Merge pull request #6 from emsearcy/sanitize-slugs

feat: add slug_from_project_name function for better project slug sanitization

Author: emsearcy

playbooks/projects/base_projects/3_umbrellas.yaml

@@ -28,7 +28,7 @@ sample_umbrella_buf:
     {% for buf_child in range(25) %}
     {% set buf_child_name = fake.catch_phrase().title() %}
     - json:
-        slug: {{ buf_child_name | lower | replace(" ", "-") }}
+        slug: {{ slug_from_project_name(buf_child_name) }}
         name: {{ buf_child_name }} Project
         description: >-
           {{ buf_child_name }}
@@ -39,8 +39,8 @@ sample_umbrella_buf:
         parent_uid: !ref "sample_umbrella_buf.steps[0]._response.uid"
         legal_entity_name: {{ buf_child_name }} Project
         legal_entity_type: Subproject
-        repository_url: https://example.com/{{ buf_child_name | lower | replace(" ", "-") }}
-        website_url: https://{{ buf_child_name | lower | replace(" ", "-") }}.example/
+        repository_url: https://example.com/{{ slug_from_project_name(buf_child_name) }}
+        website_url: https://{{ slug_from_project_name(buf_child_name) }}.example/
     {% endfor %}
 
 sample_umbrella_iubp:
@@ -71,7 +71,7 @@ sample_umbrella_iubp:
     {% for iubp_child in range(15) %}
     {% set iubp_child_name = fake.catch_phrase().title() %}
     - json:
-        slug: {{ iubp_child_name | lower | replace(" ", "-") }}
+        slug: {{ slug_from_project_name(iubp_child_name) }}
         name: {{ iubp_child_name }} Project
         description: >-
           {{ iubp_child_name }}
@@ -85,6 +85,6 @@ sample_umbrella_iubp:
         # Children's parent is the umbrella; legal parent is LF Projects, LLC.
         parent_uid: !ref "sample_umbrella_iubp.steps[0]._response.uid"
         legal_parent_uid: !ref "base_projects.steps[?json.slug == 'lfprojects']._response.uid | [0]"
-        repository_url: https://example.com/{{ iubp_child_name | lower | replace(" ", "-") }}
-        website_url: https://{{ iubp_child_name | lower | replace(" ", "-") }}.example/
+        repository_url: https://example.com/{{ slug_from_project_name(iubp_child_name) }}
+        website_url: https://{{ slug_from_project_name(iubp_child_name) }}.example/
     {% endfor %}

src/lfx_v2_mockdata/__init__.py

@@ -102,6 +102,31 @@ class UploadMockDataArgs(BaseModel):
 logger = structlog.get_logger()
 
 
+def slug_from_project_name(project_name: str) -> str:
+    """Generate a sanitized slug from a project name.
+
+    The slug is based on the project name lowercased, with non-alphanumeric
+    characters replaced with hyphens, consecutive hyphens replaced with a
+    single hyphen, and leading and trailing hyphens stripped.
+    """
+    if not project_name:
+        return ""
+
+    # Convert to lowercase.
+    slug = project_name.lower()
+
+    # Replace non-alphanumeric characters with hyphens.
+    slug = re.sub(r"[^a-z0-9]+", "-", slug)
+
+    # Replace consecutive hyphens with a single hyphen.
+    slug = re.sub(r"-+", "-", slug)
+
+    # Strip leading and trailing hyphens.
+    slug = slug.strip("-")
+
+    return slug
+
+
 class JMESPath(yaml.YAMLObject):
     """JMESPath represents a parsed !ref YAML tag.
 
@@ -521,6 +546,7 @@ def yaml_render(template_dir, yaml_file):
             .isoformat("T")
             .replace("+00:00", "Z")
         )
+        env.globals["slug_from_project_name"] = slug_from_project_name
         # Store the environment in the context for use by the !include
         # constructor/macro and remaining YAML files in this context/directory.
         jinja_env.set(env)