datachain 0.18.7__tar.gz → 0.18.9__tar.gz

{datachain-0.18.7 → datachain-0.18.9}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.11.11'
+    rev: 'v0.11.12'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.18.7/src/datachain.egg-info → datachain-0.18.9}/PKG-INFO

@@ -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 → datachain-0.18.9}/pyproject.toml

@@ -108,7 +108,7 @@ tests = [
 ]
 dev = [
   "datachain[docs,tests]",
-  "mypy==1.15.0",
+  "mypy==1.16.0",
   "types-python-dateutil",
   "types-pytz",
   "types-PyYAML",

{datachain-0.18.7 → datachain-0.18.9}/src/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-0.18.7 → datachain-0.18.9}/src/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-0.18.7 → datachain-0.18.9}/src/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-0.18.7 → datachain-0.18.9}/src/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-0.18.7 → datachain-0.18.9}/src/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 → datachain-0.18.9/src/datachain.egg-info}/PKG-INFO

@@ -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 → datachain-0.18.9}/src/datachain.egg-info/requires.txt

@@ -37,7 +37,7 @@ tomli
 
 [dev]
 datachain[docs,tests]
-mypy==1.15.0
+mypy==1.16.0
 types-python-dateutil
 types-pytz
 types-PyYAML