fix(data): make catalog snapshot hashes line-ending independent (#478)

* fix(data): regenerate stale catalog-summary snapshot hashes

catalog-summary.json was not regenerated after google-fonts.csv,
google-font-licenses.json, icons.csv and phosphor-icons-upstream.json
changed, so `npm --prefix cli run verify:data` fails on a clean
checkout of main:

  validate:semantic          4 stale snapshot errors
  validate:catalog-summary   "catalog-summary.json is stale"
  test:python                1 failure / 153
  check:assets               2 files out of sync

Regenerated with the existing --verified-at 2026-08-26: only the four
sha256 fields change. The date is a human attestation that the font
catalog was checked against the upstream google/fonts repository, so it
is deliberately left untouched -- no such verification was performed
here.

verify:data now exits 0.

Note: prepublishOnly runs sync:assets before verify:data, which
regenerates the snapshot at publish time. That is why released packages
are unaffected and the drift stayed invisible on main.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015UidECV1wVBD8SW6Abuj71

* fix(data): make catalog snapshot hashes line-ending independent

Root cause of the stale snapshot restored in the previous commit.

bd19ab9 (#462) regenerated catalog-summary.json from a CRLF checkout.
Every recorded sha256 was the CRLF hash of its source file, so the
check failed on every LF platform. The four committed values are
exactly sha256(crlf_bytes):

  google-fonts.csv              committed d03194d2…  = CRLF hash
  google-font-licenses.json     committed 7c35e410…  = CRLF hash
  icons.csv                     committed 272ccf0e…  = CRLF hash
  phosphor-icons-upstream.json  committed 81c37fb3…  = CRLF hash

Two conditions had to combine: the digest hashed raw bytes, and no
.gitattributes pinned these files to LF, so Windows checkouts get CRLF
by default. Restoring the hashes alone would let the next contributor
on Windows reproduce the same commit.

Three changes:

- normalize line endings in generate-catalog-summary.py's digest(), so
  the snapshot no longer depends on the checkout
- apply the same normalization in validate_data.py, which independently
  recomputes the hashes and has to agree with the generator
- add .gitattributes pinning src/ui-ux-pro-max/data/*.{csv,json} to LF,
  so a Windows checkout matches the committed bytes in the first place

sync-assets.mjs already normalizes to LF, so this only extends an
existing project convention to the two places that were missing it.

Adds test_catalog_summary_line_endings.py: LF and CRLF inputs must
digest identically, the committed snapshot must match the normalized
sources, and a simulated CRLF checkout must still produce the recorded
hashes. The third case fails against the pre-fix digest.

verify:data exits 0; the Python suite goes from 153 to 156 tests.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015UidECV1wVBD8SW6Abuj71

---------

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
speedy75015-crypto 2026-09-02 09:14:59 +02:00 committed by GitHub
parent 40d8b6facf
commit e2effd5775
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
11 changed files with 264 additions and 10 deletions

View File

@ -1,6 +1,6 @@
{
"schemaVersion": 1,
"verifiedAt": "2026-08-13",
"verifiedAt": "2026-08-26",
"counts": {
"styles": {
"total": 88,

View File

@ -0,0 +1,78 @@
#!/usr/bin/env python3
"""The catalog snapshot must not depend on the checkout's line endings.
Regression test for bd19ab9 (#462), where catalog-summary.json was regenerated
on a CRLF checkout. Every recorded sha256 was the CRLF hash of the source file,
so `verify:data` failed on every LF platform, including CI.
"""
import hashlib
import importlib.util
import json
import shutil
import tempfile
import unittest
from pathlib import Path
REPO = next(
parent for parent in Path(__file__).resolve().parents
if (parent / "scripts" / "generate-catalog-summary.py").is_file()
)
DATA = REPO / "src/ui-ux-pro-max/data"
SNAPSHOT_FILES = (
"google-fonts.csv",
"google-font-licenses.json",
"icons.csv",
"phosphor-icons-upstream.json",
)
def _load_generator():
path = REPO / "scripts" / "generate-catalog-summary.py"
spec = importlib.util.spec_from_file_location("generate_catalog_summary", path)
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return module
class CatalogSummaryLineEndingsTest(unittest.TestCase):
def test_digest_is_identical_for_lf_and_crlf(self):
digest = _load_generator().digest
with tempfile.TemporaryDirectory() as tmp:
lf = Path(tmp) / "lf.csv"
crlf = Path(tmp) / "crlf.csv"
lf.write_bytes(b"id,name\n1,alpha\n2,beta\n")
crlf.write_bytes(b"id,name\r\n1,alpha\r\n2,beta\r\n")
self.assertEqual(
digest(lf), digest(crlf),
"snapshot hashes must not change with the checkout's line endings",
)
def test_committed_snapshot_matches_normalized_sources(self):
summary = json.loads((DATA / "catalog-summary.json").read_text(encoding="utf-8"))
for name in SNAPSHOT_FILES:
expected = hashlib.sha256(
(DATA / name).read_bytes().replace(b"\r\n", b"\n")
).hexdigest()
self.assertEqual(
summary["snapshots"][name]["sha256"], expected,
f"{name}: committed snapshot hash does not match the LF-normalized source",
)
def test_crlf_checkout_produces_the_committed_hashes(self):
"""Simulate a Windows checkout: the recorded hashes must still validate."""
digest = _load_generator().digest
summary = json.loads((DATA / "catalog-summary.json").read_text(encoding="utf-8"))
with tempfile.TemporaryDirectory() as tmp:
for name in SNAPSHOT_FILES:
crlf_copy = Path(tmp) / name
raw = (DATA / name).read_bytes().replace(b"\r\n", b"\n")
crlf_copy.write_bytes(raw.replace(b"\n", b"\r\n"))
self.assertEqual(
digest(crlf_copy), summary["snapshots"][name]["sha256"],
f"{name}: a CRLF checkout would record a different hash",
)
if __name__ == "__main__":
unittest.main()

View File

@ -663,7 +663,11 @@ def _check_catalog_summary(summary, licenses, phosphor, problems):
problems.append(f"[catalog:summary] stale count for {key}")
snapshots = summary.get("snapshots") if isinstance(summary.get("snapshots"), dict) else {}
for name in ("google-fonts.csv", "google-font-licenses.json", "icons.csv", "phosphor-icons-upstream.json"):
digest = hashlib.sha256((DATA_DIR / name).read_bytes()).hexdigest()
# Line endings are normalized so the check matches
# generate-catalog-summary.py on CRLF checkouts too.
digest = hashlib.sha256(
(DATA_DIR / name).read_bytes().replace(b"\r\n", b"\n")
).hexdigest()
if snapshots.get(name) != {"sha256": digest}:
problems.append(f"[catalog:summary] stale snapshot for {name}")
policy = summary.get("promotionPolicy")

6
.gitattributes vendored Normal file
View File

@ -0,0 +1,6 @@
# catalog-summary.json records sha256 hashes of the files below, computed over
# their bytes. A CRLF checkout therefore produces different hashes than an LF
# one, which makes `verify:data` fail on every other platform (see #462/#478).
# Pin these files to LF so the snapshot is reproducible everywhere.
src/ui-ux-pro-max/data/*.csv text eol=lf
src/ui-ux-pro-max/data/*.json text eol=lf

View File

@ -1,6 +1,6 @@
{
"schemaVersion": 1,
"verifiedAt": "2026-08-13",
"verifiedAt": "2026-08-26",
"counts": {
"styles": {
"total": 88,

View File

@ -0,0 +1,78 @@
#!/usr/bin/env python3
"""The catalog snapshot must not depend on the checkout's line endings.
Regression test for bd19ab9 (#462), where catalog-summary.json was regenerated
on a CRLF checkout. Every recorded sha256 was the CRLF hash of the source file,
so `verify:data` failed on every LF platform, including CI.
"""
import hashlib
import importlib.util
import json
import shutil
import tempfile
import unittest
from pathlib import Path
REPO = next(
parent for parent in Path(__file__).resolve().parents
if (parent / "scripts" / "generate-catalog-summary.py").is_file()
)
DATA = REPO / "src/ui-ux-pro-max/data"
SNAPSHOT_FILES = (
"google-fonts.csv",
"google-font-licenses.json",
"icons.csv",
"phosphor-icons-upstream.json",
)
def _load_generator():
path = REPO / "scripts" / "generate-catalog-summary.py"
spec = importlib.util.spec_from_file_location("generate_catalog_summary", path)
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return module
class CatalogSummaryLineEndingsTest(unittest.TestCase):
def test_digest_is_identical_for_lf_and_crlf(self):
digest = _load_generator().digest
with tempfile.TemporaryDirectory() as tmp:
lf = Path(tmp) / "lf.csv"
crlf = Path(tmp) / "crlf.csv"
lf.write_bytes(b"id,name\n1,alpha\n2,beta\n")
crlf.write_bytes(b"id,name\r\n1,alpha\r\n2,beta\r\n")
self.assertEqual(
digest(lf), digest(crlf),
"snapshot hashes must not change with the checkout's line endings",
)
def test_committed_snapshot_matches_normalized_sources(self):
summary = json.loads((DATA / "catalog-summary.json").read_text(encoding="utf-8"))
for name in SNAPSHOT_FILES:
expected = hashlib.sha256(
(DATA / name).read_bytes().replace(b"\r\n", b"\n")
).hexdigest()
self.assertEqual(
summary["snapshots"][name]["sha256"], expected,
f"{name}: committed snapshot hash does not match the LF-normalized source",
)
def test_crlf_checkout_produces_the_committed_hashes(self):
"""Simulate a Windows checkout: the recorded hashes must still validate."""
digest = _load_generator().digest
summary = json.loads((DATA / "catalog-summary.json").read_text(encoding="utf-8"))
with tempfile.TemporaryDirectory() as tmp:
for name in SNAPSHOT_FILES:
crlf_copy = Path(tmp) / name
raw = (DATA / name).read_bytes().replace(b"\r\n", b"\n")
crlf_copy.write_bytes(raw.replace(b"\n", b"\r\n"))
self.assertEqual(
digest(crlf_copy), summary["snapshots"][name]["sha256"],
f"{name}: a CRLF checkout would record a different hash",
)
if __name__ == "__main__":
unittest.main()

View File

@ -663,7 +663,11 @@ def _check_catalog_summary(summary, licenses, phosphor, problems):
problems.append(f"[catalog:summary] stale count for {key}")
snapshots = summary.get("snapshots") if isinstance(summary.get("snapshots"), dict) else {}
for name in ("google-fonts.csv", "google-font-licenses.json", "icons.csv", "phosphor-icons-upstream.json"):
digest = hashlib.sha256((DATA_DIR / name).read_bytes()).hexdigest()
# Line endings are normalized so the check matches
# generate-catalog-summary.py on CRLF checkouts too.
digest = hashlib.sha256(
(DATA_DIR / name).read_bytes().replace(b"\r\n", b"\n")
).hexdigest()
if snapshots.get(name) != {"sha256": digest}:
problems.append(f"[catalog:summary] stale snapshot for {name}")
policy = summary.get("promotionPolicy")

View File

@ -20,7 +20,9 @@ def rows(name):
def digest(path):
return hashlib.sha256(path.read_bytes()).hexdigest()
# Normalize line endings so the snapshot does not depend on whether the
# working tree was checked out with LF or CRLF.
return hashlib.sha256(path.read_bytes().replace(b"\r\n", b"\n")).hexdigest()
def load_json(name):

View File

@ -24,16 +24,16 @@
},
"snapshots": {
"google-fonts.csv": {
"sha256": "d03194d2c35a2cdc4c6846ddde9beb54fdd1f81a3ddc80fead3c0ba2842b75fb"
"sha256": "1c8c3b2ea1faf6a1012da463756def8b3889db33f2226f0343bb4daa80307d03"
},
"google-font-licenses.json": {
"sha256": "7c35e410dd8b5853ca86c3e0e3d3cfb73db1ffa3d9a2fa688c182bc44cd9a8d7"
"sha256": "35688523f2955795caa1a47c53b83099e60c1708461476f9cc3a050cf3b0148a"
},
"icons.csv": {
"sha256": "272ccf0eb60e50ba7af55de3ef5c195d92e1862d411b6cb80d81dec4fe56deee"
"sha256": "50816c6012030178195a16ee481ebf58b47bd985d70e8ec58886cc83f6eddafc"
},
"phosphor-icons-upstream.json": {
"sha256": "81c37fb3583eb43a91e93f1a62c4da3b4ff089624c06bfe53950b8205b54974d"
"sha256": "2399325233b277b5c97a80e6a5e8941154f5d057beee4e7613db87c87d700236"
}
},
"promotionPolicy": {

View File

@ -0,0 +1,78 @@
#!/usr/bin/env python3
"""The catalog snapshot must not depend on the checkout's line endings.
Regression test for bd19ab9 (#462), where catalog-summary.json was regenerated
on a CRLF checkout. Every recorded sha256 was the CRLF hash of the source file,
so `verify:data` failed on every LF platform, including CI.
"""
import hashlib
import importlib.util
import json
import shutil
import tempfile
import unittest
from pathlib import Path
REPO = next(
parent for parent in Path(__file__).resolve().parents
if (parent / "scripts" / "generate-catalog-summary.py").is_file()
)
DATA = REPO / "src/ui-ux-pro-max/data"
SNAPSHOT_FILES = (
"google-fonts.csv",
"google-font-licenses.json",
"icons.csv",
"phosphor-icons-upstream.json",
)
def _load_generator():
path = REPO / "scripts" / "generate-catalog-summary.py"
spec = importlib.util.spec_from_file_location("generate_catalog_summary", path)
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return module
class CatalogSummaryLineEndingsTest(unittest.TestCase):
def test_digest_is_identical_for_lf_and_crlf(self):
digest = _load_generator().digest
with tempfile.TemporaryDirectory() as tmp:
lf = Path(tmp) / "lf.csv"
crlf = Path(tmp) / "crlf.csv"
lf.write_bytes(b"id,name\n1,alpha\n2,beta\n")
crlf.write_bytes(b"id,name\r\n1,alpha\r\n2,beta\r\n")
self.assertEqual(
digest(lf), digest(crlf),
"snapshot hashes must not change with the checkout's line endings",
)
def test_committed_snapshot_matches_normalized_sources(self):
summary = json.loads((DATA / "catalog-summary.json").read_text(encoding="utf-8"))
for name in SNAPSHOT_FILES:
expected = hashlib.sha256(
(DATA / name).read_bytes().replace(b"\r\n", b"\n")
).hexdigest()
self.assertEqual(
summary["snapshots"][name]["sha256"], expected,
f"{name}: committed snapshot hash does not match the LF-normalized source",
)
def test_crlf_checkout_produces_the_committed_hashes(self):
"""Simulate a Windows checkout: the recorded hashes must still validate."""
digest = _load_generator().digest
summary = json.loads((DATA / "catalog-summary.json").read_text(encoding="utf-8"))
with tempfile.TemporaryDirectory() as tmp:
for name in SNAPSHOT_FILES:
crlf_copy = Path(tmp) / name
raw = (DATA / name).read_bytes().replace(b"\r\n", b"\n")
crlf_copy.write_bytes(raw.replace(b"\n", b"\r\n"))
self.assertEqual(
digest(crlf_copy), summary["snapshots"][name]["sha256"],
f"{name}: a CRLF checkout would record a different hash",
)
if __name__ == "__main__":
unittest.main()

View File

@ -663,7 +663,11 @@ def _check_catalog_summary(summary, licenses, phosphor, problems):
problems.append(f"[catalog:summary] stale count for {key}")
snapshots = summary.get("snapshots") if isinstance(summary.get("snapshots"), dict) else {}
for name in ("google-fonts.csv", "google-font-licenses.json", "icons.csv", "phosphor-icons-upstream.json"):
digest = hashlib.sha256((DATA_DIR / name).read_bytes()).hexdigest()
# Line endings are normalized so the check matches
# generate-catalog-summary.py on CRLF checkouts too.
digest = hashlib.sha256(
(DATA_DIR / name).read_bytes().replace(b"\r\n", b"\n")
).hexdigest()
if snapshots.get(name) != {"sha256": digest}:
problems.append(f"[catalog:summary] stale snapshot for {name}")
policy = summary.get("promotionPolicy")