registry ingest test scaffolding

src/personal_mcp/registry/ingest/skill.py

@@ -0,0 +1,57 @@
+from collections.abc import Iterable
+from dataclasses import dataclass
+from fnmatch import fnmatch
+from importlib.resources.abc import Traversable
+from itertools import groupby
+from itertools import starmap
+from typing import Self
+
+from .document import MarkdownDocument
+
+
+@dataclass(frozen=True, slots=True)
+class SkillFilesBundle:
+    """Represents a skill and all of its associated markdown files."""
+
+    slug: str
+    skill: MarkdownDocument
+    references: tuple[MarkdownDocument, ...]
+    other: tuple[MarkdownDocument, ...]
+
+    @classmethod
+    def from_root(cls, root: Traversable) -> list[Self]:
+        # Should only be used for testing
+        return list(cls.from_docs(MarkdownDocument.from_root(root).values()))
+
+    @classmethod
+    def from_docs(cls, docs: Iterable[MarkdownDocument]) -> tuple[Self, ...]:
+        return tuple(starmap(cls.from_paths, group_skill_paths(docs).items()))
+
+    @classmethod
+    def from_paths(cls, slug: str, paths: set[MarkdownDocument]) -> Self:
+        skill = next(iter(p for p in paths if p.relpath.name == "SKILL.md"))
+        groups = {
+            k: tuple(v)
+            for k, v in groupby(
+                paths,
+                key=lambda p: fnmatch(p.relpath.as_posix(), f"skills/{slug}/references/*.md"),
+            )
+        }
+        references = groups.get(True, ())
+        other = tuple(p for p in groups.get(False, ()) if p != skill)
+        return cls(
+            slug=slug,
+            skill=skill,
+            references=references,
+            other=other,
+        )
+
+
+def group_skill_paths(docs: Iterable[MarkdownDocument]) -> dict[str, set[MarkdownDocument]]:
+    """Group skills from a list of markdown documents by their skill slug."""
+    s = sorted(
+        filter(lambda d: d.skill_slug is not None, docs),
+        key=lambda d: (d.skill_slug or "", d.relpath.stem),
+    )
+    grouped = groupby(s, key=lambda doc: doc.skill_slug)
+    return {k: set(g) for k, g in grouped if k}