70 lines
3.7 KiB
TypeScript
70 lines
3.7 KiB
TypeScript
import { writeFileSync } from "node:fs";
|
||
import { pyDumps, pyRepr, readRun, type J } from "./py.ts";
|
||
|
||
// 任务书 15 第 4.1 节：把一次运行的第零轮和第 1 轮导出成一份纯文本，供子 Agent 按附录一问卷阅读。
|
||
// 逐行移植对照材料里的 extract.py，输出逐字节一致（含原脚本的写法：结尾不带换行；
|
||
// 认领入口名是从调用记录的 JSON 文字里用正则抠的，名字里的引号、换行会带着 JSON 转义）。
|
||
// node eval/route/extract.ts <运行目录名> <输出文件>
|
||
// 运行目录是 /home/iomgaa/inforsi-eval/<运行目录名>/study/ledger.sqlite，只读打开。
|
||
|
||
const [run, out] = process.argv.slice(2);
|
||
if (run === undefined || out === undefined) throw new Error("用法：node eval/route/extract.ts <运行目录名> <输出文件>");
|
||
const rows = readRun(run);
|
||
const L: string[] = [];
|
||
const subs: J[] = rows.filter(([k]) => k === "submission").map(([, c]) => c);
|
||
const decisions = (name: string): J[] => rows.filter(([k, c]) => k === "decision" && c.decision === name).map(([, c]) => c);
|
||
|
||
L.push(`# 运行 ${run}\n`);
|
||
L.push("## 第零轮 一、闭门写的入口（每人按自己写的先后）\n");
|
||
for (const s of subs) {
|
||
if (s.kind !== "entry") continue;
|
||
L.push(`### ${s.author}（第 ${s.version} 版）`);
|
||
s.content.entries.forEach((e: J, i: number) => L.push(`#### 第 ${i + 1} 个：${e.name}\n${e.body}\n`));
|
||
}
|
||
L.push("## 第零轮 二、讨论（按提交先后）\n");
|
||
for (const s of subs) {
|
||
if (s.kind !== "discussion") continue;
|
||
L.push(`### ${s.author}（${s.stageId}，第 ${s.version} 版）\n${s.content.body ?? ""}\n`);
|
||
if (s.content.entries?.length) {
|
||
L.push("换成的新入口清单：");
|
||
s.content.entries.forEach((e: J, i: number) => L.push(`#### 新第 ${i + 1} 个：${e.name}\n${e.body}\n`));
|
||
}
|
||
}
|
||
// 认领时的最终入口编号：从第一条认领调用的记录（材料里的入口全文）里抠出来。
|
||
const names = new Map<string, [string, string]>();
|
||
for (const [k, c] of rows) {
|
||
if (k !== "callStarted") continue;
|
||
const txt = pyDumps(c, false);
|
||
if (!txt.includes("r0-claim")) continue;
|
||
for (const m of txt.matchAll(/### 入口 (e-researcher-\d-\d+)：(.*?)（作者 (researcher-\d)）/g)) names.set(m[1]!, [m[2]!, m[3]!]);
|
||
break;
|
||
}
|
||
L.push("## 第零轮 三、认领时的最终入口编号\n");
|
||
for (const [i, [n, a]] of names) L.push(`- ${i}（作者 ${a}）：${n}`);
|
||
L.push("\n## 第零轮 四、志愿与分配\n");
|
||
for (const s of subs) if (s.kind === "claim") L.push(`- ${s.author} 志愿：${s.content.choices.join(" > ")}`);
|
||
for (const c of decisions("entries")) L.push("分配：" + pyDumps(c.output, false));
|
||
|
||
const props = subs.filter((s) => s.kind === "proposal");
|
||
if (props.length > 0) {
|
||
L.push("\n## 第 1 轮 一、提案全文\n");
|
||
for (const s of props) {
|
||
L.push(`### ${s.item}（作者 ${s.author}）\n${s.content.body}\n`);
|
||
L.push("因子：");
|
||
for (const f of s.content.factors) L.push(`- ${f.name}：${f.method}`);
|
||
L.push("");
|
||
}
|
||
for (const c of decisions("dedup")) L.push("判重：" + pyDumps(c.output, false));
|
||
for (const kind of ["firstPrediction", "secondPrediction"]) {
|
||
L.push(`\n## 第 1 轮 ${kind} 三个数（作者→候选）`);
|
||
for (const s of subs) if (s.kind === kind) L.push(`- ${s.author} → ${s.target}：${pyRepr(s.content.range)}`);
|
||
}
|
||
for (const c of decisions("batch")) {
|
||
const merged = c.output.candidates.map((x: J) => [x.id, x.merged]);
|
||
L.push("\n选批：入选 " + pyRepr(c.output.chosen) + "；合并范围 " + pyDumps(merged, true));
|
||
}
|
||
L.push("\n## 附：第二次预测正文（看研究者如何判断风险）\n");
|
||
for (const s of subs) if (s.kind === "secondPrediction") L.push(`### ${s.author} → ${s.target}\n${s.content.body}\n`);
|
||
}
|
||
writeFileSync(out, L.join("\n"));
|