feat: read measurements at a pinned commit

measurements-pin.json names the measurements repository and the commit read. sync_measurements.py reads the clone in .cache/measurements at that commit, checks every line against its id and sidecar, and writes the site index and the SQLite databases. --fetch refuses a remote that changed or removed a line the pin holds, --bump moves the pin. validate_schemas checks every line and sidecar against their schemas, check_freshness flags a pin behind the remote head.

scripts/validate_schemas.py

@@ -593,6 +593,49 @@ def _format_errors() -> list[str]:
     ]
 
 
+def _measurement_errors(clone: Path | None = None, pin_path: Path | None = None) -> list[str]:
+    """Every record line and data file at the measurements pin, against their
+    schemas and the rules sync_measurements.py applies.
+
+    The records live in their own repository. Without a clone holding the
+    pin there is nothing to read, and the run says so.
+    """
+    import sync_measurements  # noqa: PLC0415
+    import measurement_records as mr  # noqa: PLC0415
+
+    clone = clone or sync_measurements.CLONE
+    pin = sync_measurements.load_pin(pin_path or sync_measurements.PIN_FILE)
+    if not sync_measurements.has_commit(clone, pin["commit"]):
+        print(f"SKIP measurements: {pin['commit'][:12]} is not in {clone} "
+              "(python scripts/sync_measurements.py --fetch)")
+        return []
+    commit = pin["commit"]
+    record_validator = _validator("core-probe-record.schema.json")
+    data_validator = _validator("core-probe-data.schema.json")
+    out: list[str] = []
+    files = sync_measurements.tree_files(clone, commit)
+    for path in sorted(p for p in files if p.endswith(".jsonl")):
+        text = sync_measurements.show(clone, commit, path).decode("utf-8")
+        for number, line in enumerate(text.splitlines(), 1):
+            try:
+                record = json.loads(line)
+            except json.JSONDecodeError as exc:
+                out.append(f"measurements {path}:{number}: {exc}")
+                continue
+            out.extend(_errors(record_validator, record, f"measurements {path}:{number}"))
+            data = mr.sidecar_path(path[len("records/"):-len(".jsonl")], str(record.get("id")))
+            if data in files:
+                out.extend(_errors(data_validator,
+                                   mr.read_sidecar(sync_measurements.show(clone, commit, data)),
+                                   f"measurements {data}"))
+    if not out:
+        try:
+            sync_measurements.read_records(clone, commit)
+        except sync_measurements.MeasurementsError as exc:
+            out.append(f"measurements {exc}")
+    return out
+
+
 def main() -> int:
     parser = argparse.ArgumentParser(allow_abbrev=False, description=__doc__)
     parser.add_argument(
@@ -616,12 +659,7 @@ def main() -> int:
     errors.extend(_save_directory_blocks())
     errors.extend(_registry_contract())
     errors.extend(_event_schema_errors())
-    errors.extend(
-        _validate_json_files(
-            sorted((ROOT / "measurements").glob("**/*.json")),
-            "core-probe-record.schema.json",
-        )
-    )
+    errors.extend(_measurement_errors())
 
     if not args.source_only:
         database_path = ROOT / "database.json"