datachain 0.3.16__tar.gz → 0.3.17__tar.gz

{datachain-0.3.16 → datachain-0.3.17}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.6.4'
+    rev: 'v0.6.5'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.3.16/src/datachain.egg-info → datachain-0.3.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.3.16
+Version: 0.3.17
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/catalog/catalog.py

@@ -68,8 +68,6 @@ from datachain.utils import (
     DataChainDir,
     batched,
     datachain_paths_join,
-    import_object,
-    parse_params_string,
 )
 
 from .datasource import DataSource
@@ -843,7 +841,7 @@ class Catalog:
         from datachain.query import DatasetQuery
 
         def _row_to_node(d: dict[str, Any]) -> Node:
-            del d["source"]
+            del d["file__source"]
             return Node.from_dict(d)
 
         enlisted_sources: list[tuple[bool, bool, Any]] = []
@@ -1148,30 +1146,28 @@ class Catalog:
         if not sources:
             raise ValueError("Sources needs to be non empty list")
 
-        from datachain.query import DatasetQuery
+        from datachain.lib.dc import DataChain
+        from datachain.query.session import Session
+
+        session = Session.get(catalog=self, client_config=client_config)
 
-        dataset_queries = []
+        chains = []
         for source in sources:
             if source.startswith(DATASET_PREFIX):
-                dq = DatasetQuery(
-                    name=source[len(DATASET_PREFIX) :],
-                    catalog=self,
-                    client_config=client_config,
+                dc = DataChain.from_dataset(
+                    source[len(DATASET_PREFIX) :], session=session
                 )
             else:
-                dq = DatasetQuery(
-                    path=source,
-                    catalog=self,
-                    client_config=client_config,
-                    recursive=recursive,
+                dc = DataChain.from_storage(
+                    source, session=session, recursive=recursive
                 )
 
-            dataset_queries.append(dq)
+            chains.append(dc)
 
         # create union of all dataset queries created from sources
-        dq = reduce(lambda ds1, ds2: ds1.union(ds2), dataset_queries)
+        dc = reduce(lambda dc1, dc2: dc1.union(dc2), chains)
         try:
-            dq.save(name)
+            dc.save(name)
         except Exception as e:  # noqa: BLE001
             try:
                 ds = self.get_dataset(name)
@@ -1731,26 +1727,6 @@ class Catalog:
             output, sources, client_config=client_config, recursive=recursive
         )
 
-    def apply_udf(
-        self,
-        udf_location: str,
-        source: str,
-        target_name: str,
-        parallel: Optional[int] = None,
-        params: Optional[str] = None,
-    ):
-        from datachain.query import DatasetQuery
-
-        if source.startswith(DATASET_PREFIX):
-            ds = DatasetQuery(name=source[len(DATASET_PREFIX) :], catalog=self)
-        else:
-            ds = DatasetQuery(path=source, catalog=self)
-        udf = import_object(udf_location)
-        if params:
-            args, kwargs = parse_params_string(params)
-            udf = udf(*args, **kwargs)
-        ds.add_signals(udf, parallel=parallel).save(target_name)
-
     def query(
         self,
         query_script: str,

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/cli.py

@@ -494,27 +494,6 @@ def get_parser() -> ArgumentParser:  # noqa: PLR0915
         help="Query parameters",
     )
 
-    apply_udf_parser = subp.add_parser(
-        "apply-udf", parents=[parent_parser], description="Apply UDF"
-    )
-    apply_udf_parser.add_argument("udf", type=str, help="UDF location")
-    apply_udf_parser.add_argument("source", type=str, help="Source storage or dataset")
-    apply_udf_parser.add_argument("target", type=str, help="Target dataset name")
-    apply_udf_parser.add_argument(
-        "--parallel",
-        nargs="?",
-        type=int,
-        const=-1,
-        default=None,
-        metavar="N",
-        help=(
-            "Use multiprocessing to run the UDF with N worker processes. "
-            "N defaults to the CPU count."
-        ),
-    )
-    apply_udf_parser.add_argument(
-        "--udf-params", type=str, default=None, help="UDF class parameters"
-    )
     subp.add_parser(
         "clear-cache", parents=[parent_parser], description="Clear the local file cache"
     )
@@ -1016,10 +995,6 @@ def main(argv: Optional[list[str]] = None) -> int:  # noqa: C901, PLR0912, PLR09
                 parallel=args.parallel,
                 params=args.param,
             )
-        elif args.command == "apply-udf":
-            catalog.apply_udf(
-                args.udf, args.source, args.target, args.parallel, args.udf_params
-            )
         elif args.command == "clear-cache":
             clear_cache(catalog)
         elif args.command == "gc":

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/data_storage/metastore.py

@@ -297,39 +297,6 @@ class AbstractMetastore(ABC, Serializable):
     #
     # Dataset dependencies
     #
-
-    def add_dependency(
-        self,
-        dependency: DatasetDependency,
-        source_dataset_name: str,
-        source_dataset_version: int,
-    ) -> None:
-        """Add dependency to dataset or storage."""
-        if dependency.is_dataset:
-            self.add_dataset_dependency(
-                source_dataset_name,
-                source_dataset_version,
-                dependency.dataset_name,
-                int(dependency.version),
-            )
-        else:
-            self.add_storage_dependency(
-                source_dataset_name,
-                source_dataset_version,
-                StorageURI(dependency.name),
-                dependency.version,
-            )
-
-    @abstractmethod
-    def add_storage_dependency(
-        self,
-        source_dataset_name: str,
-        source_dataset_version: int,
-        storage_uri: StorageURI,
-        storage_timestamp_str: Optional[str] = None,
-    ) -> None:
-        """Adds storage dependency to dataset."""
-
     @abstractmethod
     def add_dataset_dependency(
         self,
@@ -1268,32 +1235,6 @@ class AbstractDBMetastore(AbstractMetastore):
     #
     # Dataset dependencies
     #
-
-    def _insert_dataset_dependency(self, data: dict[str, Any]) -> None:
-        """Method for inserting dependencies."""
-        self.db.execute(self._datasets_dependencies_insert().values(**data))
-
-    def add_storage_dependency(
-        self,
-        source_dataset_name: str,
-        source_dataset_version: int,
-        storage_uri: StorageURI,
-        storage_timestamp_str: Optional[str] = None,
-    ) -> None:
-        source_dataset = self.get_dataset(source_dataset_name)
-        storage = self.get_storage(storage_uri)
-
-        self._insert_dataset_dependency(
-            {
-                "source_dataset_id": source_dataset.id,
-                "source_dataset_version_id": (
-                    source_dataset.get_version(source_dataset_version).id
-                ),
-                "bucket_id": storage.id,
-                "bucket_version": storage_timestamp_str,
-            }
-        )
-
     def add_dataset_dependency(
         self,
         source_dataset_name: str,
@@ -1305,15 +1246,15 @@ class AbstractDBMetastore(AbstractMetastore):
         source_dataset = self.get_dataset(source_dataset_name)
         dataset = self.get_dataset(dataset_name)
 
-        self._insert_dataset_dependency(
-            {
-                "source_dataset_id": source_dataset.id,
-                "source_dataset_version_id": (
+        self.db.execute(
+            self._datasets_dependencies_insert().values(
+                source_dataset_id=source_dataset.id,
+                source_dataset_version_id=(
                     source_dataset.get_version(source_dataset_version).id
                 ),
-                "dataset_id": dataset.id,
-                "dataset_version_id": dataset.get_version(dataset_version).id,
-            }
+                dataset_id=dataset.id,
+                dataset_version_id=dataset.get_version(dataset_version).id,
+            )
         )
 
     def update_dataset_dependency_source(

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/data_storage/sqlite.py

@@ -651,11 +651,14 @@ class SQLiteWarehouse(AbstractWarehouse):
         self, dataset: DatasetRecord, version: int
     ) -> list[StorageURI]:
         dr = self.dataset_rows(dataset, version)
-        query = dr.select(dr.c.source).distinct()
+        query = dr.select(dr.c.file__source).distinct()
         cur = self.db.cursor()
         cur.row_factory = sqlite3.Row  # type: ignore[assignment]
 
-        return [StorageURI(row["source"]) for row in self.db.execute(query, cursor=cur)]
+        return [
+            StorageURI(row["file__source"])
+            for row in self.db.execute(query, cursor=cur)
+        ]
 
     def merge_dataset_rows(
         self,

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/data_storage/warehouse.py

@@ -942,28 +942,6 @@ class AbstractWarehouse(ABC, Serializable):
                 self.db.drop_table(Table(name, self.db.metadata), if_exists=True)
                 pbar.update(1)
 
-    def changed_query(
-        self,
-        source_query: sa.sql.selectable.Select,
-        target_query: sa.sql.selectable.Select,
-    ) -> sa.sql.selectable.Select:
-        sq = source_query.alias("source_query")
-        tq = target_query.alias("target_query")
-
-        source_target_join = sa.join(
-            sq, tq, (sq.c.source == tq.c.source) & (sq.c.path == tq.c.path)
-        )
-
-        return (
-            select(*sq.c)
-            .select_from(source_target_join)
-            .where(
-                (sq.c.last_modified > tq.c.last_modified)
-                & (sq.c.is_latest == true())
-                & (tq.c.is_latest == true())
-            )
-        )
-
 
 def _random_string(length: int) -> str:
     return "".join(

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/lib/dc.py

@@ -1337,8 +1337,7 @@ class DataChain(DatasetQuery):
                     other.signals_schema.resolve(*right_on).db_signals(),
                 )  # type: ignore[arg-type]
             )
-
-        return super()._subtract(other, signals)  # type: ignore[arg-type]
+        return super().subtract(other, signals)  # type: ignore[arg-type]
 
     @classmethod
     def from_values(

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/lib/listing.py

@@ -77,6 +77,7 @@ def parse_listing_uri(uri: str, cache, client_config) -> tuple[str, str, str]:
     """
     Parsing uri and returns listing dataset name, listing uri and listing path
     """
+    client_config = client_config or {}
     client = Client.get_client(uri, cache, **client_config)
     storage_uri, path = Client.parse_url(uri)
 

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/lib/tar.py

@@ -30,4 +30,5 @@ def process_tar(file: File) -> Iterator[File]:
     with file.open() as fd:
         with tarfile.open(fileobj=fd) as tar:
             for entry in tar.getmembers():
-                yield build_tar_member(file, entry)
+                if entry.isfile():
+                    yield build_tar_member(file, entry)

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/node.py

@@ -114,9 +114,23 @@ class Node:
         )
 
     @classmethod
-    def from_dict(cls, d: dict[str, Any]) -> "Self":
-        kw = {f.name: d[f.name] for f in attrs.fields(cls) if f.name in d}
-        return cls(**kw)
+    def from_dict(cls, d: dict[str, Any], file_prefix: str = "file") -> "Self":
+        def _dval(field_name: str):
+            return d.get(f"{file_prefix}__{field_name}")
+
+        return cls(
+            sys__id=d["sys__id"],
+            sys__rand=d["sys__rand"],
+            source=_dval("source"),
+            path=_dval("path"),
+            etag=_dval("etag"),
+            is_latest=_dval("is_latest"),
+            size=_dval("size"),
+            last_modified=_dval("last_modified"),
+            version=_dval("version"),
+            location=_dval("location"),
+            dir_type=DirType.FILE,
+        )
 
     @classmethod
     def from_dir(cls, path, **kwargs) -> "Node":

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/query/__init__.py

@@ -2,7 +2,6 @@ from .dataset import DatasetQuery
 from .params import param
 from .schema import C, DatasetRow, LocalFilename, Object, Stream
 from .session import Session
-from .udf import udf
 
 __all__ = [
     "C",
@@ -13,5 +12,4 @@ __all__ = [
     "Session",
     "Stream",
     "param",
-    "udf",
 ]

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/query/dataset.py

@@ -3,7 +3,6 @@ import inspect
 import logging
 import os
 import random
-import re
 import string
 import subprocess
 import sys
@@ -36,7 +35,6 @@ from sqlalchemy.sql.selectable import Select
 
 from datachain.asyn import ASYNC_WORKERS, AsyncMapper, OrderedMapper
 from datachain.catalog import QUERY_SCRIPT_CANCELED_EXIT_CODE, get_catalog
-from datachain.client import Client
 from datachain.data_storage.schema import (
     PARTITION_COLUMN_ID,
     partition_col_names,
@@ -46,7 +44,6 @@ from datachain.dataset import DatasetStatus, RowDict
 from datachain.error import DatasetNotFoundError, QueryScriptCancelError
 from datachain.progress import CombinedDownloadCallback
 from datachain.sql.functions import rand
-from datachain.storage import Storage, StorageURI
 from datachain.utils import (
     batched,
     determine_processes,
@@ -77,9 +74,7 @@ INSERT_BATCH_SIZE = 10000
 
 PartitionByType = Union[ColumnElement, Sequence[ColumnElement]]
 JoinPredicateType = Union[str, ColumnClause, ColumnElement]
-# dependency can be either dataset_name + dataset_version tuple or just storage uri
-# depending what type of dependency we are adding
-DatasetDependencyType = Union[tuple[str, int], StorageURI]
+DatasetDependencyType = tuple[str, int]
 
 logger = logging.getLogger("datachain")
 
@@ -185,38 +180,6 @@ class QueryStep(StartingStep):
         )
 
 
-@frozen
-class IndexingStep(StartingStep):
-    path: str
-    catalog: "Catalog"
-    kwargs: dict[str, Any]
-    recursive: Optional[bool] = True
-
-    def apply(self):
-        self.catalog.index([self.path], **self.kwargs)
-        uri, path = Client.parse_url(self.path)
-        _partial_id, partial_path = self.catalog.metastore.get_valid_partial_id(
-            uri, path
-        )
-        dataset = self.catalog.get_dataset(Storage.dataset_name(uri, partial_path))
-        dataset_rows = self.catalog.warehouse.dataset_rows(
-            dataset, dataset.latest_version
-        )
-
-        def q(*columns):
-            col_names = [c.name for c in columns]
-            return self.catalog.warehouse.nodes_dataset_query(
-                dataset_rows,
-                column_names=col_names,
-                path=path,
-                recursive=self.recursive,
-            )
-
-        storage = self.catalog.metastore.get_storage(uri)
-
-        return step_result(q, dataset_rows.c, dependencies=[storage.uri])
-
-
 def generator_then_call(generator, func: Callable):
     """
     Yield items from generator then execute a function and yield
@@ -230,7 +193,7 @@ def generator_then_call(generator, func: Callable):
 class DatasetDiffOperation(Step):
     """
     Abstract class for operations that are calculation some kind of diff between
-    datasets queries like subtract, changed etc.
+    datasets queries like subtract etc.
     """
 
     dq: "DatasetQuery"
@@ -304,28 +267,6 @@ class Subtract(DatasetDiffOperation):
         return sq.select().except_(sq.select().where(where_clause))
 
 
-@frozen
-class Changed(DatasetDiffOperation):
-    """
-    Calculates rows that are changed in a source query compared to target query
-    Changed means it has same source + path but different last_modified
-    Example:
-        >>> ds = DatasetQuery(name="dogs_cats") # some older dataset with embeddings
-        >>> ds_updated = (
-                DatasetQuery("gs://dvcx-datalakes/dogs-and-cats")
-                .filter(C.size > 1000) # we can also filter out source query
-                .changed(ds)
-                .add_signals(calc_embeddings) # calculae embeddings only on changed rows
-                .union(ds) # union with old dataset that's missing updated rows
-                .save("dogs_cats_updated")
-            )
-
-    """
-
-    def query(self, source_query: Select, target_query: Select) -> Select:
-        return self.catalog.warehouse.changed_query(source_query, target_query)
-
-
 def adjust_outputs(
     warehouse: "AbstractWarehouse", row: dict[str, Any], udf_col_types: list[tuple]
 ) -> dict[str, Any]:
@@ -1096,28 +1037,14 @@ class ResultIter:
 class DatasetQuery:
     def __init__(
         self,
-        path: str = "",
-        name: str = "",
+        name: str,
         version: Optional[int] = None,
         catalog: Optional["Catalog"] = None,
-        client_config=None,
-        recursive: Optional[bool] = True,
         session: Optional[Session] = None,
-        anon: bool = False,
-        indexing_feature_schema: Optional[dict] = None,
         indexing_column_types: Optional[dict[str, Any]] = None,
-        update: Optional[bool] = False,
         in_memory: bool = False,
     ):
-        if client_config is None:
-            client_config = {}
-
-        if anon:
-            client_config["anon"] = True
-
-        self.session = Session.get(
-            session, catalog=catalog, client_config=client_config, in_memory=in_memory
-        )
+        self.session = Session.get(session, catalog=catalog, in_memory=in_memory)
         self.catalog = catalog or self.session.catalog
         self.steps: list[Step] = []
         self._chunk_index: Optional[int] = None
@@ -1131,26 +1058,14 @@ class DatasetQuery:
         self.feature_schema: Optional[dict] = None
         self.column_types: Optional[dict[str, Any]] = None
 
-        if path:
-            kwargs = {"update": True} if update else {}
-            self.starting_step = IndexingStep(path, self.catalog, kwargs, recursive)
-            self.feature_schema = indexing_feature_schema
-            self.column_types = indexing_column_types
-        elif name:
-            self.name = name
-            ds = self.catalog.get_dataset(name)
-            self.version = version or ds.latest_version
-            self.feature_schema = ds.get_version(self.version).feature_schema
-            self.column_types = copy(ds.schema)
-            if "sys__id" in self.column_types:
-                self.column_types.pop("sys__id")
-            self.starting_step = QueryStep(self.catalog, name, self.version)
-        else:
-            raise ValueError("must provide path or name")
-
-    @staticmethod
-    def is_storage_path(path):
-        return bool(re.compile(r"^[a-zA-Z0-9]+://").match(path))
+        self.name = name
+        ds = self.catalog.get_dataset(name)
+        self.version = version or ds.latest_version
+        self.feature_schema = ds.get_version(self.version).feature_schema
+        self.column_types = copy(ds.schema)
+        if "sys__id" in self.column_types:
+            self.column_types.pop("sys__id")
+        self.starting_step = QueryStep(self.catalog, name, self.version)
 
     def __iter__(self):
         return iter(self.db_results())
@@ -1595,21 +1510,11 @@ class DatasetQuery:
         return query
 
     @detach
-    def subtract(self, dq: "DatasetQuery") -> "Self":
-        return self._subtract(dq, on=[("source", "source"), ("path", "path")])
-
-    @detach
-    def _subtract(self, dq: "DatasetQuery", on: Sequence[tuple[str, str]]) -> "Self":
+    def subtract(self, dq: "DatasetQuery", on: Sequence[tuple[str, str]]) -> "Self":
         query = self.clone()
         query.steps.append(Subtract(dq, self.catalog, on=on))
         return query
 
-    @detach
-    def changed(self, dq: "DatasetQuery") -> "Self":
-        query = self.clone()
-        query.steps.append(Changed(dq, self.catalog))
-        return query
-
     @detach
     def generate(
         self,
@@ -1640,24 +1545,13 @@ class DatasetQuery:
 
     def _add_dependencies(self, dataset: "DatasetRecord", version: int):
         for dependency in self.dependencies:
-            if isinstance(dependency, tuple):
-                # dataset dependency
-                ds_dependency_name, ds_dependency_version = dependency
-                self.catalog.metastore.add_dataset_dependency(
-                    dataset.name,
-                    version,
-                    ds_dependency_name,
-                    ds_dependency_version,
-                )
-            else:
-                # storage dependency - its name is a valid StorageURI
-                storage = self.catalog.metastore.get_storage(dependency)
-                self.catalog.metastore.add_storage_dependency(
-                    StorageURI(dataset.name),
-                    version,
-                    storage.uri,
-                    storage.timestamp_str,
-                )
+            ds_dependency_name, ds_dependency_version = dependency
+            self.catalog.metastore.add_dataset_dependency(
+                dataset.name,
+                version,
+                ds_dependency_name,
+                ds_dependency_version,
+            )
 
     def exec(self) -> "Self":
         """Execute the query."""

{datachain-0.3.16 → datachain-0.3.17}/src/datachain/query/schema.py

@@ -19,6 +19,17 @@ if TYPE_CHECKING:
 DEFAULT_DELIMITER = "__"
 
 
+def file_signals(row, signal_name="file"):
+    # TODO this is workaround until we decide what to do with these classes
+    prefix = f"{signal_name}{DEFAULT_DELIMITER}"
+    return {
+        c_name.removeprefix(prefix): c_value
+        for c_name, c_value in row.items()
+        if c_name.startswith(prefix)
+        and DEFAULT_DELIMITER not in c_name.removeprefix(prefix)
+    }
+
+
 class ColumnMeta(type):
     @staticmethod
     def to_db_name(name: str) -> str:
@@ -86,8 +97,8 @@ class Object(UDFParameter):
         cb: Callback = DEFAULT_CALLBACK,
         **kwargs,
     ) -> Any:
-        client = catalog.get_client(row["source"])
-        uid = catalog._get_row_uid(row)
+        client = catalog.get_client(row["file__source"])
+        uid = catalog._get_row_uid(file_signals(row))
         if cache:
             client.download(uid, callback=cb)
         with client.open_object(uid, use_cache=cache, cb=cb) as f:
@@ -103,8 +114,8 @@ class Object(UDFParameter):
         cb: Callback = DEFAULT_CALLBACK,
         **kwargs,
     ) -> Any:
-        client = catalog.get_client(row["source"])
-        uid = catalog._get_row_uid(row)
+        client = catalog.get_client(row["file__source"])
+        uid = catalog._get_row_uid(file_signals(row))
         if cache:
             await client._download(uid, callback=cb)
         obj = await mapper.to_thread(
@@ -129,8 +140,8 @@ class Stream(UDFParameter):
         cb: Callback = DEFAULT_CALLBACK,
         **kwargs,
     ) -> Any:
-        client = catalog.get_client(row["source"])
-        uid = catalog._get_row_uid(row)
+        client = catalog.get_client(row["file__source"])
+        uid = catalog._get_row_uid(file_signals(row))
         if cache:
             client.download(uid, callback=cb)
         return client.open_object(uid, use_cache=cache, cb=cb)
@@ -145,8 +156,8 @@ class Stream(UDFParameter):
         cb: Callback = DEFAULT_CALLBACK,
         **kwargs,
     ) -> Any:
-        client = catalog.get_client(row["source"])
-        uid = catalog._get_row_uid(row)
+        client = catalog.get_client(row["file__source"])
+        uid = catalog._get_row_uid(file_signals(row))
         if cache:
             await client._download(uid, callback=cb)
         return await mapper.to_thread(
@@ -178,8 +189,8 @@ class LocalFilename(UDFParameter):
             # If the glob pattern is specified and the row filename
             # does not match it, then return None
             return None
-        client = catalog.get_client(row["source"])
-        uid = catalog._get_row_uid(row)
+        client = catalog.get_client(row["file__source"])
+        uid = catalog._get_row_uid(file_signals(row))
         client.download(uid, callback=cb)
         return client.cache.get_path(uid)
 
@@ -197,8 +208,8 @@ class LocalFilename(UDFParameter):
             # If the glob pattern is specified and the row filename
             # does not match it, then return None
             return None
-        client = catalog.get_client(row["source"])
-        uid = catalog._get_row_uid(row)
+        client = catalog.get_client(row["file__source"])
+        uid = catalog._get_row_uid(file_signals(row))
         await client._download(uid, callback=cb)
         return client.cache.get_path(uid)