50 lines
2.7 KiB
TypeScript
50 lines
2.7 KiB
TypeScript
import { writeFileSync } from "node:fs";
|
||
import { pyDumps, readRun, type J } from "./py.ts";
|
||
|
||
// 任务书 15 第 4.3 节的材料：几次运行的全部最终入口（认领时）和第 1 轮提案，写成一个 items.json，交给 jevroutes.ts 问 Jev。
|
||
// 逐行移植对照材料里的 items.py，输出和 Python 的 json.dump(..., ensure_ascii=False, indent=0) 逐字节一致。
|
||
// node eval/route/items.ts <输出 items.json> <运行目录名>...
|
||
// 运行目录是 /home/iomgaa/inforsi-eval/<运行目录名>/study/ledger.sqlite，只读打开。
|
||
|
||
const [out, ...runs] = process.argv.slice(2);
|
||
if (out === undefined || runs.length === 0) throw new Error("用法：node eval/route/items.ts <输出 items.json> <运行目录名>...");
|
||
|
||
function* walk(o: J): Generator<string> {
|
||
if (typeof o === "string") yield o;
|
||
else if (Array.isArray(o)) for (const v of o) yield* walk(v);
|
||
else if (o !== null && typeof o === "object") for (const v of Object.values(o)) yield* walk(v);
|
||
}
|
||
const count = (s: string, sub: string) => s.split(sub).length - 1;
|
||
|
||
const items: Array<Record<string, string>> = [];
|
||
for (const run of runs) {
|
||
const rows = readRun(run);
|
||
// 最终入口：第一条认领调用的记录里，入口全文最多的那段文字，按"### 入口 e-"切开。
|
||
for (const [k, c] of rows) {
|
||
if (k !== "callStarted" || !pyDumps(c, false).includes("r0-claim")) continue;
|
||
let txt = "";
|
||
let best = -1;
|
||
for (const s of walk(c)) {
|
||
const n = count(s, "### 入口 e-");
|
||
if (n > best) [txt, best] = [s, n];
|
||
}
|
||
for (const p of txt.split(/\n(?=### 入口 e-)/).slice(1)) {
|
||
const m = /^### 入口 (e-researcher-\d-\d+)：(.*?)（作者 (researcher-\d)）\n([\s\S]*)/.exec(p);
|
||
if (m === null) throw new Error(`${run} 的认领材料里有一段入口对不上格式：${p.slice(0, 80)}`);
|
||
const body = m[4]!.split("\n## ")[0]!.trim();
|
||
items.push({ run, id: m[1]!, kind: "entry", name: m[2]!, author: m[3]!, text: body });
|
||
}
|
||
break;
|
||
}
|
||
for (const [k, c] of rows) {
|
||
if (k !== "submission" || c.kind !== "proposal") continue;
|
||
const cc = c.content;
|
||
const t = cc.body + "\n\n因子：\n" + cc.factors.map((f: J) => `- ${f.name}：${f.method}`).join("\n");
|
||
items.push({ run, id: c.item, kind: "proposal", name: cc.body.split("\n")[0].replace(/^[# ]+/, ""), author: c.author, text: t });
|
||
}
|
||
}
|
||
const indent0 = (o: Record<string, string>) => "{\n" + Object.entries(o).map(([k, v]) => `${pyDumps(k, false)}: ${pyDumps(v, false)}`).join(",\n") + "\n}";
|
||
writeFileSync(out, "[\n" + items.map(indent0).join(",\n") + "\n]");
|
||
console.log(items.length);
|
||
items.forEach((x, i) => console.log(i, x["run"]!.slice(11), x["id"], [...x["text"]!].length, [...x["name"]!].slice(0, 70).join("")));
|