refactor: move the reference implementation to src/paperspec

The oracle had two import names, `tools.oracle` for the tools and
`paperspec` for other repositories, which could load the same code twice
in one process and needed a gate keyed on the module name. It now lives
in the standard src layout under its one name.

- git mv tools/oracle -> src/paperspec; the 22 rule modules are unchanged.
- The tools import `paperspec`. `tools/__init__.py` now holds the Python
  3.14 and cryptography/jsonschema check and puts src/ first on sys.path,
  so the tools run this checkout's code with or without pixi. The
  package's own __init__ checks nothing and exposes __version__.
- pyproject.toml: version from git tags via setuptools-scm
  (guess-next-dev, node-and-timestamp, src/paperspec/_version.py,
  gitignored). The packages stay listed rather than found because
  schemas/, sql/ and vectors/ stay at the root: the spec links to them and
  the site serves the schemas at their $id URLs.
- pixi.toml: a `dev` feature and environment with setuptools,
  setuptools-scm and python-build, and `pixi run -e dev wheel`.
- check.py scans src/paperspec for rule IDs; README, CONTRIBUTING, the
  FAQ, the overview, the vectors and tools READMEs and the changelog point
  at the new path. The FAQ no longer says the oracle is not a library.

pixi.lock is not re-solved in this commit: with a dynamic version, pixi
builds the package metadata to lock, which needs the conda environment
installed. Run `pixi lock` and commit the result before pushing; the site
workflow installs with --locked.

pixi run check passes; no computed value, vector, fixture, schema or SQL
file changed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
alexmandClaude committed 2026-10-15 09:00:40 -04:00
1 parent 2b4467d315
commit a4eecb4d5b
40 files changed
+134 -84

No files matched your search

-93
View File
@@ -1,93 +0,0 @@
"""Grading a scienting-submission/1 against a scienting-exercise/1 key.
Non-normative; see spec/19-exercises.md.
"""
from decimal import Decimal
from fractions import Fraction
from . import anchors as A
from .tree import Refusal
def dec(d):
"""A decimal string, exactly as the sum came out (spec/19 §19.4: points are decimal strings, summed exactly)."""
return format(Decimal(d), "f")
def _zero_like(d):
"""Zero with the scale of `d`, so a missed element worth "0.5" scores "0.0"."""
return Decimal(0).quantize(Decimal(d))
def _resolved(state, anchor):
r = A.resolve(state, anchor)
if r["result"] == "stale":
return None
return r["node"], r.get("span")
def _match(state, rule, student, key):
s, k = _resolved(state, student), _resolved(state, key)
if not s or not k or s[0] != k[0]:
return False
if rule.get("match") == "overlap" and k[1] is not None:
if s[1] is None:
return True
lo, hi = max(s[1][0], k[1][0]), min(s[1][1], k[1][1])
size = k[1][1] - k[1][0]
return size > 0 and Fraction(max(0, hi - lo), size) >= Fraction(rule.get("min_overlap", "0.5"))
return True
def _any(state, rule, students, keys):
return any(_match(state, rule, s, k) for s in students for k in keys)
def key_anchors(body):
key = body["key"]
out = []
for el in key.get("elements", []) + key.get("chain", []) + key.get("errors", []):
out += el["anchors"]
return out
def grade(body, submission, state):
for a in key_anchors(body):
if A.resolve(state, a)["result"] == "stale":
raise Refusal("grade.key-stale", "an anchor in the key is stale")
kind, key, rule, ans = body["exercise"], body["key"], body.get("rule", {}), submission["answers"]
items = []
def item(name, pts, got, fb):
items.append({"element": name, "points": dec(pts if got else _zero_like(pts)), "max": dec(pts), "feedback": fb})
if kind in ("anchor", "check"):
if kind == "check":
v = key["verdict"]
ok = ans.get("verdict") == v["value"]
item("verdict", v["points"], ok, v.get("feedback", {}).get("hit" if ok else "miss", ""))
for i, el in enumerate(key["elements"]):
ok = _any(state, rule, ans.get("anchors", []), el["anchors"])
item("element:%d" % i, el["points"], ok, el.get("feedback", {}).get("hit" if ok else "miss", ""))
elif kind == "trace":
chain = ans.get("chain", [])
for i, link in enumerate(key["chain"]):
ok = i < len(chain) and _any(state, rule, chain[i], link["anchors"])
item("link:%d" % i, link["points"], ok, link.get("feedback", {}).get("hit" if ok else "miss", ""))
elif kind == "reproduce":
ok = abs(Decimal(ans["value"]) - Decimal(key["value"])) <= Decimal(key["tolerance"])
item("value", key["points"], ok, key.get("feedback", {}).get("hit" if ok else "miss", ""))
elif kind == "verify":
flags = ans.get("flags", [])
for i, err in enumerate(key["errors"]):
hit = [f for f in flags if _any(state, rule, [f["anchor"]], err["anchors"])]
ok = any(f["verdict"] == err["verdict"] for f in hit)
fb = err.get("feedback", {}).get("hit" if ok else "miss", "")
item("error:%d" % i, err["points"], ok, fb)
else:
raise Refusal("grade.kind", "unknown exercise kind " + kind)
score = sum((Decimal(x["points"]) for x in items), Decimal(0))
total = sum((Decimal(x["max"]) for x in items), Decimal(0))
return {"format": "scienting-grade/1", "submission": submission["id"], "exercise": submission["exercise"],
"score": dec(score), "max": dec(total), "items": items}