feat: validator, bundle builder and release checks for 0.1.0
- 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:
89 files changed
+1141
-513
No files matched your search
+25
-146
@@ -1,13 +1,15 @@
|
||||
"""A JSON Schema (draft 2020-12) validator for the subset of keywords the spec's schemas use.
|
||||
"""JSON Schema (draft 2020-12) validation with the `jsonschema` package, and the lint of the keyword subset.
|
||||
|
||||
Non-normative.
|
||||
The spec's schemas are restricted to these keywords (spec/22-conformance.md) so that any 2020-12 validator, and
|
||||
this one, agree; CI also runs the `jsonschema` package when it is installed.
|
||||
The spec's schemas are restricted to the keywords below (spec/22-conformance.md) so that every 2020-12
|
||||
validator reads them alike; `lint` refuses any schema that leaves the subset.
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
|
||||
from jsonschema import Draft202012Validator
|
||||
from referencing import Registry, Resource
|
||||
|
||||
KEYWORDS = {
|
||||
"$schema", "$id", "$ref", "$defs", "$comment", "title", "description", "examples", "default", "deprecated",
|
||||
@@ -24,9 +26,25 @@ class SchemaError(Exception):
|
||||
|
||||
|
||||
class Store:
|
||||
"""The schemas of one folder, linted on load, with a compiled validator per schema."""
|
||||
|
||||
def __init__(self, root):
|
||||
self.root = root
|
||||
self.docs = {}
|
||||
self._registry = None
|
||||
self._validators = {}
|
||||
|
||||
def registry(self):
|
||||
if self._registry is None:
|
||||
names = sorted(f for f in os.listdir(self.root) if f.endswith(".schema.json"))
|
||||
self._registry = Registry().with_resources(
|
||||
[(self.load(f)["$id"], Resource.from_contents(self.load(f))) for f in names])
|
||||
return self._registry
|
||||
|
||||
def validator(self, name):
|
||||
if name not in self._validators:
|
||||
self._validators[name] = Draft202012Validator(self.load(name), registry=self.registry())
|
||||
return self._validators[name]
|
||||
|
||||
def load(self, name):
|
||||
if name not in self.docs:
|
||||
@@ -65,146 +83,7 @@ def lint(schema, where):
|
||||
lint(s, "%s/%s/%d" % (where, k, i))
|
||||
|
||||
|
||||
def _type_ok(t, x):
|
||||
if t == "null":
|
||||
return x is None
|
||||
if t == "boolean":
|
||||
return isinstance(x, bool)
|
||||
if t == "integer":
|
||||
return isinstance(x, int) and not isinstance(x, bool)
|
||||
if t == "number":
|
||||
return isinstance(x, (int, float)) and not isinstance(x, bool)
|
||||
if t == "string":
|
||||
return isinstance(x, str)
|
||||
if t == "array":
|
||||
return isinstance(x, list)
|
||||
if t == "object":
|
||||
return isinstance(x, dict)
|
||||
raise SchemaError("unknown type " + t)
|
||||
|
||||
|
||||
def _equal(a, b):
|
||||
if isinstance(a, bool) or isinstance(b, bool):
|
||||
return type(a) is type(b) and a == b
|
||||
return a == b
|
||||
|
||||
|
||||
def validate(store, name, instance):
|
||||
"""Return a list of error strings; empty when the instance is valid."""
|
||||
schema = store.load(name)
|
||||
errors = []
|
||||
_v(store, name, schema, instance, "", errors)
|
||||
return errors
|
||||
|
||||
|
||||
def _v(store, base, s, x, path, errors):
|
||||
if s is True:
|
||||
return
|
||||
if s is False:
|
||||
errors.append(path + ": not allowed")
|
||||
return
|
||||
if "$ref" in s:
|
||||
b2, target = store.deref(base, s["$ref"])
|
||||
_v(store, b2, target, x, path, errors)
|
||||
if "type" in s:
|
||||
ts = s["type"] if isinstance(s["type"], list) else [s["type"]]
|
||||
if not any(_type_ok(t, x) for t in ts):
|
||||
errors.append("%s: expected %s" % (path or "/", "/".join(ts)))
|
||||
return
|
||||
if "const" in s and not _equal(s["const"], x):
|
||||
errors.append("%s: expected %r" % (path or "/", s["const"]))
|
||||
if "enum" in s and not any(_equal(e, x) for e in s["enum"]):
|
||||
errors.append("%s: %r is not one of %r" % (path or "/", x, s["enum"]))
|
||||
if isinstance(x, str):
|
||||
if "minLength" in s and len(x) < s["minLength"]:
|
||||
errors.append("%s: shorter than %d" % (path, s["minLength"]))
|
||||
if "maxLength" in s and len(x) > s["maxLength"]:
|
||||
errors.append("%s: longer than %d" % (path, s["maxLength"]))
|
||||
if "pattern" in s and not re.search(s["pattern"], x):
|
||||
errors.append("%s: %r does not match %s" % (path, x, s["pattern"]))
|
||||
if isinstance(x, (int, float)) and not isinstance(x, bool):
|
||||
if "minimum" in s and x < s["minimum"]:
|
||||
errors.append("%s: below %s" % (path, s["minimum"]))
|
||||
if "maximum" in s and x > s["maximum"]:
|
||||
errors.append("%s: above %s" % (path, s["maximum"]))
|
||||
if "exclusiveMinimum" in s and x <= s["exclusiveMinimum"]:
|
||||
errors.append("%s: not above %s" % (path, s["exclusiveMinimum"]))
|
||||
if "exclusiveMaximum" in s and x >= s["exclusiveMaximum"]:
|
||||
errors.append("%s: not below %s" % (path, s["exclusiveMaximum"]))
|
||||
if isinstance(x, list):
|
||||
if "minItems" in s and len(x) < s["minItems"]:
|
||||
errors.append("%s: fewer than %d items" % (path, s["minItems"]))
|
||||
if "maxItems" in s and len(x) > s["maxItems"]:
|
||||
errors.append("%s: more than %d items" % (path, s["maxItems"]))
|
||||
if s.get("uniqueItems"):
|
||||
seen = [json.dumps(i, sort_keys=True) for i in x]
|
||||
if len(seen) != len(set(seen)):
|
||||
errors.append("%s: items are not unique" % path)
|
||||
pre = s.get("prefixItems", [])
|
||||
for i, item in enumerate(x):
|
||||
if i < len(pre):
|
||||
_v(store, base, pre[i], item, "%s/%d" % (path, i), errors)
|
||||
elif "items" in s:
|
||||
_v(store, base, s["items"], item, "%s/%d" % (path, i), errors)
|
||||
if "contains" in s:
|
||||
if not any(not _sub(store, base, s["contains"], i) for i in x):
|
||||
errors.append("%s: no item matches `contains`" % path)
|
||||
if isinstance(x, dict):
|
||||
if "minProperties" in s and len(x) < s["minProperties"]:
|
||||
errors.append("%s: fewer than %d properties" % (path, s["minProperties"]))
|
||||
if "maxProperties" in s and len(x) > s["maxProperties"]:
|
||||
errors.append("%s: more than %d properties" % (path, s["maxProperties"]))
|
||||
for r in s.get("required", []):
|
||||
if r not in x:
|
||||
errors.append("%s: missing %s" % (path or "/", r))
|
||||
for k, deps in s.get("dependentRequired", {}).items():
|
||||
if k in x:
|
||||
for d in deps:
|
||||
if d not in x:
|
||||
errors.append("%s: %s requires %s" % (path or "/", k, d))
|
||||
props = s.get("properties", {})
|
||||
pprops = s.get("patternProperties", {})
|
||||
for k, v in x.items():
|
||||
matched = False
|
||||
if k in props:
|
||||
matched = True
|
||||
_v(store, base, props[k], v, path + "/" + k, errors)
|
||||
for pat, ps in pprops.items():
|
||||
if re.search(pat, k):
|
||||
matched = True
|
||||
_v(store, base, ps, v, path + "/" + k, errors)
|
||||
if not matched and "additionalProperties" in s:
|
||||
ap = s["additionalProperties"]
|
||||
if ap is False:
|
||||
errors.append("%s: unexpected property %s" % (path or "/", k))
|
||||
else:
|
||||
_v(store, base, ap, v, path + "/" + k, errors)
|
||||
if "propertyNames" in s:
|
||||
_v(store, base, s["propertyNames"], k, path + "/" + k, errors)
|
||||
for sub in s.get("allOf", []):
|
||||
_v(store, base, sub, x, path, errors)
|
||||
if "anyOf" in s:
|
||||
if all(_sub(store, base, sub, x) for sub in s["anyOf"]):
|
||||
errors.append("%s: matches none of anyOf" % (path or "/"))
|
||||
if "oneOf" in s:
|
||||
ok = [sub for sub in s["oneOf"] if not _sub(store, base, sub, x)]
|
||||
if len(ok) != 1:
|
||||
detail = ""
|
||||
if not ok:
|
||||
best = min((_sub(store, base, sub, x) for sub in s["oneOf"]), key=len)
|
||||
detail = " (closest: %s)" % "; ".join(best[:3])
|
||||
errors.append("%s: matches %d of oneOf%s" % (path or "/", len(ok), detail))
|
||||
if "not" in s and not _sub(store, base, s["not"], x):
|
||||
errors.append("%s: matches `not`" % (path or "/"))
|
||||
if "if" in s:
|
||||
if not _sub(store, base, s["if"], x):
|
||||
if "then" in s:
|
||||
_v(store, base, s["then"], x, path, errors)
|
||||
elif "else" in s:
|
||||
_v(store, base, s["else"], x, path, errors)
|
||||
|
||||
|
||||
def _sub(store, base, s, x):
|
||||
e = []
|
||||
_v(store, base, s, x, "", e)
|
||||
return e
|
||||
"""Return a list of error strings, `path: message`, in path order; empty when the instance is valid."""
|
||||
errors = sorted(store.validator(name).iter_errors(instance), key=lambda e: [str(x) for x in e.absolute_path])
|
||||
return ["%s: %s" % ("/" + "/".join(str(x) for x in e.absolute_path), e.message) for e in errors]
|
||||
Reference in new issue
Block a user