WIP simplifying load/startup

src/personal_mcp/skills/document_loader.py

@@ -1,125 +0,0 @@
-from __future__ import annotations
-
-import re
-from importlib.resources.abc import Traversable
-from pathlib import PurePosixPath
-from typing import Any
-
-import yaml
-
-from ..registry.models.common import SKILL_ID_RE
-from ..registry.models.common import ReferenceEntry
-from ..registry.models.prompt import PromptFrontmatter
-from ..registry.models.skill import SkillFrontmatter
-
-
-def _parse_frontmatter(markdown: str, *, path: str) -> tuple[dict[str, Any], str]:
-    if not markdown.startswith("---"):
-        raise ValueError(f"missing YAML frontmatter: {path}")
-
-    lines = markdown.splitlines()
-    if len(lines) < 3 or lines[0].strip() != "---":
-        raise ValueError(f"invalid YAML frontmatter start: {path}")
-
-    end_index: int | None = None
-    for i in range(1, len(lines)):
-        if lines[i].strip() == "---":
-            end_index = i
-            break
-
-    if end_index is None:
-        raise ValueError(f"missing YAML frontmatter terminator: {path}")
-
-    raw_yaml = "\n".join(lines[1:end_index])
-    body = "\n".join(lines[end_index + 1 :])
-    parsed = yaml.safe_load(raw_yaml)
-    if not isinstance(parsed, dict):
-        raise TypeError(f"frontmatter must parse to an object: {path}")
-    return parsed, body
-
-
-def _walk_markdown(
-    node: Traversable,
-    *,
-    prefix: PurePosixPath | None = None,
-) -> list[tuple[str, Traversable]]:
-    prefix = PurePosixPath() if prefix is None else prefix
-    results: list[tuple[str, Traversable]] = []
-    for child in sorted(node.iterdir(), key=lambda item: item.name):
-        relpath = prefix.joinpath(child.name)
-        if child.is_dir():
-            results.extend(_walk_markdown(child, prefix=relpath))
-            continue
-        if not child.is_file() or not child.name.lower().endswith(".md"):
-            continue
-        results.append((relpath.as_posix(), child))
-    return results
-
-
-def _validate_skill_frontmatter(raw: dict[str, Any], *, skill_dir_name: str) -> SkillFrontmatter:
-    model = SkillFrontmatter.model_validate(raw)
-    if model.name != skill_dir_name:
-        raise ValueError("frontmatter name must exactly match skill directory name")
-    if model.x_personal_mcp.id != model.name:
-        raise ValueError("x-personal-mcp.id must exactly match name")
-    expected_capability = f"resource://skills/{model.name}/document"
-    if expected_capability not in model.x_personal_mcp.capabilities:
-        raise ValueError(f"capabilities must include {expected_capability}")
-    return model
-
-
-def _validate_prompt_frontmatter(raw: dict[str, Any], *, prompt_dir_name: str) -> PromptFrontmatter:
-    model = PromptFrontmatter.model_validate(raw)
-    if model.name != prompt_dir_name:
-        raise ValueError("frontmatter name must exactly match prompt directory name")
-    if model.x_personal_mcp.id != model.name:
-        raise ValueError("x-personal-mcp.id must exactly match name")
-    expected_capability = f"resource://prompts/{model.name}/document"
-    if expected_capability not in model.x_personal_mcp.capabilities:
-        raise ValueError(f"capabilities must include {expected_capability}")
-    return model
-
-
-def _title_from_reference_filename(filename: str) -> str:
-    stem = PurePosixPath(filename).stem
-    normalized = stem.replace("-", " ").replace("_", " ").split()
-    if not normalized:
-        return stem
-    return " ".join(token.capitalize() for token in normalized)
-
-
-def _reference_id_from_filename(filename: str) -> str | None:
-    stem = PurePosixPath(filename).stem.strip().lower().replace("_", "-")
-    normalized = re.sub(r"[^a-z0-9-]+", "-", stem)
-    normalized = re.sub(r"-+", "-", normalized).strip("-")
-    if not normalized:
-        return None
-    if not SKILL_ID_RE.fullmatch(normalized):
-        return None
-    return normalized
-
-
-def _discover_top_level_references(
-    *,
-    skill_dir: Traversable,
-) -> dict[str, ReferenceEntry]:
-    references_dir = skill_dir.joinpath("references")
-    if not references_dir.is_dir():
-        return {}
-
-    discovered: dict[str, ReferenceEntry] = {}
-    for child in sorted(references_dir.iterdir(), key=lambda item: item.name):
-        if child.is_dir() or not child.is_file():
-            continue
-        if not child.name.lower().endswith(".md"):
-            continue
-
-        ref_id = _reference_id_from_filename(child.name)
-        if ref_id is None:
-            continue
-
-        discovered[ref_id] = ReferenceEntry(
-            path=PurePosixPath("references").joinpath(child.name).as_posix(),
-            title=_title_from_reference_filename(child.name),
-        )
-    return discovered