Create-knowledge-find-decode/scripts/build_creation_demo.py

"""创作知识 query 正交 demo：5 套家族机械正交 → LLM 只做排除(query_filter.txt) → 存 JSON。

不真实搜，只产 query 供前端看。轴严格取分类树的"创作支"：
  实质 = 实质树·理念支(排除表象)   形式 = 形式树·架构支(排除呈现)
  目的池 = 作用树 + 感受树 + 意图树 全部合一(随机取)
  阶段意图 = 灵感/选题/脚本 展开成创作者真会搜的词(选题/开头/钩子/标题/封面/文案…)——脊柱，每族必带
  模态 = 视频/图片   知识类型 = 怎么做/有哪些/为什么
脊柱(每条都带)：… 阶段意图 + 模态 + 知识类型；前面配 实质/形式/目的 之一或组合。
5 家族：① 实质×阶段 ② 形式×阶段 ③ 实质×形式×阶段 ④ 目的池×阶段 ⑤ 纯阶段，各 20 条。
每条原串过 query_filter.txt(keep/排除)，存 keep+reason 供前端展示。
用法：PYTHONPATH=. CK_ENV_FILE=.env python scripts/build_creation_demo.py
"""
from __future__ import annotations

import json
import random
from pathlib import Path

from acquisition.query import ACTIONS, _nonleaf_d4   # 老正交动作轴 + 4级非叶子取作用节点
from acquisition.query import STAGES as OLD_STAGES   # 老的裸阶段 灵感/选题/脚本
from acquisition.query_filter import filter_queries   # 共享筛选器(query_filter.txt)
from core.config import Settings

ROOT = Path(__file__).resolve().parent.parent
TREES = ROOT / "scope_trees" / "trees_index.json"
OUT = ROOT / "data" / "queries" / "creation_demo.json"
PER = 30
BATCH_N = 30        # 全 demo 统一抽这么多个「实质 / 形式」，各族共用同一批；PER=BATCH_N 保证整批都用上、左右一一对应
KTYPE = ["怎么做", "有哪些", "为什么"]
MODALITY = ["视频", "图片"]   # 被创作内容的形态(与教学帖本身格式无关),正交进所有家族
# 创作阶段意图轴(脊柱):灵感/选题/脚本 展开成创作者真会搜的词(query构造.md)。真实数据里
# "脚本"0次、但 开头/钩子/标题/封面/选题 各几十次——故用展开词,不用三个干阶段词。
STAGE_INTENT = {
    "灵感": ["找素材", "内容方向", "案例拆解", "灵感", "拆解", "复盘"],
    "选题": ["选题", "爆款选题", "选题方向"],
    "脚本": ["脚本", "文案", "开头", "钩子", "结构", "标题", "封面", "结尾"],
}
INTENT = [w for ws in STAGE_INTENT.values() for w in ws]   # 扁平成一个池,随机取


def _segs(p):
    return [x for x in (p or "").split("/") if x]


def _leaves(idx, source_type, under=None):
    """某树某支下的叶子节点名(没有更深子节点的=元素层)。under 限定分支。"""
    paths = [(_segs(n["path"]), n.get("name")) for n in idx if n.get("source_type") == source_type]
    if under:
        paths = [(s, nm) for s, nm in paths if under in s]
    allp = {"/".join(s) for s, _ in paths}
    out, seen = [], set()
    for s, nm in paths:
        if len(s) < 2:
            continue
        full = "/".join(s)
        is_leaf = not any(o != full and o.startswith(full + "/") for o in allp)
        name = nm or s[-1]
        if is_leaf and name and name not in seen:
            seen.add(name)
            out.append(name)
    return out


def _nonleaf(idx, source_type, depths=(3, 4), under=None):
    """某树某支下、指定层级的【非叶子"类目"节点】(底下还有元素,不取元素本身)。
    对齐制作侧取法:实质/形式 取 depth 3-4 的类目层,而非最深的元素层。"""
    paths = [(_segs(n["path"]), n.get("name")) for n in idx if n.get("source_type") == source_type]
    if under:
        paths = [(s, nm) for s, nm in paths if under in s]
    allp = {"/".join(s) for s, _ in paths}
    out, seen = [], set()
    for s, nm in paths:
        if len(s) not in depths:
            continue
        full = "/".join(s)
        is_nonleaf = any(o != full and o.startswith(full + "/") for o in allp)
        name = nm or (s[-1] if s else "")
        if is_nonleaf and name and name not in seen:
            seen.add(name)
            out.append(name)
    return out


def main():
    settings = Settings.from_env()
    rng = random.Random(7)
    idx = json.loads(TREES.read_text("utf-8"))
    SHI = _nonleaf(idx, "实质", depths=(3, 4), under="理念")   # 类目层,非元素
    XING = _nonleaf(idx, "形式", depths=(3, 4), under="架构")  # 类目层,非元素
    POOL = _leaves(idx, "作用") + _leaves(idx, "感受") + _leaves(idx, "意图")
    print(f"实质 {len(SHI)} / 形式 {len(XING)} / 目的池 {len(POOL)} / 业务阶段 {len(INTENT)}")

    # 全 demo 统一「一批实质 / 一批形式」——各家族都取同一批、且顺序一致，方便切页签横向比较
    SHI_BATCH = rng.sample(SHI, min(BATCH_N, len(SHI)))
    XING_BATCH = rng.sample(XING, min(BATCH_N, len(XING)))
    print(f"统一批: 实质×{len(SHI_BATCH)} 形式×{len(XING_BATCH)}")

    def pick(seq):
        return rng.choice(seq)

    def shi(i):    # 按 query 序号轮转,保证每族都覆盖整批、首次出现顺序一致
        return SHI_BATCH[i % len(SHI_BATCH)]

    def xing(i):
        return XING_BATCH[i % len(XING_BATCH)]

    # 第六、第七家族(老正交方案)：实质 / 形式 一律沿用上面的统一批(shi/xing，与 f1/f2 完全一致、同序，便于横向对比)；
    # 阶段=灵感/选题/脚本、动作=构思/策划/组织/撰写/改编/润色(+无动作变体)、作用取4级非叶子。query 形如「(实质) 叙事组织 脚本撰写 趣味互动 有哪些」
    F6_ZY = _nonleaf_d4("作用", 10)
    F6_STAGE_ACT = [(s, a) for s in OLD_STAGES for a in ACTIONS] + [("", "")]   # +「无动作」=老方案的 /

    def _old_tail(i):
        st, ac = F6_STAGE_ACT[i % len(F6_STAGE_ACT)]
        zy_ = F6_ZY[i % len(F6_ZY)]
        suf = KTYPE[i % len(KTYPE)]
        seg = (st + ac) if ac else ""                       # 脚本撰写 / 空(动作=/ 时连阶段一起省)
        return st, ac, zy_, suf, seg

    def gen6(i):   # 形式×阶段×动作×作用×知识类型，形式=共享批(同 f2)
        f_ = xing(i)
        st, ac, zy_, suf, seg = _old_tail(i)
        q = " ".join([f_] + ([seg] if seg else []) + [zy_, suf])
        return {"parts": {"形式": f_, "阶段": st or "/", "动作": ac or "/", "作用": zy_, "知识类型": suf}, "query": q}

    def gen7(i):   # 实质×形式×阶段×动作×作用×知识类型，实质=共享批(同 f1)、形式=共享批(同 f2)
        s_, f_ = shi(i), xing(i)
        st, ac, zy_, suf, seg = _old_tail(i)
        q = " ".join([s_, f_] + ([seg] if seg else []) + [zy_, suf])
        return {"parts": {"实质": s_, "形式": f_, "阶段": st or "/", "动作": ac or "/", "作用": zy_, "知识类型": suf}, "query": q}

    # 每家族：生成器 + 用到的轴。家族名 = axes 用「×」连接，直接反映正交结构(见下方循环)。
    # axes 顺序即前端列顺序；业务阶段=脊柱每族必带，模态+知识类型收尾
    families = [
        {"key": "f1", "axes": ["实质", "模态", "业务阶段", "知识类型"],
         "gen": lambda i: {"parts": {"实质": shi(i), "业务阶段": pick(INTENT), "模态": pick(MODALITY), "知识类型": pick(KTYPE)}}},
        {"key": "f2", "axes": ["形式", "模态", "业务阶段", "知识类型"],
         "gen": lambda i: {"parts": {"形式": xing(i), "业务阶段": pick(INTENT), "模态": pick(MODALITY), "知识类型": pick(KTYPE)}}},
        {"key": "f4", "axes": ["作用/感受/意图", "模态", "业务阶段", "知识类型"],
         "gen": lambda i: {"parts": {"目的": pick(POOL), "业务阶段": pick(INTENT), "模态": pick(MODALITY), "知识类型": pick(KTYPE)}}},
        {"key": "f3", "axes": ["实质", "形式", "模态", "业务阶段", "知识类型"],
         "gen": lambda i: {"parts": {"实质": shi(i), "形式": xing(i), "业务阶段": pick(INTENT), "模态": pick(MODALITY), "知识类型": pick(KTYPE)}}},
        {"key": "f5", "axes": ["模态", "业务阶段", "知识类型"],
         "gen": lambda i: {"parts": {"业务阶段": pick(INTENT), "模态": pick(MODALITY), "知识类型": pick(KTYPE)}}},
        {"key": "f6", "axes": ["形式", "阶段", "动作", "作用", "知识类型"], "gen": gen6},
        {"key": "f7", "axes": ["实质", "形式", "阶段", "动作", "作用", "知识类型"], "gen": gen7},
    ]
    # 各部件按固定顺序拼成原串（内容维度在前，模态贴题材后，业务阶段+知识类型收尾）
    order = ["实质", "形式", "目的", "模态", "业务阶段", "知识类型"]

    # 业务阶段值存「分组结构」(STAGE_INTENT)，前端按 灵感/选题/脚本 分组+缩进展示；其余轴是扁平数组
    out = {"axis_values": {"实质": SHI, "形式": XING, "目的池": POOL, "业务阶段": STAGE_INTENT,
                           "模态": MODALITY, "知识类型": KTYPE,
                           "阶段": OLD_STAGES, "动作": ACTIONS, "作用": F6_ZY},   # 第六家族的老轴
           "families": []}
    for fam in families:
        name = " × ".join(fam["axes"])   # 家族名直接反映正交结构
        seen, items = set(), []
        while len(items) < PER and len(seen) < PER * 40:
            g = fam["gen"](len(items))                # 序号轮转实质/形式批
            parts = g["parts"]
            q = g.get("query") or " ".join(parts[k] for k in order if k in parts)   # f6 自带 query 串
            if q in seen:
                continue
            seen.add(q)
            items.append({"query": q, "parts": parts})
        verdicts = filter_queries([it["query"] for it in items], settings)
        for it, v in zip(items, verdicts):
            it.update(v)
        kept = sum(1 for it in items if it["keep"])
        print(f"[{name}] 生成 {len(items)} 条, 筛后保留 {kept}")
        out["families"].append({"key": fam["key"], "name": name, "axes": fam["axes"], "items": items})

    OUT.parent.mkdir(parents=True, exist_ok=True)
    OUT.write_text(json.dumps(out, ensure_ascii=False, indent=1), encoding="utf-8")
    print(f"→ {OUT}")


if __name__ == "__main__":
    main()