Preserve failed-run checkpoint when snapshot receipts are invalid

paper_atlas/collectors/rss2026.py

@@ -6,7 +6,6 @@ import hashlib
 import json
 from pathlib import Path
 import re
-import tempfile
 import unicodedata
 
 from paper_atlas.io.html import Document, Node, clean
@@ -147,11 +146,15 @@ def collect(out, *, snapshots=None, cache=None):
     evidence = {}; receipts = {}
     if snapshots is not None:
         root = Path(snapshots)
-        for r in json.loads((root/'receipts.json').read_bytes()):
-            name = r['file']
-            if not isinstance(name, str) or Path(name).name != name or name in receipts:
-                raise ValueError('Unsafe or repeated snapshot receipt')
-            receipts[name] = r
+        try:
+            for r in json.loads((root/'receipts.json').read_bytes()):
+                name = r['file']
+                if not isinstance(name, str) or Path(name).name != name or name in receipts:
+                    raise ValueError('Unsafe or repeated snapshot receipt')
+                receipts[name] = r
+        except Exception as error:
+            (out/'failed.json').write_text(json.dumps({'status': 'failed_not_complete', 'error_type': type(error).__name__, 'database_written': False})+'\n')
+            raise
     def page(name, url):
         if snapshots is not None:
             path = root/name

tests/test_rss2026.py

@@ -96,3 +96,5 @@ class Rss2026Tests(unittest.TestCase):
         receipts=[*self.fixture['receipts'],{**self.fixture['receipts'][0],'file':'../outside'}]
         (self.snap/'receipts.json').write_text(json.dumps(receipts))
         with self.assertRaisesRegex(ValueError,'Unsafe'):rss.collect(self.root/'unsafe',snapshots=self.snap)
+        self.assertTrue((self.root/'unsafe/failed.json').exists())
+        self.assertFalse((self.root/'unsafe/collection-report.json').exists())