infra/paperspec
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: validator, bundle builder and release checks for 0.1.0

Browse Source 
- Add tools/validate.py: validates packages, and with --correction runs
  proposed corrections through the gate against a package without
  writing anything (spec/11 §11.4). The gate now refuses a proposal that
  fails the correction schema, rule correction.schema.
- tools/load.py validates every package before loading, and with
  --bundle --built-from builds a scienting-bundle/1 with the FTS5 search
  index and bundle_meta (spec/13 §13.5). Search rows are defined per
  unit (sentence, cell, equation outside a sentence, figure-text) with
  the parent kind as context.
- Roster keys carry a role, and a key with the role owner may revoke any
  receipt (spec/08 §8.7, spec/20); roster schema, store table and the
  fixture roster updated. The checker signs a trial revocation to prove
  the rule both ways.
- A qa: receipt raises the nodes it sampled except those in its errors
  (spec/08 §8.2); the example paper's fidelity counts become 27 F3,
  13 F2, 4 F1 and 1 F0.
- The destination chooses the keyed scheme, not the text policy:
  hmac-team between the team's machines, hkdf-pages outside the team
  (spec/05 §5.8, spec/12 §12.5).
- A TextQuoteSelector must repeat the anchor's plain quote and is absent
  for hashed or keyed anchors (spec/18 §18.3).
- Add fixtures/records/suspect.json, a scienting-suspect/1 record.
- Oracle: hashes are kept incrementally and checked after every
  correction against a full recomputation; load and write refuse unsafe
  manifest paths; Ed25519, HKDF and schema validation come from the
  cryptography and jsonschema packages; canonical JSON uses the built-in
  encoder with an exact RFC 8785 fallback.
- The tools need Python 3.14 with cryptography and jsonschema; the py310
  CI environment is dropped and the workflow runs the default only.
- Resolve every [CHECK] note in the docs, READMEs and context; add
  CONTRIBUTING.md; every tool answers --help and refuses unknown options.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
alexmandClaude committed 2026-10-14 18:58:00 -04:00
1 parent b357af84d8
commit 8c8b51cc3f
89 files changed
+1141 -513
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tools/build.py
+33 -21
View File
@@ -43,10 +43,10 @@ def secret(name):
KEYS = {
"ana": {"name": "Ana Example", "purposes": ["sign"]},
"ben": {"name": "Ben Example", "purposes": ["sign"]},
"ben-spot": {"name": "Ben Example", "purposes": ["spot-check"]},
"cara": {"name": "Cara Example", "purposes": ["sign"]},
"ana": {"name": "Ana Example", "role": "owner", "purposes": ["sign"]},
"ben": {"name": "Ben Example", "role": "editor", "purposes": ["sign"]},
"ben-spot": {"name": "Ben Example", "role": "editor", "purposes": ["spot-check"]},
"cara": {"name": "Cara Example", "role": "reader", "purposes": ["sign"]},
}
TEAM_SECRET = hashlib.sha256(b"manuspec fixture team secret: smithlab").digest()
@@ -54,7 +54,7 @@ TEAM_SECRET = hashlib.sha256(b"manuspec fixture team secret: smithlab").digest()
def roster():
keys = []
for kid, k in KEYS.items():
keys.append({"id": kid, "person": {"name": k["name"]}, "scheme": "ed25519",
keys.append({"id": kid, "person": {"name": k["name"]}, "role": k["role"], "scheme": "ed25519",
"public": base64.b64encode(crypto.ed25519_public(secret(kid))).decode(),
"purposes": k["purposes"], "registered_at": "2026-09-01T00:00:00Z", "revoked_at": None})
return {"format": "scienting-roster/1", "store": STORE, "keys": keys}
@@ -118,9 +118,9 @@ def _math_node(kind, e):
def expand(s, page=None):
page = s.get("page", page)
if isinstance(s, str):
s = {"s": [s]}
page = s.get("page", page)
if "s" in s:
kids = []
n = {"kind": "sentence", "content": runs_of(s["s"], kids), "children": kids}
@@ -565,7 +565,6 @@ def build_hale(out):
anchors = []
for rk, bond, pre in rows:
for st, (kc, rc) in (("A", ("_ak", "_ar")), ("B", ("_bk", "_br"))):
kname = pre + kc.replace("_a", "_a").replace("_b", "_b")
kid, rid = names.ids[pre + kc], names.ids[pre + rc]
kv, rv = norm(hashing.plain(final_doc, kid)), norm(hashing.plain(final_doc, rid))
row_key = rk + "-" + st.lower()
@@ -1007,6 +1006,8 @@ def corrections_vectors():
("insert-text", {"op": "insert", "target": nm["@d"], "run": 0, "offset": 8, "text": "only ", "evidence": crop}),
("insert-text-no-crop", {"op": "insert", "target": nm["@d"], "run": 0, "offset": 8, "text": "only ",
"evidence": person}),
("insert-text-bad-run", {"op": "insert", "target": nm["@d"], "run": 7, "offset": 0, "text": "x",
"evidence": crop}),
("insert-node", {"op": "insert", "parent": nm["@p2"], "place_after": nm["@c"],
"node": {"kind": "sentence", "content": [{"kind": "text", "text": "A dropped sentence."}]},
"evidence": crop}),
@@ -1050,7 +1051,6 @@ def resolve_vectors(hale):
nid = names.ids[a["node"]]
if a.get("container_of"):
nid = d0.nodes[nid]["parent"]
cid = cid
span = None
if "quote" in a:
t = hashing.plain(d0, nid)
@@ -1134,6 +1134,12 @@ def records(out, hale):
return AN.make_anchor(doc, vals, nid, rev, span=span, store=STORE)
wr(out, "roster.json", ROSTER)
# The doubtful reading behind the first correction, as the converter raised it before anyone answered it.
sus = {"format": "scienting-suspect/1", "kind": "number", "node": I["@s4"], "a": "10-3", "b": "10\u22123",
"crop": crop_sha(I["@s4"]),
"note": "The text layer reads a hyphen on the line; the page image shows a raised minus three."}
sus = dict(sus, id=record_id(sha256_hex(jcs.dumpb(sus))))
wr(out, "suspect.json", sus)
wr(out, "anchor-span.json", anchor("@s3", "first test case"))
wr(out, "anchor-cell.json", anchor("@cc_ak"))
wr(out, "anchor-paragraph.json", AN.make_anchor(doc, vals, doc.nodes[I["@s3"]]["parent"], rev, store=STORE))
@@ -1393,9 +1399,8 @@ def records(out, hale):
# --- invalid packages ---------------------------------------------------------------
def invalid(out):
def invalid(out, tiny):
base = os.path.join(out, "fixtures", "invalid")
tiny = tiny_package(None)
files = tiny["files"]
nodes = [json.loads(x) for x in files["nodes.jsonl"].decode().splitlines()]
nm = tiny["names"].ids
@@ -1418,7 +1423,6 @@ def invalid(out):
with open(os.path.join(base, name, "expect.json"), "wb") as fh:
fh.write((jcs.dumps({"rule": rule, "note": note}) + "\n").encode())
write(os.path.join(out, "fixtures", "packages", "tiny2026example"), files)
case("hash-mismatch", "doc.hash.node-hash", {"nodes.jsonl": edit_nodes(lambda ns: by(ns, "@a").update(node_hash="0" * 64))},
"A node_hash that does not recompute.")
case("text-edited", "doc.hash.text-hash", {"nodes.jsonl": edit_nodes(
@@ -1531,16 +1535,24 @@ def main(out):
tiny = tiny_package(os.path.join(out, "fixtures", "packages", "tiny2026example"))
records(out, hale)
vectors(out, hale, tiny)
invalid(out)
invalid(out, tiny)
def cli():
import argparse
ap = argparse.ArgumentParser(
description="Build every fixture and test vector from fixtures/src and the oracle. The build is "
"deterministic, and tools/check.py rebuilds into a temporary folder to prove it.")
ap.add_argument("--out", metavar="DIR", default=ROOT,
help="build into DIR instead of rewriting fixtures/ and vectors/ in this repository")
out = os.path.abspath(ap.parse_args().out)
if out != ROOT:
for sub in ("registry", "fixtures/src"):
dst = os.path.join(out, sub)
if not os.path.exists(dst):
shutil.copytree(os.path.join(ROOT, sub), dst)
main(out)
if __name__ == "__main__":
out = ROOT
if "--out" in sys.argv:
out = sys.argv[sys.argv.index("--out") + 1]
if out != ROOT:
for sub in ("registry", "fixtures/src"):
dst = os.path.join(out, sub)
if not os.path.exists(dst):
shutil.copytree(os.path.join(ROOT, sub), dst)
main(out)
cli()