Files
reuse-surface/reuse_surface/registry.py
tegwick 70a5003f6e
Some checks failed
ci / validate-registry (push) Has been cancelled
Implement REUSE-WP-0013 registry establish, update, and stats
Add stats, establish (scaffold, publish-check, discover), and update CLI
commands with optional llm-connect bridge, validate --root for sibling repos,
pytest coverage, and documentation for sibling registry onboarding.
2026-06-16 01:21:01 +02:00

90 lines
2.9 KiB
Python

from __future__ import annotations
import re
from pathlib import Path
from typing import Any
import yaml
ROOT = Path(__file__).resolve().parent.parent
CAPABILITIES_DIR = ROOT / "registry" / "capabilities"
INDEX_PATH = ROOT / "registry" / "indexes" / "capabilities.yaml"
SCHEMA_PATH = ROOT / "schemas" / "capability.schema.yaml"
LEVEL_ORDERS = {
"discovery": ["D0", "D1", "D2", "D3", "D4", "D5", "D6", "D7"],
"availability": ["A0", "A1", "A2", "A3", "A4", "A5", "A6", "A7"],
"completeness": ["C0", "C1", "C2", "C3", "C4", "C5", "C6"],
"reliability": ["R0", "R1", "R2", "R3", "R4", "R5", "R6"],
}
def load_schema() -> dict[str, Any]:
with SCHEMA_PATH.open(encoding="utf-8") as handle:
return yaml.safe_load(handle)
def parse_front_matter(path: Path) -> dict[str, Any]:
text = path.read_text(encoding="utf-8")
match = re.match(r"^---\n(.*?)\n---", text, re.DOTALL)
if not match:
raise ValueError(f"{path}: missing YAML front matter")
data = yaml.safe_load(match.group(1))
if not isinstance(data, dict):
raise ValueError(f"{path}: front matter must be a mapping")
return data
def capability_paths(target: Path | None = None) -> list[Path]:
if target is not None:
return [target]
return sorted(CAPABILITIES_DIR.glob("*.md"))
def load_index() -> dict[str, Any]:
with INDEX_PATH.open(encoding="utf-8") as handle:
return yaml.safe_load(handle)
def parse_vector(vector: str) -> dict[str, str]:
parts = [part.strip() for part in vector.split("/")]
if len(parts) != 4:
raise ValueError(f"invalid vector: {vector}")
return {
"discovery": parts[0],
"availability": parts[1],
"completeness": parts[2],
"reliability": parts[3],
}
def level_at_least(dimension: str, current: str, minimum: str) -> bool:
order = LEVEL_ORDERS[dimension]
return order.index(current) >= order.index(minimum)
def registry_paths(repo_root: Path) -> dict[str, Path]:
registry = repo_root / "registry"
return {
"registry": registry,
"capabilities": registry / "capabilities",
"index": registry / "indexes" / "capabilities.yaml",
"sources": registry / "federation" / "sources.yaml",
}
def load_index_at(path: Path) -> dict[str, Any]:
with path.open(encoding="utf-8") as handle:
return yaml.safe_load(handle)
def entry_vector(front_matter: dict[str, Any]) -> str:
discovery = front_matter["maturity"]["discovery"]["current"]
availability = front_matter["maturity"]["availability"]["current"]
completeness = front_matter["external_evidence"]["completeness"]["level"]
reliability = front_matter["external_evidence"]["reliability"]["level"]
return f"{discovery} / {availability} / {completeness} / {reliability}"
def vectors_match(index_vector: str, front_matter: dict[str, Any]) -> bool:
return index_vector.replace(" ", "") == entry_vector(front_matter).replace(" ", "")