Separated open-cmis-tck and guide-board repositories

src/guide_board/artifacts.py

@@ -0,0 +1,65 @@
+"""Artifact manifest helpers."""
+
+from __future__ import annotations
+
+import hashlib
+import mimetypes
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+
+from guide_board.schema import assert_valid
+
+
+def build_artifact_manifest(
+    run_dir: Path,
+    run_id: str,
+    evidence: list[dict[str, Any]],
+) -> list[dict[str, Any]]:
+    artifacts: list[dict[str, Any]] = []
+    seen: set[str] = set()
+    for item in evidence:
+        producer = item["check_id"]
+        for artifact_ref in item.get("artifact_refs", []):
+            if not isinstance(artifact_ref, str) or artifact_ref in seen:
+                continue
+            seen.add(artifact_ref)
+            path = (run_dir / artifact_ref).resolve()
+            try:
+                path.relative_to(run_dir.resolve())
+            except ValueError:
+                continue
+            if not path.exists() or not path.is_file():
+                continue
+            artifact = {
+                "id": f"artifact:{_safe_id(artifact_ref)}",
+                "run_id": run_id,
+                "path": artifact_ref,
+                "media_type": _media_type(path),
+                "producer": producer,
+                "checksum": f"sha256:{_sha256(path)}",
+                "created_at": datetime.now(timezone.utc).isoformat(),
+                "retention_class": "raw",
+            }
+            assert_valid(artifact, "raw-artifact")
+            artifacts.append(artifact)
+    return artifacts
+
+
+def _sha256(path: Path) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as handle:
+        for chunk in iter(lambda: handle.read(1024 * 1024), b""):
+            digest.update(chunk)
+    return digest.hexdigest()
+
+
+def _media_type(path: Path) -> str:
+    guessed, _ = mimetypes.guess_type(path.name)
+    if guessed:
+        return guessed
+    return "application/octet-stream"
+
+
+def _safe_id(value: str) -> str:
+    return "".join(char if char.isalnum() or char in {"-", "_"} else "_" for char in value)