alexmandClaude
a4eecb4d5b
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>
92 lines
3.8 KiB
Python
Executable File
92 lines
3.8 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Validate packages, or run the correction gate on proposals against a package.
|
|
|
|
Non-normative tooling.
|
|
Usage: python3 tools/validate.py PACKAGE [PACKAGE ...]
|
|
python3 tools/validate.py --correction PROPOSALS PACKAGE
|
|
A package is a folder, or a zipped package (`.sct.zip`), which is unpacked under the rules of spec/12 §12.2
|
|
before it is checked. Each is checked as spec/22 §22.2 describes, and each failure printed as
|
|
`package: where: rule: message`.
|
|
With --correction, PROPOSALS is a JSON file holding one proposed correction, or a JSON Lines file of several
|
|
applied in order. Each runs through the gate (spec/11 §11.4) against the package's current state, and the record
|
|
it would append to corrections.jsonl is printed, until one is refused. Nothing is written.
|
|
Exit status: 0 when everything is valid, 1 when something is refused, 2 for a usage error.
|
|
"""
|
|
|
|
import argparse
|
|
import json
|
|
import os
|
|
import sys
|
|
import tempfile
|
|
|
|
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 paperspec import corrections, jcs, package # noqa: E402
|
|
from paperspec.schema import Store # noqa: E402
|
|
from paperspec.tree import Refusal # noqa: E402
|
|
|
|
|
|
def read_proposals(path):
|
|
with open(path, encoding="utf-8") as f:
|
|
text = f.read()
|
|
try:
|
|
return [json.loads(text)]
|
|
except json.JSONDecodeError:
|
|
return [json.loads(ln) for ln in text.splitlines() if ln.strip()]
|
|
|
|
|
|
def validate_one(path, store, limit):
|
|
"""The validation report of a package folder or a zipped package."""
|
|
if package.is_zip(path):
|
|
return package.validate_zip(path, store, limit=limit)
|
|
return package.validate(path, store)
|
|
|
|
|
|
def main():
|
|
lines = __doc__.splitlines()
|
|
ap = argparse.ArgumentParser(description=lines[0], epilog="\n".join(lines[5:]),
|
|
formatter_class=argparse.RawDescriptionHelpFormatter)
|
|
ap.add_argument("--correction", metavar="PROPOSALS",
|
|
help="a JSON or JSON Lines file of proposed corrections to run through the gate")
|
|
ap.add_argument("--max-size", metavar="BYTES", type=int, default=package.ZIP_LIMIT,
|
|
help="refuse a zipped package that expands past this many bytes (default %d)" % package.ZIP_LIMIT)
|
|
ap.add_argument("packages", nargs="+", metavar="PACKAGE", help="package folders or zipped packages")
|
|
a = ap.parse_args()
|
|
if a.correction and len(a.packages) != 1:
|
|
ap.error("--correction checks proposals against exactly one package")
|
|
store, bad = Store(os.path.join(ROOT, "schemas")), False
|
|
for p in a.packages:
|
|
for e in validate_one(p, store, a.max_size).errors:
|
|
print("%s: %s: %s: %s" % (p, e["where"], e["rule"], e["message"]), file=sys.stderr)
|
|
bad = True
|
|
if bad:
|
|
return 1
|
|
if not a.correction:
|
|
for p in a.packages:
|
|
print("%s: valid" % p)
|
|
return 0
|
|
pkg = a.packages[0]
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
if package.is_zip(pkg):
|
|
pkg = package.read_zip(pkg, tmp, a.max_size)
|
|
state = package.read_state(pkg)
|
|
if any(n.get("withheld") for n in state.nodes):
|
|
print("%s: doc.policy.withheld: a package that withholds its text takes no corrections" % a.packages[0],
|
|
file=sys.stderr)
|
|
return 1
|
|
for i, proposal in enumerate(read_proposals(a.correction), 1):
|
|
try:
|
|
state, record = corrections.gate(state, proposal, store)
|
|
except Refusal as e:
|
|
where = "%s:%d" % (a.correction, i) + (" " + e.node if e.node else "")
|
|
print("%s: %s: %s" % (where, e.rule, e.message), file=sys.stderr)
|
|
return 1
|
|
print(jcs.dumps(record))
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|