utils.py

@@ -18,13 +18,11 @@ class AbstractUDF(ABC):
 
 
 class DataChainError(Exception):
-    def __init__(self, message):
-        super().__init__(message)
+    pass
 
 
 class DataChainParamsError(DataChainError):
-    def __init__(self, message):
-        super().__init__(message)
+    pass
 
 
 class DataChainColumnError(DataChainParamsError):

datachain/lib/video.py

@@ -34,21 +34,27 @@ def video_info(file: Union[File, VideoFile]) -> Video:
         file.ensure_cached()
         file_path = file.get_local_path()
         if not file_path:
-            raise FileError(file, "unable to download video file")
+            raise FileError("unable to download video file", file.source, file.path)
 
     try:
         probe = ffmpeg.probe(file_path)
     except Exception as exc:
-        raise FileError(file, "unable to extract metadata from video file") from exc
+        raise FileError(
+            "unable to extract metadata from video file", file.source, file.path
+        ) from exc
 
     all_streams = probe.get("streams")
     video_format = probe.get("format")
     if not all_streams or not video_format:
-        raise FileError(file, "unable to extract metadata from video file")
+        raise FileError(
+            "unable to extract metadata from video file", file.source, file.path
+        )
 
     video_streams = [s for s in all_streams if s["codec_type"] == "video"]
     if len(video_streams) == 0:
-        raise FileError(file, "unable to extract metadata from video file")
+        raise FileError(
+            "unable to extract metadata from video file", file.source, file.path
+        )
 
     video_stream = video_streams[0]
 

datachain/query/dataset.py

@@ -1348,7 +1348,7 @@ class DatasetQuery:
 
             async def get_params(row: Sequence) -> tuple:
                 row_dict = RowDict(zip(query_fields, row))
-                return tuple(
+                return tuple(  # noqa: C409
                     [
                         await p.get_value_async(
                             self.catalog, row_dict, mapper, **kwargs

{datachain-0.18.7.dist-info → datachain-0.18.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.18.7
+Version: 0.18.9
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0
@@ -94,7 +94,7 @@ Requires-Dist: scipy; extra == "tests"
 Requires-Dist: ultralytics; extra == "tests"
 Provides-Extra: dev
 Requires-Dist: datachain[docs,tests]; extra == "dev"
-Requires-Dist: mypy==1.15.0; extra == "dev"
+Requires-Dist: mypy==1.16.0; extra == "dev"
 Requires-Dist: types-python-dateutil; extra == "dev"
 Requires-Dist: types-pytz; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"

{datachain-0.18.7.dist-info → datachain-0.18.9.dist-info}/RECORD

@@ -72,9 +72,9 @@ datachain/lib/arrow.py,sha256=mFO_6wRqzpEzBhXf7Xn1aeLUvaiHcC6XQ-8as9sbcgY,10253
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=ZwBXELtqROEdLL4DmxTipnwUZmhQvMz_UVDzyf7nQ9Y,2899
 datachain/lib/dataset_info.py,sha256=d-jz6zeDU5DEgYtyeSF5nK0MU-40FV5km_iOCh4pXzo,3179
-datachain/lib/file.py,sha256=0oFm1MWU7AatXplxRj-6Xbjjb6A_AvM_awwk9mYb0hc,30466
+datachain/lib/file.py,sha256=mzc7_fpHAkVhs4z3jBUhFQzPEbODdXJpzjVfby2IkC4,31117
 datachain/lib/hf.py,sha256=gjxuStZBlKtNk3-4yYSlWZDv9zBGblOdvEy_Lwap5hA,5882
-datachain/lib/image.py,sha256=butvUY_33PVEYPKX2nVCPeJjJVcBaptZwsE9REQsTS8,3247
+datachain/lib/image.py,sha256=erWvZW5M3emnbl6_fGAOPyKm-1EKbt3vOdWPfe3Oo7U,3265
 datachain/lib/listing.py,sha256=5_GoATtIwCtd1JMqlorPB_vQDxndOQZpiWjNOG3NMw4,7007
 datachain/lib/listing_info.py,sha256=9ua40Hw0aiQByUw3oAEeNzMavJYfW0Uhe8YdCTK-m_g,1110
 datachain/lib/meta_formats.py,sha256=Epydbdch1g4CojK8wd_ePzmwmljC4fVWlJtZ16jsX-A,6349
@@ -86,8 +86,8 @@ datachain/lib/tar.py,sha256=3WIzao6yD5fbLqXLTt9GhPGNonbFIs_fDRu-9vgLgsA,1038
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
 datachain/lib/udf.py,sha256=FWqA476ygdk4MU-0qehYKxvnt8Tekh21Cyf3RgddD1k,16674
 datachain/lib/udf_signature.py,sha256=2EtsOPDNSPqcOlYwqbCdy6RF5MldI-7smii8aLy8p7Y,7543
-datachain/lib/utils.py,sha256=QrjVs_oLRXEotOPUYurBJypBFi_ReTJmxcnJeH4j2Uk,1596
-datachain/lib/video.py,sha256=suH_8Mi8VYk4-IVb1vjSduF_njs64ji1WGKHxDLnGYw,6629
+datachain/lib/utils.py,sha256=rG2y7NwTqZOuomZZRmrA-Q-ANM_j1cToQYqDJoOeGyU,1480
+datachain/lib/video.py,sha256=u6fLJWj5G6QqsVkpfHnKGklBNpG3BRRg6v3izngnNcU,6767
 datachain/lib/webdataset.py,sha256=o7SHk5HOUWsZ5Ln04xOM04eQqiBHiJNO7xLgyVBrwo8,6924
 datachain/lib/webdataset_laion.py,sha256=xvT6m_r5y0KbOx14BUe7UC5mOgrktJq53Mh-H0EVlUE,2525
 datachain/lib/convert/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -121,7 +121,7 @@ datachain/model/ultralytics/pose.py,sha256=pBlmt63Qe68FKmexHimUGlNbNOoOlMHXG4fzX
 datachain/model/ultralytics/segment.py,sha256=63bDCj43E6iZ0hFI5J6uQfksdCmjEp6sEm1XzVaE8pw,2986
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=-goxLpE0EUvaDHu66rstj53UnfHpYfBUGux8GSpJ93k,4306
-datachain/query/dataset.py,sha256=3c3MAiIl7ZnCii_0dZA-Om73ornNMSKkna32JX3H05E,60587
+datachain/query/dataset.py,sha256=dI51zOU1Drev65f6SPn4mvRdwRXs4SOW5STMm3WYd7A,60601
 datachain/query/dispatch.py,sha256=A0nPxn6mEN5d9dDo6S8m16Ji_9IvJLXrgF2kqXdi4fs,15546
 datachain/query/metrics.py,sha256=DOK5HdNVaRugYPjl8qnBONvTkwjMloLqAr7Mi3TjCO0,858
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
@@ -153,9 +153,9 @@ 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-0.18.7.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.18.7.dist-info/METADATA,sha256=OXGuP0EbV6ZC57NPhtyse2-6OP2pDKbhJkmcDfHp1mU,11319
-datachain-0.18.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datachain-0.18.7.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.18.7.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.18.7.dist-info/RECORD,,
+datachain-0.18.9.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.18.9.dist-info/METADATA,sha256=0BhJEeQiYf41Rg7DLgJ-WtiUu9cpwwUtVwo__lPaMAw,11319
+datachain-0.18.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datachain-0.18.9.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.18.9.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.18.9.dist-info/RECORD,,