Files
paper-atlas/tests/test_arxiv_audit.py
T
codex-bot 503908198e
Metadata integrity checks / metadata (push) Successful in 26s
Audit raw arXiv IDs and preserve per-record category evidence
2026-11-06 19:11:02 +08:00

45 lines
2.4 KiB
Python

from types import SimpleNamespace
from unittest.mock import patch
import json
from pathlib import Path
import sqlite3
from contextlib import closing
import tempfile
import unittest
import zipfile
from paper_atlas.audits.arxiv import audit,MEMBER
class ArxivSourceAuditTests(unittest.TestCase):
def setUp(self):
self.temp=tempfile.TemporaryDirectory();self.addCleanup(self.temp.cleanup);self.root=Path(self.temp.name)
self.archive=self.root/'metadata.zip';self.out=self.root/'audit.json'
disk=patch('paper_atlas.audits.arxiv.shutil.disk_usage',return_value=SimpleNamespace(free=16*1024**3));disk.start();self.addCleanup(disk.stop)
def write(self,body):
with zipfile.ZipFile(self.archive,'w',compression=zipfile.ZIP_DEFLATED) as z:z.writestr(MEMBER,body)
def test_repeated_ids_and_payload_changes_are_distinct_from_unique_papers(self):
one={'id':'2601.00001','title':'A paper','abstract':'First text'};updated={**one,'abstract':'Revised text'}
two={'id':'2601.00002','title':'Another paper','abstract':''}
self.write('\n'.join(json.dumps(row) for row in (one,updated,updated,two)))
result=audit(self.archive,self.out)
self.assertEqual((result['raw_rows'],result['unique_external_ids'],result['extra_rows_for_repeated_ids']),(4,2,2))
self.assertTrue(result['zip_eof_crc_verified']);self.assertEqual(result['missing_abstract_rows'],1)
duplicate=result['duplicate_ids'][0];self.assertEqual(duplicate['occurrences'],3)
self.assertTrue(duplicate['has_payload_variants']);self.assertEqual([v['occurrences'] for v in duplicate['variants']],[1,2])
with closing(sqlite3.connect(result['id_index'])) as c:self.assertEqual(c.execute('SELECT count(*) FROM raw_ids').fetchone()[0],2)
with self.assertRaisesRegex(ValueError,'output exists'):audit(self.archive,self.out)
def test_invalid_or_unverified_input_never_publishes_audit_outputs(self):
self.write('{"id":"2601.00001","title":"Valid"}\nnot JSON')
with self.assertRaises(json.JSONDecodeError):audit(self.archive,self.out)
self.assertFalse(self.out.exists());self.assertFalse(self.out.with_suffix('.ids.sqlite').exists())
self.write('{"id":"2601.00001","title":"Valid"}')
with self.assertRaisesRegex(ValueError,'checksum mismatch'):audit(self.archive,self.out,'0'*64)
self.assertFalse(self.out.exists())
if __name__=='__main__':unittest.main()