Parse dependencies from all args if depends_on is not used. (#384)

Author: tobiasraabe

docs/source/changes.md

@@ -8,6 +8,8 @@ releases are available on [PyPI](https://pypi.org/project/pytask) and
 ## 0.4.0 - 2023-xx-xx
 
 - {pull}`323` remove Python 3.7 support and use a new Github action to provide mamba.
+- {pull}`384` allows to parse dependencies from every function argument if `depends_on`
+  is not present.
 - {pull}`387` replaces pony with sqlalchemy.
 - {pull}`391` removes `@pytask.mark.parametrize`.
 

docs/source/tutorials/defining_dependencies_products.md

@@ -4,8 +4,8 @@ To ensure pytask executes all tasks in the correct order, define which dependenc
 required and which products are produced by a task.
 
 :::{important}
-If you do not specify dependencies and products as explained below, pytask will not be able
-to build a graph, a {term}`DAG`, and will not be able to execute all tasks in the
+If you do not specify dependencies and products as explained below, pytask will not be
+able to build a graph, a {term}`DAG`, and will not be able to execute all tasks in the
 project correctly!
 :::
 
@@ -19,15 +19,16 @@ def task_create_random_data(produces):
     ...
 ```
 
-The {func}`@pytask.mark.produces <pytask.mark.produces>` marker attaches a
-product to a task which is a {class}`pathlib.Path` to file. After the task has finished,
-pytask will check whether the file exists.
+The {func}`@pytask.mark.produces <pytask.mark.produces>` marker attaches a product to a
+task which is a {class}`pathlib.Path` to file. After the task has finished, pytask will
+check whether the file exists.
 
-Optionally, you can use `produces` as an argument of the task function and get access to
-the same path inside the task function.
+Add `produces` as an argument of the task function to get access to the same path inside
+the task function.
 
 :::{tip}
-If you do not know about {mod}`pathlib` check out [^id3] and [^id4]. The module is beneficial for handling paths conveniently and across platforms.
+If you do not know about {mod}`pathlib` check out [^id3] and [^id4]. The module is
+beneficial for handling paths conveniently and across platforms.
 :::
 
 ## Dependencies
@@ -44,7 +45,7 @@ def task_plot_data(depends_on, produces):
     ...
 ```
 
-Use `depends_on` as a function argument to work with the dependency path and, for
+Add `depends_on` as a function argument to work with the path of the dependency and, for
 example, load the data.
 
 ## Conversion
@@ -61,9 +62,6 @@ def task_create_random_data(produces):
     ...
 ```
 
-If you use `depends_on` or `produces` as arguments for the task function, you will have
-access to the paths of the targets as {class}`pathlib.Path`.
-
 ## Multiple dependencies and products
 
 The easiest way to attach multiple dependencies or products to a task is to pass a
@@ -108,7 +106,9 @@ Why does pytask recommend dictionaries and convert lists, tuples, or other
 iterators to dictionaries? First, dictionaries with positions as keys behave very
 similarly to lists.
 
-Secondly, dictionaries use keys instead of positions that are more verbose and descriptive and do not assume a fixed ordering. Both attributes are especially desirable in complex projects.
+Secondly, dictionaries use keys instead of positions that are more verbose and
+descriptive and do not assume a fixed ordering. Both attributes are especially desirable
+in complex projects.
 
 ## Multiple decorators
 

src/_pytask/collect.py

@@ -12,7 +12,9 @@
 from typing import Iterable
 
 from _pytask.collect_utils import depends_on
+from _pytask.collect_utils import parse_dependencies_from_task_function
 from _pytask.collect_utils import parse_nodes
+from _pytask.collect_utils import parse_products_from_task_function
 from _pytask.collect_utils import produces
 from _pytask.config import hookimpl
 from _pytask.config import IS_FILE_SYSTEM_CASE_SENSITIVE
@@ -22,6 +24,7 @@
 from _pytask.exceptions import CollectionError
 from _pytask.mark_utils import has_mark
 from _pytask.nodes import FilePathNode
+from _pytask.nodes import PythonNode
 from _pytask.nodes import Task
 from _pytask.outcomes import CollectionOutcome
 from _pytask.outcomes import count_outcomes
@@ -167,11 +170,20 @@ def pytask_collect_task(
 
     """
     if (name.startswith("task_") or has_mark(obj, "task")) and callable(obj):
-        dependencies = parse_nodes(session, path, name, obj, depends_on)
-        products = parse_nodes(session, path, name, obj, produces)
+        if has_mark(obj, "depends_on"):
+            nodes = parse_nodes(session, path, name, obj, depends_on)
+            dependencies = {"depends_on": nodes}
+        else:
+            dependencies = parse_dependencies_from_task_function(
+                session, path, name, obj
+            )
+
+        if has_mark(obj, "produces"):
+            products = parse_nodes(session, path, name, obj, produces)
+        else:
+            products = parse_products_from_task_function(session, path, name, obj)
 
         markers = obj.pytask_meta.markers if hasattr(obj, "pytask_meta") else []
-        kwargs = obj.pytask_meta.kwargs if hasattr(obj, "pytask_meta") else {}
 
         # Get the underlying function to avoid having different states of the function,
         # e.g. due to pytask_meta, in different layers of the wrapping.
@@ -184,7 +196,6 @@ def pytask_collect_task(
             depends_on=dependencies,
             produces=products,
             markers=markers,
-            kwargs=kwargs,
         )
     return None
 
@@ -205,7 +216,7 @@ def pytask_collect_task(
 @hookimpl(trylast=True)
 def pytask_collect_node(
     session: Session, path: Path, node: str | Path
-) -> FilePathNode | None:
+) -> FilePathNode | PythonNode:
     """Collect a node of a task as a :class:`pytask.nodes.FilePathNode`.
 
     Strings are assumed to be paths. This might be a strict assumption, but since this
@@ -226,8 +237,6 @@ def pytask_collect_node(
         handled by this function.
 
     """
-    if isinstance(node, str):
-        node = Path(node)
     if isinstance(node, Path):
         if not node.is_absolute():
             node = path.parent.joinpath(node)
@@ -246,7 +255,7 @@ def pytask_collect_node(
                 raise ValueError(_TEMPLATE_ERROR.format(node, case_sensitive_path))
 
         return FilePathNode.from_path(node)
-    return None
+    return PythonNode(value=node)
 
 
 def _not_ignored_paths(

src/_pytask/collect_command.py

@@ -20,6 +20,7 @@
 from _pytask.exceptions import ResolvingDependenciesError
 from _pytask.mark import select_by_keyword
 from _pytask.mark import select_by_mark
+from _pytask.nodes import FilePathNode
 from _pytask.outcomes import ExitCode
 from _pytask.path import find_common_ancestor
 from _pytask.path import relative_to
@@ -123,7 +124,11 @@ def _find_common_ancestor_of_all_nodes(
     for task in tasks:
         all_paths.append(task.path)
         if show_nodes:
-            all_paths.extend(x.path for x in tree_just_flatten(task.depends_on))
+            all_paths.extend(
+                x.path
+                for x in tree_just_flatten(task.depends_on)
+                if isinstance(x, FilePathNode)
+            )
             all_paths.extend(x.path for x in tree_just_flatten(task.produces))
 
     common_ancestor = find_common_ancestor(*all_paths, *paths)
@@ -160,14 +165,14 @@ def _print_collected_tasks(
 
     Parameters
     ----------
-    dictionary : Dict[Path, List["Task"]]
+    dictionary
         A dictionary with path on the first level, tasks on the second, dependencies and
         products on the third.
-    show_nodes : bool
+    show_nodes
         Indicator for whether dependencies and products should be displayed.
-    editor_url_scheme : str
+    editor_url_scheme
         The scheme to create an url.
-    common_ancestor : Path
+    common_ancestor
         The path common to all tasks and nodes.
 
     """
@@ -197,9 +202,13 @@ def _print_collected_tasks(
             )
 
             if show_nodes:
-                for node in sorted(
-                    tree_just_flatten(task.depends_on), key=lambda x: x.path
-                ):
+                file_path_nodes = [
+                    i
+                    for i in tree_just_flatten(task.depends_on)
+                    if isinstance(i, FilePathNode)
+                ]
+                sorted_nodes = sorted(file_path_nodes, key=lambda x: x.path)
+                for node in sorted_nodes:
                     reduced_node_name = relative_to(node.path, common_ancestor)
                     url_style = create_url_style_for_path(node.path, editor_url_scheme)
                     task_branch.add(