feat(review): supersede stale items and inspect each file state once

A semantics table or resolver version change no longer leaves two pending
items for one file. A new item supersedes the other items of the same bytes
when every one is pending and undecided (revision 0, no decision row, the
self-heal's safe delete). Beside a decided or advanced item nothing new is
stored, and the rescan's stat shortcut skips those bytes under any version.

The inspection item version now folds a narrower fingerprint: the table
restricted to the graph's node classes plus its class-independent parts, so
an edit about other classes leaves every item alone.

The inspection profile runs once per file state. The scan resolves the
untraced file at batch level, skips files already queued or decided at their
current size and mtime under their version, and remembers files it found
untraced in this process. The capture reuses the scan's result when it holds
the same records.
This commit is contained in:
Vito Sansevero
2026-10-23 16:02:49 -07:00
parent 341757ea8e
commit 143b2a6b44
8 changed files with 705 additions and 126 deletions
+47 -2
View File
@@ -90,6 +90,23 @@ _PENDING_AT = (
"WHERE f.locator=? AND b.size=? AND b.mtime_ns=? AND i.resolver_version=? "
"AND i.state='pending' LIMIT 1"
)
# Bytes verified at this stat whose item carries a decision (any version).
_DECIDED_AT = (
f"SELECT 1 FROM {FILES_TABLE} f " # nosec B608
f"JOIN {BYTES_TABLE} b ON b.file_id=f.id "
f"JOIN {ITEMS_TABLE} i ON i.byte_id=b.id "
"WHERE f.locator=? AND b.size=? AND b.mtime_ns=? "
"AND (i.state<>'pending' OR i.revision<>0 OR EXISTS (SELECT 1 FROM "
f"{DECISIONS_TABLE} d WHERE d.item_id=i.id)) LIMIT 1"
)
# The other items of one byte record (another version or evidence), with
# whether each may be superseded: pending, revision 0, no decision row.
_OTHER_ITEMS_OF_BYTES = (
"SELECT i.id, (i.state='pending' AND i.revision=0 AND NOT EXISTS " # nosec B608
f"(SELECT 1 FROM {DECISIONS_TABLE} d WHERE d.item_id=i.id)) "
f"FROM {ITEMS_TABLE} i WHERE i.byte_id=? "
"AND NOT (i.resolver_version=? AND i.evidence_hash=?)"
)
# Pending items of one file: the candidates a link settles.
_PENDING_OF_LOCATOR = (
f"SELECT i.id FROM {FILES_TABLE} f " # nosec B608
@@ -274,6 +291,12 @@ class ReviewOperations:
``LibraryCommandError("storage-changed")`` when the storage epoch is
no longer ``epoch`` (a restore since the capture) and ``ValueError``
for invalid facts or evidence.
One file never holds two pending items for the same bytes: the new
item supersedes the byte record's other items (an older resolver or
semantics version) when every one is pending and undecided (the safe
delete of the self-heal); when one carries a decision or a later
revision, it is kept and nothing new is stored (False).
"""
_validate_target(locator, sha256, size, mtime_ns)
_validate_spelling(spelled_path, locator)
@@ -297,6 +320,15 @@ class ReviewOperations:
)
if created or moved:
conn.execute(_BUMP_IMAGE_INDEX)
others = conn.execute(
_OTHER_ITEMS_OF_BYTES, (byte_id, resolver_version, evidence_hash)
).fetchall()
if any(not removable for _id, removable in others):
return False
superseded = sum(
conn.execute(_SETTLE_ITEM, (item_id,)).rowcount
for item_id, _removable in others
)
cursor = conn.execute(
_INSERT_ITEM,
(
@@ -314,9 +346,9 @@ class ReviewOperations:
)
inserted = cursor.rowcount > 0
refreshed = _refresh_spelling(conn, locator, spelled_path)
if inserted or refreshed:
if inserted or refreshed or superseded:
conn.execute(_BUMP_REVIEW_INDEX)
if inserted or refreshed:
if inserted or refreshed or superseded:
notify_review_change(self.model.db_path)
return inserted
@@ -389,6 +421,19 @@ class ReviewOperations:
)
return row is not None
def review_decided_at(self, locator: str, size: int, mtime_ns: int) -> bool:
"""True when bytes verified at this stat carry a decided item.
Any version: a newer resolver or table never adds an item beside a
decision, so the rescan need not copy those bytes again.
"""
row = (
self.model.get_connection()
.execute(_DECIDED_AT, (locator, size, mtime_ns))
.fetchone()
)
return row is not None
def review_pending_at(
self, locator: str, size: int, mtime_ns: int, resolver_version: int
) -> bool: