Merge remote-tracking branch 'origin/feat/249-needs-review-backend' into feat/249-needs-review-ui

database/review.py

@@ -40,6 +40,7 @@ from .review_schema import (
     METADATA_TABLE,
     canonical_evidence,
     evidence_digest,
+    evidence_offers_choice,
 )
 
 # Only this module's table constants are interpolated into the SQL below.
@@ -96,6 +97,13 @@ _PENDING_OF_LOCATOR = (
     f"JOIN {ITEMS_TABLE} i ON i.byte_id=b.id "
     "WHERE f.locator=? AND i.state='pending'"
 )
+# Pending items of one file with their evidence: an untraced file's settle.
+_PENDING_EVIDENCE_OF_LOCATOR = (
+    f"SELECT i.id,i.evidence 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 i.state='pending'"
+)
 # Only an undecided item goes: a decision row (RESTRICT) is never deleted.
 _SETTLE_ITEM = (
     f"DELETE FROM {ITEMS_TABLE} WHERE id=? AND state='pending' "  # nosec B608
@@ -437,6 +445,41 @@ class ReviewOperations:
             notify_review_change(self.model.db_path)
         return removed
 
+    def settle_untraced_review_items(self, locators) -> int:
+        """Remove the pending, undecided items that offer nothing to choose.
+
+        ``locators`` are files the caller found ambiguous without a choice
+        (fewer than two candidates carry a prompt). Of their items, one leaves
+        the queue only when its own stored evidence offers no choice either
+        (``evidence_offers_choice``) and it is still ``pending`` at revision 0
+        with no decision row, the same safe delete as
+        ``settle_linked_review_items``. Files without a pending item cost one
+        indexed read and open no write transaction. Returns how many items
+        were removed (the review index revision moves when any was).
+        """
+        locators = list(locators)
+        for locator in locators:
+            _validate_locator(locator)
+        conn = self.model.get_connection()
+        pending = [
+            locator
+            for locator in locators
+            if conn.execute(_PENDING_OF_LOCATOR, (locator,)).fetchone() is not None
+        ]
+        if not pending:
+            return 0
+        removed = 0
+        with self._pair_transaction() as conn:
+            for locator in pending:
+                rows = conn.execute(_PENDING_EVIDENCE_OF_LOCATOR, (locator,)).fetchall()
+                for item_id, evidence in rows:
+                    if evidence_offers_choice(json.loads(evidence)):
+                        continue
+                    removed += conn.execute(_SETTLE_ITEM, (item_id,)).rowcount
+            if removed:
+                conn.execute(_BUMP_REVIEW_INDEX)
+        return removed
+
     def review_queue_page(self, *, limit: int, after: tuple | None = None) -> dict:
         """One page of pending items, oldest first, from one snapshot.
 

database/review_schema.py

@@ -200,6 +200,44 @@ def canonical_evidence(value: Any) -> str:
     return text
 
 
+def choosable(candidate: Any) -> bool:
+    """True when a candidate offers a prompt to choose: it is ``resolved`` and
+    its positive side carries non-blank text. The page disables any other
+    candidate, so it is never something to choose.
+    """
+    if not isinstance(candidate, dict) or candidate.get("state") != "resolved":
+        return False
+    positive = candidate.get("positive")
+    if not isinstance(positive, dict):
+        return False
+    text = positive.get("text")
+    return isinstance(text, str) and bool(text.strip())
+
+
+# An item is worth a decision only when at least this many candidates offer
+# a prompt; with fewer there is nothing to choose between (maintainer test of
+# #284/#288: 39 items whose candidates were all "unresolved").
+MIN_CHOOSABLE = 2
+
+
+def evidence_offers_choice(evidence: Any) -> bool:
+    """False when stored evidence provably offers nothing to choose.
+
+    Unlimited evidence must list ``MIN_CHOOSABLE`` choosable candidates. A
+    limited item stores none, only ``candidate_total``; it may offer a choice
+    (more than ``MAX_CANDIDATES`` prompts) unless that total is too small.
+    """
+    if not isinstance(evidence, dict):
+        return False
+    if evidence.get("limited"):
+        total = evidence.get("candidate_total")
+        return type(total) is int and total >= MIN_CHOOSABLE
+    candidates = evidence.get("candidates")
+    if not isinstance(candidates, list):
+        return False
+    return sum(1 for c in candidates if choosable(c)) >= MIN_CHOOSABLE
+
+
 def evidence_digest(text: str) -> str:
     """SHA-256 of canonical evidence text (ASCII, hence UTF-8 identical)."""
     return hashlib.sha256(text.encode("utf-8")).hexdigest()