Merge branch 'main' into add-coverage

Author: lwasser

CHANGELOG.md

@@ -8,6 +8,7 @@
 - Fix: migrate to pytest for tests and setup hatch scripts (#89, @lwasser)
 - Add: Partner support to package (#92, @lwasser)
 - Add: Code coverage setup (#97, @lwasser)
+- Fix: Add validation step to categories attr in pydantic model (#105, @lwasser)
 
 ## [v0.15](https://github.com/pyOpenSci/pyosMeta/releases/tag/v0.15)
 

pyproject.toml

@@ -10,7 +10,6 @@ authors = [{ name = "Leah Wasser", email = "[email protected]" }]
 maintainers = [
   { name = "pyOpenSci", email = "[email protected]" }, # Optional
 ]
-
 classifiers = [
   "Development Status :: 4 - Beta",
   "Intended Audience :: Developers",
@@ -24,33 +23,31 @@ classifiers = [
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
 ]
-
-
 dependencies = [
-  "ruamel-yaml>=0.17.21",
-  "requests",
-  "python-dotenv",
-  "pydantic>=2.0",
-  "requests",
-  "python-dotenv",
+    "pydantic>=2.0",
+    "python-dotenv",
+    "requests",
+    "ruamel-yaml>=0.17.21",
 ]
-
-
-# This is the metadata that pip reads to understand what versions your package supports
+# This is metadata that pip reads to understand what Python versions your package supports
 requires-python = ">=3.10"
 readme = "README.md"
 license = { text = "MIT" }
 
-
 [project.optional-dependencies]
-dev = ["pre-commit"]
+dev = [
+    "black",
+    "flake8",
+    "pre-commit",
+    "pytest",
+    "pytest-cov"
+]
 
 [project.urls]
 "Homepage" = "https://github.com/pyopensci/pyosmeta/"
 "Bug Reports" = "https://github.com/pyopensci/pyosmeta/issues"
 "Source" = "https://github.com/pyopensci/pyosmeta/issues"
 
-
 # These are entry points that allow you to surface specific functionality
 # for a user to run directly from the package.
 [project.scripts]
@@ -79,6 +76,9 @@ run-coverage = "pytest --cov-config=pyproject.toml --cov=pyosmeta --cov=tests/*"
 run-no-cov = "run-coverage --no-cov"
 run-report = "run-coverage --cov-report=xml:coverage.xml"
 
+
+### Tool configuration ###
+
 [tool.black]
 line-length = 79
 target-version = ['py310']

src/pyosmeta/__about__.py

@@ -265,6 +265,51 @@ def clean_gh_url(cls, user: dict[str, str]) -> dict[str, str]:
 
         return user
 
+    @field_validator(
+        "categories",
+        mode="before",
+    )
+    @classmethod
+    def clean_categories(cls, categories: list[str]) -> list[str]:
+        """Make sure each category in the list is a valid value.
+
+        Valid pyos software categories are:
+            citation-management-bibliometrics, data-deposition,
+            data-extraction, data-processing-munging, data-retrieval,
+            data-validation-testing, data-visualization-analysis,
+            database-interoperability, education,
+            geospatial, scientific-software-wrappers,
+            workflow-automation-versioning
+
+
+        Parameters
+        ----------
+        categories : list[str]
+            List of categories to clean.
+
+        Returns
+        -------
+        list[str]
+            List of cleaned categories.
+        """
+
+        valid_categories = {
+            "data-processing": "data-processing-munging",
+            "data-validation": "data-validation-testing",
+            "scientific-software": "scientific-software-wrapper",
+        }
+
+        cleaned_cats = []
+        for category in categories:
+            for valid_prefix, valid_cat in valid_categories.items():
+                if category.startswith(valid_prefix):
+                    cleaned_cats.append(valid_cat)
+                    break
+            else:
+                # No match found, keep the original category
+                cleaned_cats.append(category)
+        return cleaned_cats
+
 
 @dataclass
 class ProcessIssues:

src/pyosmeta/parse_issues.py

@@ -1,6 +1,6 @@
 import pytest
 
-from pyosmeta.parse_issues import ProcessIssues
+from pyosmeta.parse_issues import ProcessIssues, ReviewModel
 
 checked = [
     ["Submitting Author", "Nabil Freij (@nabobalis)"],
@@ -65,3 +65,37 @@ def test_get_categories(
 
     # Assert the result matches the expected categories
     assert categories == expected_categories
+
+
+@pytest.mark.parametrize(
+    "input_categories,expected_return",
+    [
+        (
+            ["data-processing"],
+            ["data-processing-munging"],
+        ),
+        (
+            ["data-processing/munging"],
+            ["data-processing-munging"],
+        ),
+        (
+            ["scientific-software and friends"],
+            ["scientific-software-wrapper"],
+        ),
+        (
+            ["data-validation and things -testing"],
+            ["data-validation-testing"],
+        ),
+        (
+            ["data-processing", "data-extraction"],
+            ["data-processing-munging", "data-extraction"],
+        ),
+    ],
+)
+def test_clean_categories(
+    input_categories: list[str], expected_return: list[str]
+):
+    """Test that ensures our pydantic model cleans categories as expected"""
+
+    review = ReviewModel(categories=input_categories)
+    assert review.categories == expected_return