You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

73 lines
2.7 KiB

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

import { describe, expect, it } from "vitest";
import { classifyMail } from "@/services/parse/classify";
import { extractMailInstructions } from "@/services/parse/split-instructions";
/** 金样:docx/邮件/模板/附件下载_邮件识别 */
const GOLD_SUBJECT =
"\u667a\u9e3f2+WHLC027G597465+WHSU8127240+\u6d1b\u6749\u77f6+40HQ+EDT2026.04-25 ETA2026.05-15\u8239\u540d\u822a\u6b21HMM EMERALD 013E+\u63d0\u62c6\u6d3e";
const GOLD_BODY = [
"\u8bf7\u67e5\u6536\u65b0\u589e\u9884\u62a5\uff1a\u667a\u9e3f2+WHLC027G597465+WHSU8127240+\u6d1b\u6749\u77f6+40HQ",
"DO\u4e5f\u540c\u6b65\u4e0a\u4f20\u81f3\u9644\u4ef6\u8bf7\u6ce8\u610f\u67e5\u6536\uff01",
].join("\n");
const GOLD_FILES = [
"\u6570\u636e\u6a21\u7248.xlsx",
"WHSU8127240-DO.pdf",
"\u667a\u9e3f2+WHLC027G597465+WHSU8127240+\u6d1b\u6749\u77f6+40HQ+EDT2026.04-25 ETA2026.05-15\u8239\u540d\u822a\u6b21HMM EMERALD 013E+\u63d0\u62c6\u6d3e.xlsx",
];
describe("recognize gold — \u9644\u4ef6\u4e0b\u8f7d_\u90ae\u4ef6\u8bc6\u522b", () => {
it("classify: DO primary + NEW_CONTAINER signals", () => {
const r = classifyMail({
subject: GOLD_SUBJECT,
body: GOLD_BODY,
filenames: GOLD_FILES,
});
expect(r.mail_type).toBe("DO_UPLOAD");
expect(r.scores.DO_UPLOAD).toBeGreaterThanOrEqual(40);
expect(r.scores.NEW_CONTAINER).toBeGreaterThanOrEqual(40);
expect(r.signals.some((s) => s.signal === "\u65b0\u589e\u9884\u62a5")).toBe(
true,
);
expect(r.signals.some((s) => /DO/.test(s.signal))).toBe(true);
});
it("body-only \u65b0\u589e\u9884\u62a5 still scores forecast", () => {
const r = classifyMail({
subject: "WHSU8127240",
body: "\u8bf7\u67e5\u6536\u65b0\u589e\u9884\u62a5",
filenames: ["\u6570\u636e\u6a21\u7248.xlsx"],
});
expect(r.scores.NEW_CONTAINER).toBeGreaterThanOrEqual(40);
expect(r.mail_type).toBe("NEW_CONTAINER");
});
it("\u6570\u636e\u6a21\u7248.xlsx alone can lift forecast", () => {
const r = classifyMail({
subject: "WHSU8127240+40HQ+ETA",
body: "\u8bf7\u67e5\u6536",
filenames: ["\u6570\u636e\u6a21\u7248.xlsx"],
});
expect(r.scores.NEW_CONTAINER).toBeGreaterThanOrEqual(40);
expect(r.mail_type).toBe("NEW_CONTAINER");
});
it("split: forecast + do_upload both current", () => {
const units = extractMailInstructions({
subject: GOLD_SUBJECT,
body: GOLD_BODY,
filenames: GOLD_FILES,
});
const kinds = units.map((u) => u.uiKind);
expect(kinds).toContain("forecast");
expect(kinds).toContain("do_upload");
expect(units.filter((u) => u.uiKind === "forecast")[0]?.isCurrent).toBe(
true,
);
expect(units.filter((u) => u.uiKind === "do_upload")[0]?.isCurrent).toBe(
true,
);
});
});