xiaoxia-saas/tests/unit/test_1970_narrative_clip_weighted.py

"""#1970 P2 叙事匹配 AI 标签加权测试。

测试范围：
- AI 标签命中时权重 2.0
- 无 AI 标签时降级到素材标签权重 1.0
- 混合场景（部分素材有 AI 标签，部分只有素材标签）
- compute_tag_match_score 归一化得分
"""

from __future__ import annotations

import datetime as dt
import random
from dataclasses import dataclass, field

import pytest

from packages.domain.narrative_match import (
    AI_TAG_WEIGHT,
    ASSET_TAG_WEIGHT,
    _compute_ai_score,
    _extract_ai_tag_names,
    compute_tag_match_score,
    match_assets_by_script_tags,
    pick_narrative_assets,
)


@dataclass
class FakeAsset:
    id: str
    tag_ids: list[str] = field(default_factory=list)
    tags: list[str] = field(default_factory=list)
    status: str = "ready"
    file_type: str = "video"
    duration: float = 10.0
    quality_score: float | None = None
    created_at: object = None
    metadata: dict = field(default_factory=dict)


def _make_old_dt():
    return dt.datetime(2020, 1, 1, tzinfo=dt.UTC)


# ── _extract_ai_tag_names ─────────────────────────────────────────────────


class TestExtractAiTagNames:
    def test_extracts_all_keys(self):
        ai_tags = {
            "scene": ["工厂", "车间"],
            "objects": ["产品"],
            "action": ["演示"],
            "shot": "特写",  # shot 不参与标签匹配
            "has_text": False,
        }
        names = _extract_ai_tag_names(ai_tags)
        assert names == {"工厂", "车间", "产品", "演示"}

    def test_empty_dict(self):
        assert _extract_ai_tag_names({}) == set()

    def test_none_values(self):
        ai_tags = {"scene": None, "objects": None, "action": None}
        assert _extract_ai_tag_names(ai_tags) == set()

    def test_case_insensitive(self):
        ai_tags = {"scene": ["Factory"], "objects": [], "action": []}
        names = _extract_ai_tag_names(ai_tags)
        assert "factory" in names


# ── _compute_ai_score ─────────────────────────────────────────────────────


class TestComputeAiScore:
    def test_single_clip_hit(self):
        wanted = {"工厂", "演示"}
        clips = [{"scene": ["工厂"], "objects": [], "action": ["演示"]}]
        score = _compute_ai_score("a1", wanted, {"a1": clips})
        # 命中 2 个 × 2.0 = 4.0
        assert score == 2 * AI_TAG_WEIGHT

    def test_multiple_clips_takes_best(self):
        wanted = {"工厂", "演示"}
        clips = [
            {"scene": ["工厂"], "objects": [], "action": []},  # 1 hit = 2.0
            {"scene": ["工厂"], "objects": [], "action": ["演示"]},  # 2 hits = 4.0
        ]
        score = _compute_ai_score("a1", wanted, {"a1": clips})
        assert score == 2 * AI_TAG_WEIGHT  # best = 2 hits

    def test_no_match(self):
        wanted = {"美食"}
        clips = [{"scene": ["工厂"], "objects": [], "action": ["演示"]}]
        score = _compute_ai_score("a1", wanted, {"a1": clips})
        assert score == 0.0

    def test_no_clips_for_asset(self):
        wanted = {"工厂"}
        assert _compute_ai_score("a1", wanted, {}) == 0.0
        assert _compute_ai_score("a1", wanted, None) == 0.0

    def test_empty_wanted(self):
        clips = [{"scene": ["工厂"], "objects": [], "action": []}]
        assert _compute_ai_score("a1", set(), {"a1": clips}) == 0.0


# ── match_assets_by_script_tags with AI tags ──────────────────────────────


class TestMatchWithAiTags:
    def test_ai_tag_hit_puts_in_matched(self):
        """有 AI 标签命中 → 进入命中池."""
        assets = [FakeAsset("a1", created_at=_make_old_dt())]
        clip_ai_tags = {"a1": [{"scene": ["工厂"], "objects": [], "action": []}]}

        matched, unmatched = match_assets_by_script_tags(
            assets,
            script_tags=["工厂"],
            clip_ai_tags_by_asset=clip_ai_tags,
        )

        assert [a.id for a in matched] == ["a1"]
        assert unmatched == []

    def test_ai_tag_no_match_puts_in_unmatched(self):
        """AI 标签未命中 → 进入未命中池."""
        assets = [FakeAsset("a1", created_at=_make_old_dt())]
        clip_ai_tags = {"a1": [{"scene": ["办公室"], "objects": [], "action": []}]}

        matched, unmatched = match_assets_by_script_tags(
            assets,
            script_tags=["工厂"],
            clip_ai_tags_by_asset=clip_ai_tags,
        )

        assert matched == []
        assert [a.id for a in unmatched] == ["a1"]

    def test_asset_tag_still_works_without_ai_tags(self):
        """无 AI 标签时，素材标签仍按权重 1.0 匹配."""
        assets = [FakeAsset("a1", tags=["工厂"], created_at=_make_old_dt())]

        matched, unmatched = match_assets_by_script_tags(
            assets,
            script_tags=["工厂"],
        )

        assert [a.id for a in matched] == ["a1"]

    def test_mixed_ai_and_asset_tags(self):
        """混合场景：一个素材有 AI 标签，另一个只有素材标签."""
        assets = [
            FakeAsset("a1", created_at=_make_old_dt()),  # AI 标签命中
            FakeAsset("a2", tags=["工厂"], created_at=_make_old_dt()),  # 素材标签命中
            FakeAsset("a3", tags=["美食"], created_at=_make_old_dt()),  # 无命中
        ]
        clip_ai_tags = {"a1": [{"scene": ["工厂"], "objects": [], "action": []}]}

        matched, unmatched = match_assets_by_script_tags(
            assets,
            script_tags=["工厂"],
            clip_ai_tags_by_asset=clip_ai_tags,
        )

        assert {a.id for a in matched} == {"a1", "a2"}
        assert [a.id for a in unmatched] == ["a3"]

    def test_ai_tag_and_asset_tag_both_hit(self):
        """同一素材 AI 标签和素材标签都命中 → 仍在命中池."""
        assets = [FakeAsset("a1", tags=["工厂"], created_at=_make_old_dt())]
        clip_ai_tags = {"a1": [{"scene": ["工厂"], "objects": [], "action": []}]}

        matched, unmatched = match_assets_by_script_tags(
            assets,
            script_tags=["工厂"],
            tag_names_by_id={"a1": ["工厂"]},
            clip_ai_tags_by_asset=clip_ai_tags,
        )

        assert [a.id for a in matched] == ["a1"]


# ── compute_tag_match_score ───────────────────────────────────────────────


class TestComputeTagMatchScore:
    def test_ai_only_score(self):
        """仅 AI 标签命中."""
        clip_ai_tags = {"a1": [{"scene": ["工厂"], "objects": [], "action": ["演示"]}]}
        score = compute_tag_match_score(
            "a1",
            script_tags=["工厂", "演示"],
            clip_ai_tags_by_asset=clip_ai_tags,
        )
        # AI: 2 hits × 2.0 = 4.0; asset: 0; max = 2 × 3.0 = 6.0
        assert abs(score - 4.0 / 6.0) < 0.01

    def test_asset_only_score(self):
        """仅素材标签命中."""
        score = compute_tag_match_score(
            "a1",
            script_tags=["工厂", "演示"],
            tag_names_by_id={"a1": ["工厂"]},
        )
        # AI: 0; asset: 1 hit × 1.0 = 1.0; max = 2 × 3.0 = 6.0
        assert abs(score - 1.0 / 6.0) < 0.01

    def test_both_ai_and_asset_score(self):
        """AI 标签 + 素材标签同时命中."""
        clip_ai_tags = {"a1": [{"scene": ["工厂"], "objects": [], "action": []}]}
        score = compute_tag_match_score(
            "a1",
            script_tags=["工厂", "演示"],
            tag_names_by_id={"a1": ["工厂"]},
            clip_ai_tags_by_asset=clip_ai_tags,
        )
        # AI: 1 hit × 2.0 = 2.0; asset: 1 hit × 1.0 = 1.0; max = 2 × 3.0 = 6.0
        assert abs(score - 3.0 / 6.0) < 0.01

    def test_no_match_score_zero(self):
        """无命中 → 得分 0."""
        score = compute_tag_match_score(
            "a1",
            script_tags=["工厂"],
            tag_names_by_id={"a1": ["美食"]},
        )
        assert score == 0.0

    def test_full_match_score_one(self):
        """全命中 → 得分接近 1.0."""
        clip_ai_tags = {"a1": [{"scene": ["工厂"], "objects": ["产品"], "action": ["演示"]}]}
        score = compute_tag_match_score(
            "a1",
            script_tags=["工厂", "产品", "演示"],
            clip_ai_tags_by_asset=clip_ai_tags,
        )
        # AI: 3 hits × 2.0 = 6.0; max = 3 × 3.0 = 9.0 → 6/9 = 0.667
        # 注意：仅 AI 标签命中不可能达到 1.0（因为 max 包含素材权重）
        assert score > 0.5

    def test_empty_script_tags(self):
        """空文案标签 → 得分 0."""
        assert compute_tag_match_score("a1", script_tags=[]) == 0.0


# ── pick_narrative_assets with AI tags ────────────────────────────────────


class TestPickNarrativeWithAiTags:
    def _assets(self):
        old = _make_old_dt()
        return [
            FakeAsset("ai_match", created_at=old),  # AI 标签命中
            FakeAsset("asset_match", tags=["工厂"], created_at=old),  # 素材标签命中
            FakeAsset("no_match", tags=["美食"], created_at=old),  # 无命中
        ]

    def test_ai_match_prioritized(self):
        """AI 标签命中的素材进入命中池."""
        clip_ai_tags = {"ai_match": [{"scene": ["工厂"], "objects": [], "action": []}]}

        picked = pick_narrative_assets(
            self._assets(),
            script_tags=["工厂"],
            clip_ai_tags_by_asset=clip_ai_tags,
            limit=2,
            rng=random.Random(0),
        )

        ids = {a.id for a in picked}
        assert "ai_match" in ids
        assert "asset_match" in ids

    def test_fallback_when_no_ai_match(self):
        """AI 标签和素材标签都未命中 → 降级."""
        clip_ai_tags = {"ai_match": [{"scene": ["办公室"], "objects": [], "action": []}]}

        picked = pick_narrative_assets(
            self._assets(),
            script_tags=["不存在"],
            clip_ai_tags_by_asset=clip_ai_tags,
            limit=2,
            rng=random.Random(0),
        )

        assert len(picked) == 2  # 从全量中选取

    def test_backward_compat_without_ai_tags(self):
        """不传 clip_ai_tags_by_asset 时行为与之前完全一致."""
        picked = pick_narrative_assets(
            self._assets(),
            script_tags=["工厂"],
            limit=2,
            rng=random.Random(0),
        )

        # 仅素材标签匹配
        ids = {a.id for a in picked}
        assert "asset_match" in ids


if __name__ == "__main__":
    pytest.main([__file__, "-q"])