Fix #45. (#47)

Author: tobiasraabe

.github/workflows/main.yml

@@ -48,7 +48,7 @@ jobs:
 
       - name: Run unit tests and doctests.
         shell: bash -l {0}
-        run: tox -e pytest -- -m "unit or (not integration and not end_to_end)" --cov=./ --cov-report=xml -n auto
+        run: tox -e test -- -m "unit or (not integration and not end_to_end)" --cov=./ --cov-report=xml -n auto
 
       - name: Upload coverage report for unit tests and doctests.
         if: runner.os == 'Linux' && matrix.python-version == '3.10'
@@ -57,7 +57,7 @@ jobs:
 
       - name: Run end-to-end tests.
         shell: bash -l {0}
-        run: tox -e pytest -- -m end_to_end --cov=./ --cov-report=xml -n auto
+        run: tox -e test -- -m end_to_end --cov=./ --cov-report=xml -n auto
 
       - name: Upload coverage reports of end-to-end tests.
         if: runner.os == 'Linux' && matrix.python-version == '3.10'

.pre-commit-config.yaml

@@ -46,7 +46,7 @@ repos:
         additional_dependencies: [
             attrs>=21.3.0,
             click,
-            pytask>=0.4.0,
+            pytask>=0.4.5,
             types-PyYAML,
             types-setuptools
         ]

CHANGES.md

@@ -5,9 +5,10 @@ chronological order. Releases follow [semantic versioning](https://semver.org/)
 releases are available on [PyPI](https://pypi.org/project/pytask-r) and
 [Anaconda.org](https://anaconda.org/conda-forge/pytask-r).
 
-## 0.4.1 - 2024-xx-xx
+## 0.4.1 - 2024-04-20
 
 - {pull}`46` modernizes the package.
+- {pull}`47` fixes couple of issues raised in {issue}`45`.
 
 ## 0.4.0 - 2023-10-08
 

README.md

@@ -31,34 +31,30 @@ You also need to have R installed and `Rscript` on your command line. Test it by
 the following on the command line
 
 ```console
-$ Rscript --help
+Rscript --help
 ```
 
-If an error is shown instead of a help page, you can install R with `conda` by choosing
-either R or Microsoft R Open (MRO). Choose one of the two following commands. (See
-[here](https://docs.anaconda.com/anaconda/user-guide/tasks/%20using-r-language) for
-further explanation on Anaconda, R, and MRO.)
+If an error is shown instead of a help page, you can install R with `conda`.
 
 ```console
-$ conda install -c r r-base     # For normal R.
-$ conda install -c r mro-base   # For MRO.
+conda install -c conda-forge r-base
 ```
 
 Or install install R from the official [R Project](https://www.r-project.org/).
 
 ## Usage
 
-To create a task which runs a R script, define a task function with the `@pytask.mark.r`
-decorator. The `script` keyword provides an absolute path or path relative to the task
-module to the R script.
+To create a task that runs an R script, define a task function with the `@mark.r`
+decorator. The `script` keyword provides an absolute path or a path relative to the task
+module.
 
 ```python
-import pytask
+from pathlib import Path
+from pytask import mark
 
 
-@pytask.mark.r(script="script.r")
-@pytask.mark.produces("out.rds")
-def task_run_r_script():
+@mark.r(script=Path("script.r"))
+def task_run_r_script(produces: Path = Path("out.rds")):
     pass
 ```
 
@@ -68,10 +64,9 @@ more information.
 
 ### Dependencies and Products
 
-Dependencies and products can be added as with a normal pytask task using the
-`@pytask.mark.depends_on` and `@pytask.mark.produces` decorators. which is explained in
-this
-[tutorial](https://pytask-dev.readthedocs.io/en/stable/tutorials/defining_dependencies_products.html).
+Dependencies and products can be added as usual. See this
+[tutorial](https://pytask-dev.readthedocs.io/en/stable/tutorials/defining_dependencies_products.html)
+for some help.
 
 ### Accessing dependencies and products in the script
 
@@ -99,10 +94,13 @@ To parse the JSON file, you need to install
 You can also pass any other information to your script by using the `@task` decorator.
 
 ```python
+from pathlib import Path
+from pytask import mark, task
+
+
 @task(kwargs={"number": 1})
-@pytask.mark.r(script="script.r")
-@pytask.mark.produces("out.rds")
-def task_run_r_script():
+@mark.r(script=Path("script.r"))
+def task_run_r_script(produces: Path = Path("out.rds")):
     pass
 ```
 
@@ -115,11 +113,11 @@ config$number  # Is 1.
 ### Debugging
 
 In case a task throws an error, you might want to execute the script independently from
-pytask. After a failed execution, you see the command which executed the R script in the
+pytask. After a failed execution, you see the command that executed the R script in the
 report of the task. It looks roughly like this
 
 ```console
-$ Rscript <options> script.r <path-to>/.pytask/task_py_task_example.json
+Rscript <options> script.r <path-to>/.pytask/task_py_task_example.json
 ```
 
 ### Command Line Arguments
@@ -128,9 +126,8 @@ The decorator can be used to pass command line arguments to `Rscript`. See the f
 example.
 
 ```python
-@pytask.mark.r(script="script.r", options="--vanilla")
-@pytask.mark.produces("out.rds")
-def task_run_r_script():
+@mark.r(script=Path("script.r"), options="--vanilla")
+def task_run_r_script(produces: Path = Path("out.rds")):
     pass
 ```
 
@@ -146,9 +143,8 @@ different outputs.
 for i in range(2):
 
     @task
-    @pytask.mark.r(script=f"script_{i}.r")
-    @pytask.mark.produces(f"out_{i}.csv")
-    def task_execute_r_script():
+    @mark.r(script=Path(f"script_{i}.r"))
+    def task_execute_r_script(produces: Path = Path(f"out_{i}.csv")):
         pass
 ```
 
@@ -159,9 +155,8 @@ If you want to pass different inputs to the same R script, pass these arguments
 for i in range(2):
 
     @task(kwargs={"i": i})
-    @pytask.mark.r(script="script.r")
-    @pytask.mark.produces(f"output_{i}.csv")
-    def task_execute_r_script():
+    @mark.r(script=Path("script.r"))
+    def task_execute_r_script(produces: Path = Path(f"output_{i}.csv")):
         pass
 ```
 
@@ -189,11 +184,11 @@ supports YAML (if PyYaml is installed).
 Use the `serializer` keyword arguments of the `@pytask.mark.r` decorator with
 
 ```python
-@pytask.mark.r(script="script.r", serializer="yaml")
+@mark.r(script=Path("script.r"), serializer="yaml")
 def task_example(): ...
 ```
 
-And in your R script use
+And, in your R script use
 
 ```r
 library(yaml)
@@ -203,22 +198,22 @@ config <- read_yaml(args[length(args)])
 
 Note that the `YAML` package needs to be installed.
 
-If you need a custom serializer, you can also provide any callable to `serializer` which
-transforms data to a string. Use `suffix` to set the correct file ending.
+If you need a custom serializer, you can also provide any callable `serializer` which
+transforms data into a string. Use `suffix` to set the correct file ending.
 
 Here is a replication of the JSON example.
 
 ```python
 import json
 
 
-@pytask.mark.r(script="script.r", serializer=json.dumps, suffix=".json")
+@mark.r(script=Path("script.r"), serializer=json.dumps, suffix=".json")
 def task_example(): ...
 ```
 
 ### Configuration
 
-You can influence the default behavior of pytask-r with some configuration values.
+You can influence the default behavior of pytask-r with configuration values.
 
 **`r_serializer`**
 

pyproject.toml

@@ -10,7 +10,7 @@ classifiers = [
     "Programming Language :: R",
 ]
 requires-python = ">=3.8"
-dependencies = ["click", "pluggy>=1.0.0", "pytask>=0.4.0"]
+dependencies = ["click", "pluggy>=1.0.0", "pytask>=0.4.5"]
 dynamic = ["version"]
 
 [[project.authors]]

src/pytask_r/collect.py

@@ -66,11 +66,11 @@ def pytask_collect_task(
             default_serializer=session.config["r_serializer"],
             default_suffix=session.config["r_suffix"],
         )
-        script, options, _, suffix = r(**marks[0].kwargs)
+        script, options, _, suffix = r(**mark.kwargs)
 
         obj.pytask_meta.markers.append(mark)
 
-        # Collect the nodes in @pytask.mark.julia and validate them.
+        # Collect the nodes in @pytask.mark.r and validate them.
         path_nodes = Path.cwd() if path is None else path.parent
 
         if isinstance(script, str):
@@ -93,10 +93,13 @@ def pytask_collect_task(
             ),
         )
 
-        if not (isinstance(script_node, PathNode) and script_node.path.suffix == ".r"):
+        if not (
+            isinstance(script_node, PathNode)
+            and script_node.path.suffix in (".r", ".R")
+        ):
             msg = (
                 "The 'script' keyword of the @pytask.mark.r decorator must point "
-                f"to Julia file with the .r suffix, but it is {script_node}."
+                f"to an R file with the .r or .R extension, but it is {script_node}."
             )
             raise ValueError(msg)
 
@@ -169,7 +172,7 @@ def _parse_r_mark(
     default_serializer: str,
     default_suffix: str,
 ) -> Mark:
-    """Parse a Julia mark."""
+    """Parse an R mark."""
     script, options, serializer, suffix = r(**mark.kwargs)
 
     parsed_kwargs = {}

src/pytask_r/config.py

@@ -20,7 +20,7 @@ def pytask_parse_config(config: dict[str, Any]) -> None:
             f"{list(SERIALIZERS)}."
         )
         raise ValueError(msg)
-    config["r_suffix"] = config.get("r_suffix", "")
+    config["r_suffix"] = config.get("r_suffix", ".json")
     config["r_options"] = _parse_value_or_whitespace_option(config.get("r_options"))
 
 

src/pytask_r/execute.py

@@ -44,11 +44,11 @@ def collect_keyword_arguments(task: PTask) -> dict[str, Any]:
     # Remove all kwargs from the task so that they are not passed to the function.
     kwargs: dict[str, Any] = {
         **tree_map(  # type: ignore[dict-item]
-            lambda x: str(x.path) if isinstance(x, PPathNode) else str(x.value),
+            lambda x: str(x.path) if isinstance(x, PPathNode) else x.value,
             task.depends_on,
         ),
         **tree_map(  # type: ignore[dict-item]
-            lambda x: str(x.path) if isinstance(x, PPathNode) else str(x.value),
+            lambda x: str(x.path) if isinstance(x, PPathNode) else x.value,
             task.produces,
         ),
     }