feat: 实现 board_select 周去重与深池补满

Co-authored-by: Cursor <cursoragent@cursor.com>

daily/board_select.py

@@ -0,0 +1,46 @@
+"""五榜唯一列表主人：周去重 + 深池补满。"""
+
+from __future__ import annotations
+
+import logging
+from typing import Any, Literal
+
+from daily.delta import skill_id
+
+logger = logging.getLogger(__name__)
+
+
+def board_select(
+    *,
+    board: str,
+    items: list[dict[str, Any]],
+    recent_keys: set[str],
+    limit: int,
+    pool_size: int,
+    kind: Literal["skill", "github"],
+) -> list[dict[str, Any]]:
+    """从深池过滤近 N 日已展示 key，按原顺序取满 limit；不足则短榜。"""
+    if kind == "skill":
+        from daily.skills_group import group_skills_by_source
+
+        pool = group_skills_by_source(items, limit=pool_size, pool_size=pool_size)
+
+        def key_fn(x: dict[str, Any]) -> str:
+            return skill_id(x)
+    else:
+        pool = items[: max(pool_size, limit)]
+
+        def key_fn(x: dict[str, Any]) -> str:
+            return str(x.get("repo") or "")
+
+    out: list[dict[str, Any]] = []
+    for item in pool:
+        k = key_fn(item)
+        if not k or k in recent_keys:
+            continue
+        out.append(item)
+        if len(out) >= limit:
+            break
+    if len(out) < limit:
+        logger.info("board_short:%s:%s", board, len(out))
+    return out

tests/test_board_select.py

@@ -0,0 +1,58 @@
+# tests/test_board_select.py
+from __future__ import annotations
+
+import unittest
+
+from daily.board_select import board_select
+
+
+def _gh(repo: str) -> dict:
+    return {"repo": repo, "description": repo}
+
+
+class BoardSelectTests(unittest.TestCase):
+    def test_filters_recent_and_keeps_order(self):
+        pool = [_gh(f"o/r{i}") for i in range(20)]
+        recent = {"o/r0", "o/r1", "o/r2"}
+        out = board_select(
+            board="github_trending",
+            items=pool,
+            recent_keys=recent,
+            limit=5,
+            pool_size=20,
+            kind="github",
+        )
+        keys = [x["repo"] for x in out]
+        self.assertEqual(keys, ["o/r3", "o/r4", "o/r5", "o/r6", "o/r7"])
+
+    def test_deep_pool_fills_after_filter(self):
+        pool = [_gh(f"o/r{i}") for i in range(8)]
+        recent = {f"o/r{i}" for i in range(6)}  # 前 6 全封
+        out = board_select(
+            board="github_emerging",
+            items=pool,
+            recent_keys=recent,
+            limit=5,
+            pool_size=8,
+            kind="github",
+        )
+        self.assertEqual([x["repo"] for x in out], ["o/r6", "o/r7"])  # 短榜
+
+    def test_skill_uses_skill_id(self):
+        items = [
+            {"id": "a/b/s1", "source": "a/b", "title": "s1", "installs": 10},
+            {"id": "c/d/s2", "source": "c/d", "title": "s2", "installs": 9},
+        ]
+        out = board_select(
+            board="skills_trending",
+            items=items,
+            recent_keys={"a/b/s1"},
+            limit=10,
+            pool_size=50,
+            kind="skill",
+        )
+        self.assertEqual([x["id"] for x in out], ["c/d/s2"])
+
+
+if __name__ == "__main__":
+    unittest.main()