refactor: ♻️ match Sprout (#40)

Author: martonvago

README.md

@@ -14,17 +14,16 @@ gh repo create NAME --template seedcase-project/template-data-package
 
 To add uv:
 
-1.  Delete the `pyproject.toml` file.
-2.  In the terminal run `uv init`.
-3.  Look at the Git pane and take what was removed and move it over into
+1. Delete the `pyproject.toml` file.
+2. In the terminal run `uv init`.
+3. Look at the Git pane and take what was removed and move it over into
     the new `pyproject.toml` file. You can mimic what was done in
     `example-seed-beetle` repo.
 
 Then, in the terminal, run:
 
 ``` bash
-uv add polars pyjanitor
-uv add "seedcase-sprout @ git+<https://github.com/seedcase-project/seedcase-sprout>"
+uv add polars pyjanitor seedcase-sprout
 uv add --dev ruff commitizen pre-commit typos
 ```
 

data-raw/.gitignore

@@ -0,0 +1,62 @@
+# import polars as pl
+import seedcase_sprout as sp
+
+from scripts.properties import properties
+
+# from scripts.resource_properties import resource_properties
+
+
+def main():
+    """Run the build pipeline of the data package."""
+    ## PROPERTIES
+
+    ## Create the properties script in default location if it doesn't already exist.
+    package_path = sp.PackagePath()
+    sp.create_properties_script()
+
+    ## Load your raw, but tidy, data into a Polars DataFrame.
+    # raw_data = pl.read_csv(package_path.root() / "raw" / "data.csv")
+    ## Extract field properties from the data.
+    # field_properties = sp.extract_field_properties(data=raw_data)
+
+    ## Create the resource properties script if it doesn't already exist.
+    # sp.create_resource_properties_script(
+    #     resource_name="",
+    #     fields=field_properties,
+    # )
+
+    ## Save the properties to `datapackage.json`.
+    sp.write_properties(properties=properties)
+
+    ## README
+
+    ## Create the README text for the data package.
+    readme_text = sp.as_readme_text(properties)
+    ## Write the README text to a `README.md` file.
+    sp.write_file(readme_text, package_path.readme())
+
+    ## BATCH DATA
+
+    ## Save the batch data.
+    # sp.write_resource_batch(
+    #     data=raw_data, resource_properties=resource_properties
+    # )
+
+    ## RESOURCE DATA
+
+    ## Read in all the batch data files for the resource as a list.
+    # batch_data = sp.read_resource_batches(
+    #     resource_properties=resource_properties
+    # )
+    ## Join them all together into a single Polars DataFrame.
+    # joined_data = sp.join_resource_batches(
+    #     data_list=batch_data, resource_properties=resource_properties
+    # )
+    ## Write the resource data file.
+    # sp.write_resource_data(
+    #     data=joined_data, resource_properties=resource_properties
+    # )
+
+
+if __name__ == "__main__":
+    main()

data-raw/downloaded/.gitignore

@@ -17,7 +17,7 @@ requires-python = ">=3.12"
 dependencies = [
     "polars>=1.27.0",
     "pyjanitor>=0.31.0",
-    "seedcase-sprout",
+    "seedcase-sprout>=0.46.3",
 ]
 
 [project.urls]
@@ -31,6 +31,3 @@ dev = [
     "ruff>=0.11.4",
     "typos>=1.32.0",
 ]
-
-[tool.uv.sources]
-seedcase-sprout = { git = "https://github.com/seedcase-project/seedcase-sprout" }

main.py

@@ -0,0 +1 @@
+"""Processing and build pipeline scripts."""

pyproject.toml

@@ -0,0 +1,53 @@
+import seedcase_sprout as sp
+
+# from .resource_properties import resource_properties
+
+properties = sp.PackageProperties(
+    ## Required:
+    name="template-data-package",
+    title="",
+    description="",
+    licenses=[
+        sp.LicenseProperties(
+            ## Required:
+            name="",
+            ## Optional:
+            # path="",
+            # title="",
+        ),
+    ],
+    ## Optional:
+    # homepage="",
+    # contributors=[
+    #    sp.ContributorProperties(
+    #        ## Required:
+    #        title="",
+    #        ## Optional:
+    #        path="",
+    #        email="",
+    #        given_name="",
+    #        family_name="",
+    #        organization="",
+    #        roles=[""],
+    #    ),
+    # ],
+    # keywords=[""],
+    # image="",
+    # sources=[
+    #    sp.SourceProperties(
+    #        ## Required:
+    #        title="",
+    #        ## Optional:
+    #        path="",
+    #        email="",
+    #        version="",
+    #    ),
+    # ],
+    # resources=[
+    #     resource_properties,
+    # ],
+    ## Autogenerated:
+    id="108e33ad-33f9-414f-a93c-bfed390be4e6",
+    version="0.1.0",
+    created="2025-07-04T15:17:28+01:00",
+)