第 1 卷第 1 章：1–9 年

dfannals/slice.py

@@ -0,0 +1,195 @@
+"""把史料切成章节素材。
+
+真实数据（403853 条事件 / 250 年）证明：按"重要事件数量"切章会得到几千章。
+所以改为先按时间窗分桶（每窗 10 年），再在窗内按显著度取前 N 条——
+这样一章天然覆盖一段年月，既有大事件链，也不会漏掉时代的推进。
+"""
+from __future__ import annotations
+
+from collections import defaultdict
+from dataclasses import dataclass, field
+
+from dfannals import legends as lg
+from dfannals import score
+from dfannals.legends import Event, World
+
+YEARS_PER_CHAPTER = 10      # 一个时间窗覆盖的年数
+EVENTS_PER_CHAPTER = 12     # 每章最多收录的史料条目
+MIN_EVENTS_PER_CHAPTER = 3  # 少于这个数量就并入上一章（太平年月）
+MAX_PER_CATEGORY = 4        # 同一类事件每章上限，避免整章都是讣告
+
+
+@dataclass
+class Chapter:
+    index: int
+    start_year: int
+    end_year: int
+    events: list[Event] = field(default_factory=list)
+    quiet_years: list[tuple[int, int]] = field(default_factory=list)
+
+    @property
+    def key(self) -> str:
+        return f"{self.index:03d}-{self.start_year}-{self.end_year}"
+
+    @property
+    def span(self) -> str:
+        if self.start_year == self.end_year:
+            return f"{self.start_year} 年"
+        return f"{self.start_year}–{self.end_year} 年"
+
+    def categories(self) -> list[str]:
+        seen: list[str] = []
+        for e in self.events:
+            c = score.category(e)
+            if c not in seen:
+                seen.append(c)
+        return seen
+
+
+def plan(
+    world: World,
+    years_per_chapter: int = YEARS_PER_CHAPTER,
+    per_chapter: int = EVENTS_PER_CHAPTER,
+    min_events: int = MIN_EVENTS_PER_CHAPTER,
+    max_per_category: int = MAX_PER_CATEGORY,
+) -> list[Chapter]:
+    prom = score.prominence(world)
+    scored = [(score.significance(e, prom), e) for e in world.events]
+    scored = [pair for pair in scored if pair[0] > 0]
+    if not scored:
+        lo, hi = world.event_years()
+        return [Chapter(index=1, start_year=lo, end_year=hi)]
+
+    lo = min(e.year for _, e in scored)
+    hi = max(e.year for _, e in scored)
+
+    buckets: dict[int, list[tuple[int, Event]]] = defaultdict(list)
+    for sig, e in scored:
+        buckets[e.year // years_per_chapter].append((sig, e))
+
+    chapters: list[Chapter] = []
+    for b in range(lo // years_per_chapter, hi // years_per_chapter + 1):
+        window_start = max(b * years_per_chapter, lo)
+        window_end = min(b * years_per_chapter + years_per_chapter - 1, hi)
+        ranked = sorted(buckets.get(b, []), key=lambda p: (-p[0], p[1].year, p[1].id))
+        # 按类别限额挑选：让一章里有战事、兴亡、器物，而不是 12 条死亡讣告
+        picks: list[tuple[int, Event]] = []
+        used: dict[str, int] = {}
+        for sig, ev in ranked:
+            cat = score.category(ev)
+            if used.get(cat, 0) >= max_per_category:
+                continue
+            used[cat] = used.get(cat, 0) + 1
+            picks.append((sig, ev))
+            if len(picks) >= per_chapter:
+                break
+        events = sorted((e for _, e in picks), key=lambda e: (e.year, e.seconds72, e.id))
+
+        if not events:
+            if chapters:
+                chapters[-1].quiet_years.append((window_start, window_end))
+                chapters[-1].end_year = window_end
+            continue
+
+        if len(events) < min_events and chapters:
+            chapters[-1].events.extend(events)
+            chapters[-1].end_year = window_end
+            continue
+
+        chapters.append(
+            Chapter(index=len(chapters) + 1, start_year=window_start, end_year=window_end, events=events)
+        )
+
+    for i, c in enumerate(chapters, 1):
+        c.index = i
+    return chapters
+
+
+def _figure_line(world: World, fid: int, prom) -> str:
+    fig = world.figures.get(fid)
+    if not fig:
+        return f"- HF#{fid}（史料无记载）"
+    bits = [lg.pretty(fig.name) or f"HF#{fid}", fig.race or "未知种族", fig.alive_span]
+    if fig.profession:
+        bits.append(fig.profession)
+    bits.append(f"史料出现 {prom.get(fid, 0)} 次")
+    return "- " + " | ".join(bits)
+
+
+def material(world: World, chapter: Chapter, max_figures: int = 40) -> str:
+    """把一章的史料渲染成给模型看的素材文本。"""
+    prom = score.prominence(world)
+    lines: list[str] = [
+        f"## 本章范围：{chapter.span}",
+        "",
+        f"共 {len(chapter.events)} 条史料，类型：{('、'.join(chapter.categories())) or '无'}。",
+        "",
+        "### 事件流水（按时间排序，专名保留游戏原文）",
+        "",
+    ]
+
+    participation: dict[int, int] = {}
+    for e in chapter.events:
+        chunks = [f"{e.year}年", e.type]
+        for tag, kind in lg.ID_FIELDS.items():
+            for i in e.ids(tag):
+                # id 为负是“无此项”，不要渲染成 HF#-1 这类噪音
+                if kind == "figure":
+                    name = world.figure_name(i)
+                elif kind == "site":
+                    name = world.site_name(i)
+                elif kind == "entity":
+                    name = world.entity_name(i)
+                else:
+                    name = ""
+                if not name:
+                    continue
+                chunks.append(f"{tag}={name}")
+                if kind == "figure":
+                    participation[i] = participation.get(i, 0) + 1
+        extra = []
+        for field_name in ("state", "reason", "circumstance"):
+            v = e.text(field_name)
+            if v and v not in ("-1", ""):
+                extra.append(f"{field_name}={v}")
+        if extra:
+            chunks.append("·".join(extra))
+        lines.append("- " + " · ".join(chunks))
+
+    if chapter.quiet_years:
+        spans = "、".join(f"{a}–{b} 年" for a, b in chapter.quiet_years)
+        lines += [
+            "",
+            "### 太平年月（史料无值得立传的事件）",
+            "",
+            f"- {spans}：这段时期只留下琐碎记录，可一笔带过。",
+        ]
+
+    lines += ["", "### 本章登场人物（史料中的身份信息）", ""]
+    for fid, _ in sorted(participation.items(), key=lambda kv: -prom.get(kv[0], 0))[:max_figures]:
+        lines.append(_figure_line(world, fid, prom))
+
+    sites = sorted({n for e in chapter.events for i in e.ids("site_id") if (n := world.site_name(i))})
+    if sites:
+        lines += ["", "### 相关地点", "", "- " + "、".join(sites)]
+
+    ents = sorted({n for e in chapter.events for i in e.ids("entity_id") if (n := world.entity_name(i))})
+    if ents:
+        lines += ["", "### 相关势力", "", "- " + "、".join(ents)]
+
+    return "\n".join(lines)
+
+
+def overview(world: World, chapters: list[Chapter], limit: int = 10) -> str:
+    lo, hi = world.event_years()
+    lines = [
+        f"世界：{world.name}" + (f"（{world.altname}）" if world.altname else ""),
+        f"历史：{lo}–{hi} 年 | 史料事件 {len(world.events)} 条 | "
+        f"人物 {len(world.figures)} | 势力 {len(world.entities)} | 地点 {len(world.sites)}",
+        f"规划章节：{len(chapters)} 章（每章约 {YEARS_PER_CHAPTER} 年 / 最多 {EVENTS_PER_CHAPTER} 条史料）",
+    ]
+    for c in chapters[:limit]:
+        lines.append(f"  第 {c.index} 章 {c.span}：{len(c.events)} 条（{('、'.join(c.categories())) or '无'}）")
+    if len(chapters) > limit:
+        lines.append(f"  …… 其余 {len(chapters) - limit} 章略")
+    return "\n".join(lines)