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

+15 -14
View File
@@ -20,21 +20,22 @@ from fractions import Fraction
ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.insert(0, ROOT)
import tools # noqa: E402,F401 checks the runtime and puts src/ first on the path, before paperspec is imported
from tools.oracle import align as AL # noqa: E402
from tools.oracle import anchors as AN # noqa: E402
from tools.oracle import corrections as CO # noqa: E402
from tools.oracle import crypto, db, fingerprint as FP, grade as GR, hashing, jcs, receipts as RC, rights as RI # noqa: E402
from tools.oracle import package as PK # noqa: E402
from tools.oracle import keys as K, log as LG, mldsa, targets as TG, vrf # noqa: E402
from paperspec import align as AL # noqa: E402
from paperspec import anchors as AN # noqa: E402
from paperspec import corrections as CO # noqa: E402
from paperspec import crypto, db, fingerprint as FP, grade as GR, hashing, jcs, receipts as RC, rights as RI # noqa: E402
from paperspec import package as PK # noqa: E402
from paperspec import keys as K, log as LG, mldsa, targets as TG, vrf # noqa: E402
import unicodedata # noqa: E402
from tools.oracle.model import Doc # noqa: E402
from tools.oracle.notation import fold_math # noqa: E402
from tools.oracle.schema import Store, validate as sv # noqa: E402
from paperspec.model import Doc # noqa: E402
from paperspec.notation import fold_math # noqa: E402
from paperspec.schema import Store, validate as sv # noqa: E402
from jsonschema import Draft202012Validator # noqa: E402
from jsonschema.exceptions import SchemaError # noqa: E402
from tools.oracle.text import cp_to_utf16, letter_first, mint_node_id, norm, record_id, sha256_hex # noqa: E402
from tools.oracle.tree import Refusal # noqa: E402
from paperspec.text import cp_to_utf16, letter_first, mint_node_id, norm, record_id, sha256_hex # noqa: E402
from paperspec.tree import Refusal # noqa: E402
FAILS = []
# Folders that are not part of the repository: version control, environments and caches.
@@ -111,11 +112,11 @@ def check_registry():
for rule in js(p("registry", "stamps", "scienting-stamps-1.json"))["rules"]:
re.compile(rule["pattern"])
rules = {r["id"] for r in js(p("registry", "rules.json"))["rules"]}
for f in sorted(os.listdir(p("tools", "oracle"))):
for f in sorted(os.listdir(p("src", "paperspec"))):
if f.endswith(".py"):
for rule in re.findall(r'(?:Refusal|rep\.add)\(\s*"([a-z][a-z0-9.-]+)"', open(p("tools", "oracle", f)).read()):
for rule in re.findall(r'(?:Refusal|rep\.add)\(\s*"([a-z][a-z0-9.-]+)"', open(p("src", "paperspec", f)).read()):
if not rule.endswith("."):
ok("registry", rule in rules, "tools/oracle/%s raises %s, which is not in rules.json" % (f, rule))
ok("registry", rule in rules, "src/paperspec/%s raises %s, which is not in rules.json" % (f, rule))
for v in ("text-hash", "match-hash", "align-key", "own-hash", "node-hash"):
ok("registry", "doc.hash." + v in rules, "doc.hash.%s is not in rules.json" % v)
# The character data the hashes depend on is pinned to one Unicode version (spec/01 §1.4).