Add paperspec correct, check math forms and datasets, and give the tools public names

The work the other paper tools planned for paperspec (paperdesk PLAN M5.4,
paperform PLAN 4.2):

- paperspec correct and paperspec.revision apply proposed corrections to a
  package, folder or zip, and write it only once it validates.
- doc.math.form is checked: label and style commands always, the form's own
  spelling when papermath is installed or forms= is passed.
- paperspec.datasets and seven doc.dataset.* rules check a package's datasets.
- fixtures/invalid gains suspect-witness and math-form-label (33 in all).
- Canonical JSON reads numbers as doubles, so 1e20 round-trips.
- The registries and the JSON-LD context ship in the wheel.
- Public names for what paperdesk and paperform imported as private ones,
  with the old names kept as aliases.
- The text and lossy-projection functions are about three times faster
  through the gate, tested equal to the old code on every code point.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013XwDhn4LkrKQfw4ArDEr2E
This commit is contained in:
alexmandClaude committed 2026-10-20 22:10:17 -04:00
1 parent 8c07dd7c15
commit 4fb8b4f5a7
70 files changed
+4470 -270

No files matched your search

+203
View File
@@ -0,0 +1,203 @@
# SPDX-License-Identifier: Apache-2.0
# Copyright 2026 Scienting
#
# Source Code: https://git.scient.ing/papers/paperspec
# See the LICENSE.md file for full license terms.
"""Claim references and pins (spec/18 §18.4)."""
import json
import re
import pytest
from hypothesis import given, settings, strategies as st
from conftest import FIXTURES, ROOT
from paperspec import claims
PROPERTIES = settings(derandomize=True, max_examples=200, database=None, deadline=None)
SCHEMA = json.loads((ROOT / "schemas" / "common.schema.json").read_text("utf-8"))
# ECMAScript `$` matches only at the end; Python's also matches before a final newline.
REF_PATTERN = SCHEMA["$defs"]["claimRef"]["pattern"].removesuffix("$") + r"\Z"
PIN_PATTERN = SCHEMA["$defs"]["claimPin"]["pattern"].removesuffix("$") + r"\Z"
TAGS = st.text(alphabet="0123456789ABCDEFGHJKMNPQRSTVWXYZ", min_size=8, max_size=8)
HOSTS = st.one_of(
st.none(),
st.from_regex(r"[a-z0-9][a-z0-9-]{0,8}\.[a-z]{2,6}", fullmatch=True),
)
HASHES = st.text(alphabet="0123456789abcdef", min_size=64, max_size=64)
def _fixture_texts() -> list[str]:
found = set()
for path in FIXTURES.rglob("*"):
if path.is_file():
text = path.read_text("utf-8", errors="ignore")
found.update(re.findall(r"claim:[A-Za-z0-9./@_-]+", text))
return sorted(found)
def test_the_patterns_are_those_of_the_schema():
schema_ref, schema_pin = re.compile(REF_PATTERN), re.compile(PIN_PATTERN)
samples = [
"claim:272XTX7C",
"claim:272XTX7C@02f47b",
"claim:example.org/272XTX7C",
"claim:example.org/272XTX7C@02f47b",
"claim:272XTX7I",
"claim:272xtx7c",
"claim:272XTX7",
"claim:272XTX7C@02F47B",
"claim:localhost/272XTX7C",
"claim:a.b/272XTX7C@02f47",
"claim:272XTX7C ",
"claim:272XTX7C\n",
]
for s in samples:
assert bool(claims.CLAIM_REF_RE.match(s)) == bool(schema_ref.match(s)), s
assert bool(claims.CLAIM_PIN_RE.match(s)) == bool(schema_pin.match(s)), s
@given(st.from_regex(REF_PATTERN) | st.from_regex(PIN_PATTERN) | st.text(max_size=30))
@PROPERTIES
def test_the_patterns_agree_with_the_schema_on_any_text(s):
assert bool(claims.CLAIM_REF_RE.match(s)) == bool(re.match(REF_PATTERN, s))
assert bool(claims.CLAIM_PIN_RE.match(s)) == bool(re.match(PIN_PATTERN, s))
def test_the_fixtures_hold_claim_references_and_pins():
texts = _fixture_texts()
assert any("@" in t for t in texts)
assert any("@" not in t for t in texts)
@pytest.mark.parametrize("text", _fixture_texts())
def test_a_fixture_claim_parses_and_formats_back(text):
pin = claims.parse_pin(text)
if "@" in text:
assert pin is not None
assert claims.parse_ref(text) is None
assert pin["ref"] + "@" + pin["pin"] == text
else:
ref = claims.parse_ref(text)
assert ref is not None
assert claims.format_ref(ref["tag"], ref["host"]) == text
assert pin is None
def test_a_reference_has_a_tag_and_no_host_for_the_local_store():
assert claims.parse_ref("claim:272XTX7C") == {"host": None, "tag": "272XTX7C"}
def test_a_reference_to_another_store_has_its_host():
assert claims.parse_ref("claim:claims.example.org/272XTX7C") == {
"host": "claims.example.org",
"tag": "272XTX7C",
}
def test_a_pin_splits_into_reference_tag_and_pin():
assert claims.parse_pin("claim:a.org/272XTX7C@02f47b") == {
"ref": "claim:a.org/272XTX7C",
"host": "a.org",
"tag": "272XTX7C",
"pin": "02f47b",
}
@pytest.mark.parametrize(
"text",
[
"",
"272XTX7C",
"claim:",
"claim:272XTX7",
"claim:272XTX7CC",
"claim:272xtx7c",
"claim:272XTX7U",
"claim:272XTX7L",
"claim:272XTX7I",
"claim:272XTX7O",
"claim:localhost/272XTX7C",
"claim:Example.org/272XTX7C",
"claim:amber/k-bond",
"claim:272XTX7C@02f47b ",
"claim:272XTX7C\n",
],
)
def test_text_that_is_not_a_reference_does_not_parse(text):
assert claims.parse_ref(text) is None
@pytest.mark.parametrize(
"text",
[
"claim:272XTX7C",
"claim:272XTX7C@",
"claim:272XTX7C@02f47",
"claim:272XTX7C@02f47b0",
"claim:272XTX7C@02F47B",
"claim:272XTX7C@02f47g",
"272XTX7C@02f47b",
"claim:272XTX7C@02f47b\n",
],
)
def test_text_that_is_not_a_pin_does_not_parse(text):
assert claims.parse_pin(text) is None
def test_a_reference_is_not_a_pin_and_a_pin_is_not_a_reference():
assert claims.parse_pin("claim:272XTX7C") is None
assert claims.parse_ref("claim:272XTX7C@02f47b") is None
def test_format_ref_writes_the_local_and_the_hosted_form():
assert claims.format_ref("272XTX7C") == "claim:272XTX7C"
assert claims.format_ref("272XTX7C", "a.org") == "claim:a.org/272XTX7C"
assert claims.format_ref("272XTX7C", host="") == "claim:272XTX7C"
@pytest.mark.parametrize(
("tag", "host"), [("short", None), ("272xtx7c", None), ("272XTX7C", "nodot")]
)
def test_format_ref_refuses_what_is_not_a_reference(tag, host):
with pytest.raises(ValueError, match="not a claim reference"):
claims.format_ref(tag, host)
def test_format_pin_keeps_the_first_six_digits_of_the_hash():
digest = "02f47b" + "0" * 58
assert claims.format_pin("claim:272XTX7C", digest) == "claim:272XTX7C@02f47b"
def test_format_pin_refuses_a_bad_reference_or_hash():
with pytest.raises(ValueError, match="not a claim reference"):
claims.format_pin("claim:nope", "0" * 64)
with pytest.raises(ValueError, match="64 lowercase hex"):
claims.format_pin("claim:272XTX7C", "02f47b")
with pytest.raises(ValueError, match="64 lowercase hex"):
claims.format_pin("claim:272XTX7C", "A" * 64)
@given(TAGS, HOSTS)
@PROPERTIES
def test_a_formatted_reference_parses_back(tag, host):
ref = claims.format_ref(tag, host)
assert claims.parse_ref(ref) == {"host": host, "tag": tag}
assert re.match(REF_PATTERN, ref)
@given(TAGS, HOSTS, HASHES)
@PROPERTIES
def test_a_formatted_pin_parses_back(tag, host, digest):
ref = claims.format_ref(tag, host)
pin = claims.format_pin(ref, digest)
assert claims.parse_pin(pin) == {
"ref": ref,
"host": host,
"tag": tag,
"pin": digest[:6],
}
assert re.match(PIN_PATTERN, pin)