Remove attrs dependency. (#744)

Author: tobiasraabe

CHANGELOG.md

@@ -7,6 +7,8 @@ releases are available on [PyPI](https://pypi.org/project/pytask) and
 
 ## Unreleased
 
+- {pull}`744` Removed the direct dependency on attrs and migrated internal models to
+  dataclasses.
 - {pull}`766` moves runtime profiling persistence from SQLite to a JSON snapshot plus
   append-only journal in `.pytask/`, keeping runtime data resilient to crashes and
   compacted on normal build exits.

docs/source/reference_guides/api.md

@@ -203,6 +203,7 @@ Nodes are the interface for different kinds of dependencies or products.
    :members:
 .. autoclass:: pytask.PickleNode
    :members:
+   :exclude-members: serializer, deserializer
 .. autoclass:: pytask.PythonNode
    :members:
 .. autoclass:: pytask.DirectoryNode

docs_src/how_to_guides/the_data_catalog.py

@@ -1,11 +1,11 @@
+from dataclasses import dataclass
 from pathlib import Path
 from typing import Any
 
 import cloudpickle
-from attrs import define
 
 
-@define
+@dataclass
 class PickleNode:
     """A node for pickle files.
 

pyproject.toml

@@ -21,7 +21,6 @@ classifiers = [
 ]
 dynamic = ["version"]
 dependencies = [
-    "attrs>=21.3.0",
     "click>=8.1.8,!=8.2.0",
     "click-default-group>=1.2.4",
     "msgspec>=0.18.6",

src/_pytask/cache.py

@@ -5,16 +5,15 @@
 import functools
 import hashlib
 import inspect
+from dataclasses import dataclass
+from dataclasses import field
 from inspect import FullArgSpec
 from typing import TYPE_CHECKING
 from typing import Any
 from typing import ParamSpec
 from typing import Protocol
 from typing import TypeVar
 
-from attrs import define
-from attrs import field
-
 from _pytask._hashlib import hash_value
 
 if TYPE_CHECKING:
@@ -35,17 +34,17 @@ class HasCache(Protocol):
     cache: Cache
 
 
-@define
+@dataclass
 class CacheInfo:
     hits: int = 0
     misses: int = 0
 
 
-@define
+@dataclass
 class Cache:
-    _cache: dict[str, Any] = field(factory=dict)
-    _sentinel: Any = field(factory=object)
-    cache_info: CacheInfo = field(factory=CacheInfo)
+    _cache: dict[str, Any] = field(default_factory=dict)
+    _sentinel: Any = field(default_factory=object)
+    cache_info: CacheInfo = field(default_factory=CacheInfo)
 
     def memoize(self, func: Callable[P, R]) -> Memoized[P, R]:
         func_module = getattr(func, "__module__", "")

src/_pytask/clean.py

@@ -6,11 +6,11 @@
 import itertools
 import shutil
 import sys
+from dataclasses import dataclass
 from typing import TYPE_CHECKING
 from typing import Any
 
 import click
-from attrs import define
 
 from _pytask.click import ColoredCommand
 from _pytask.click import EnumChoice
@@ -243,7 +243,7 @@ def _find_all_unknown_paths(
     )
 
 
-@define(repr=False)
+@dataclass(repr=False)
 class _RecursivePathNode:
     """A class for a path to a file or directory which recursively instantiates itself.
 

src/_pytask/coiled_utils.py

@@ -1,18 +1,17 @@
 from __future__ import annotations
 
+from dataclasses import dataclass
 from typing import TYPE_CHECKING
 from typing import Any
 
-from attrs import define
-
 if TYPE_CHECKING:
     from collections.abc import Callable
 
 try:
     from coiled.function import Function
 except ImportError:
 
-    @define
+    @dataclass
     class Function:
         cluster_kwargs: dict[str, Any]
         environ: dict[str, Any]

src/_pytask/collect_utils.py

@@ -3,13 +3,12 @@
 from __future__ import annotations
 
 import inspect
+from dataclasses import replace
 from typing import TYPE_CHECKING
 from typing import Annotated
 from typing import Any
 from typing import get_origin
 
-import attrs
-
 from _pytask._inspect import get_annotations
 from _pytask.exceptions import NodeNotCollectedError
 from _pytask.models import NodeInfo
@@ -308,7 +307,7 @@ def collect_dependency(
         # If a node is a dependency and its value is not set, the node is a product in
         # another task and the value will be set there. Thus, we wrap the original node
         # in another node to retrieve the value after it is set.
-        new_node = attrs.evolve(node, value=node)
+        new_node = replace(node, value=node)
         node_info = node_info._replace(value=new_node)
 
     collected_node = session.hook.pytask_collect_node(

src/_pytask/dag_utils.py

@@ -3,11 +3,11 @@
 from __future__ import annotations
 
 import itertools
+from dataclasses import dataclass
+from dataclasses import field
 from typing import TYPE_CHECKING
 
 import networkx as nx
-from attrs import define
-from attrs import field
 
 from _pytask.mark_utils import has_mark
 
@@ -61,7 +61,7 @@ def node_and_neighbors(dag: nx.DiGraph, node: str) -> Iterable[str]:
     return itertools.chain(dag.predecessors(node), [node], dag.successors(node))
 
 
-@define
+@dataclass
 class TopologicalSorter:
     """The topological sorter class.
 
@@ -78,9 +78,9 @@ class TopologicalSorter:
     """
 
     dag: nx.DiGraph
-    priorities: dict[str, int] = field(factory=dict)
-    _nodes_processing: set[str] = field(factory=set)
-    _nodes_done: set[str] = field(factory=set)
+    priorities: dict[str, int] = field(default_factory=dict)
+    _nodes_processing: set[str] = field(default_factory=set)
+    _nodes_done: set[str] = field(default_factory=set)
 
     @classmethod
     def from_dag(cls, dag: nx.DiGraph) -> TopologicalSorter:

src/_pytask/data_catalog.py

@@ -20,7 +20,6 @@
 from _pytask.exceptions import NodeNotCollectedError
 from _pytask.models import NodeInfo
 from _pytask.node_protocols import PNode
-from _pytask.node_protocols import PPathNode
 from _pytask.node_protocols import PProvisionalNode
 from _pytask.node_protocols import warn_about_upcoming_attributes_field_on_nodes
 from _pytask.nodes import PickleNode
@@ -39,6 +38,14 @@ def _get_parent_path_of_data_catalog_module(stacklevel: int = 2) -> Path:
     return Path.cwd()
 
 
+def _is_path_node_type(node_type: type[Any]) -> bool:
+    """Return True if the class looks like a path-based node."""
+    for cls in node_type.__mro__:
+        if "path" in getattr(cls, "__annotations__", {}):
+            return True
+    return False
+
+
 @dataclass(kw_only=True)
 class DataCatalog:
     """A data catalog.
@@ -115,7 +122,7 @@ def add(self, name: str, node: PNode | PProvisionalNode | Any = None) -> None:
 
         if node is None:
             filename = hashlib.sha256(name.encode()).hexdigest()
-            if isinstance(self.default_node, PPathNode):
+            if _is_path_node_type(self.default_node):
                 assert self.path is not None
                 self._entries[name] = self.default_node(
                     name=name, path=self.path / f"{filename}.pkl"