hef/selection.py

@@ -58,6 +58,38 @@ def candidates_for_mode(records, mode: str, pool_size: int) -> list[Record]:
 from typing import Optional
 
 
+def ranked_candidates(
+    records,
+    coord: Coordinate,
+    mode: str,
+    *,
+    pool_size: int = 4,
+    weights: Weights = Weights(),
+    approved_only: bool = False,
+) -> list[tuple[Record, float]]:
+    """Mode-eligible records sorted nearest-first, each paired with its distance.
+
+    Applies the same approved_only filter and 'av' pool fallback as select(),
+    then returns up to pool_size nearest (record, distance) pairs. This is the
+    single source of truth for "the pool"; select() picks from it.
+    """
+    if mode not in CONTENT_MODES:
+        raise ValueError(
+            f"ranked_candidates expects a content mode {sorted(CONTENT_MODES)}, "
+            f"got {mode!r}"
+        )
+    pool = records
+    if approved_only:
+        pool = [r for r in pool if r.review_status == "approved"]
+    candidates = candidates_for_mode(pool, mode, pool_size)
+    ranked = sorted(
+        candidates,
+        key=lambda r: (distance(coord, record_coordinate(r), weights), r.id),
+    )
+    nearest = ranked[:pool_size]
+    return [(r, distance(coord, record_coordinate(r), weights)) for r in nearest]
+
+
 def select(
     records,
     coord: Coordinate,
@@ -82,17 +114,17 @@ def select(
         )
     if mode == "none":
         return None
-    pool = records
-    if approved_only:
-        pool = [r for r in pool if r.review_status == "approved"]
-    candidates = candidates_for_mode(pool, mode, pool_size)
-    if not candidates:
-        return None
-    ranked = sorted(
-        candidates,
-        key=lambda r: (distance(coord, record_coordinate(r), weights), r.id),
+    ranked = ranked_candidates(
+        records,
+        coord,
+        mode,
+        pool_size=pool_size,
+        weights=weights,
+        approved_only=approved_only,
     )
-    nearest = ranked[:pool_size]
+    if not ranked:
+        return None
+    nearest = [r for r, _ in ranked]
     if rng is None:
         return nearest[0]
     return rng.choice(nearest)

tests/test_selection_ranked.py

@@ -0,0 +1,87 @@
+import random
+
+import pytest
+
+from hef.catalog import Record
+from hef.selection import Coordinate, Weights, ranked_candidates, select
+
+
+def make_record(**overrides):
+    base = dict(
+        id="r",
+        title="t",
+        source_url="u",
+        source_archive="internet_archive",
+        license="public_domain",
+        mode="video",
+        left=0,
+        right=0,
+        dark=0,
+        light=0,
+        duration_s=600,
+        file_path="",
+    )
+    base.update(overrides)
+    return Record(**base)
+
+
+def test_ranked_candidates_sorts_nearest_first_with_distances():
+    near = make_record(id="near", mode="video", left=1, right=1, dark=0, light=0)
+    far = make_record(id="far", mode="video", left=4, right=4, dark=4, light=4)
+    ranked = ranked_candidates([far, near], Coordinate(0, 0, 0, 0), "video")
+    assert [r.id for r, _ in ranked] == ["near", "far"]
+    assert ranked[0][1] < ranked[1][1]
+
+
+def test_ranked_candidates_caps_at_pool_size():
+    recs = [make_record(id=f"r{i}", mode="video", left=i % 5) for i in range(10)]
+    ranked = ranked_candidates(recs, Coordinate(0, 0, 0, 0), "video", pool_size=3)
+    assert len(ranked) == 3
+
+
+def test_ranked_candidates_filters_by_mode():
+    a = make_record(id="aud", mode="audio")
+    v = make_record(id="vid", mode="video")
+    ranked = ranked_candidates([a, v], Coordinate(0, 0, 0, 0), "audio")
+    assert [r.id for r, _ in ranked] == ["aud"]
+
+
+def test_ranked_candidates_av_falls_back_to_audio_and_video():
+    a = make_record(id="aud", mode="audio")
+    v = make_record(id="vid", mode="video")
+    ranked = ranked_candidates([a, v], Coordinate(0, 0, 0, 0), "av", pool_size=4)
+    assert {r.id for r, _ in ranked} == {"aud", "vid"}
+
+
+def test_ranked_candidates_approved_only():
+    p = make_record(id="prop", mode="video", review_status="proposed")
+    ok = make_record(id="appr", mode="video", review_status="approved")
+    ranked = ranked_candidates([p, ok], Coordinate(0, 0, 0, 0), "video", approved_only=True)
+    assert [r.id for r, _ in ranked] == ["appr"]
+
+
+def test_ranked_candidates_rejects_none_mode():
+    with pytest.raises(ValueError):
+        ranked_candidates([], Coordinate(0, 0, 0, 0), "none")
+
+
+def test_select_returns_rank_one_of_ranked_candidates():
+    recs = [
+        make_record(id="near", mode="video", left=1),
+        make_record(id="far", mode="video", left=4),
+    ]
+    coord = Coordinate(0, 0, 0, 0)
+    ranked = ranked_candidates(recs, coord, "video")
+    assert select(recs, coord, "video", rng=None).id == ranked[0][0].id
+
+
+def test_select_none_mode_still_returns_none():
+    recs = [make_record(id="v", mode="video")]
+    assert select(recs, Coordinate(0, 0, 0, 0), "none") is None
+
+
+def test_select_shuffles_within_pool_when_rng_given():
+    recs = [make_record(id=f"r{i}", mode="video", left=i) for i in range(5)]
+    coord = Coordinate(0, 0, 0, 0)
+    picks = {select(recs, coord, "video", pool_size=5, rng=random.Random(s)).id for s in range(20)}
+    assert len(picks) > 1