koc-loop/tests/resource-import.test.mjs

import assert from "node:assert/strict";
import test from "node:test";
import { strFromU8, strToU8, unzipSync, zipSync } from "fflate";
import { buildRecoveryWorkbook } from "../lib/recovery-workbook.ts";
import {
  RESOURCE_IMPORT_MAX_ROWS,
  mergeCooperationSources,
  normalizeProfileUrl,
  parseResourceFollowers,
  parseResourceImportFile,
  resourceImportMissingFields,
  resourcePlatformUid,
} from "../lib/resource-import.ts";

test("accepts several thousand accounts in one import file", () => {
  const csv = [
    "账号主页,账号昵称,账号ID,IP属地,粉丝数,合作来源",
    ...Array.from({ length: 3_000 }, (_, index) => {
      const id = String(index + 1).padStart(6, "0");
      return `https://www.xiaohongshu.com/user/profile/bulk${id},账号${id},${id},上海,100,批量资源`;
    }),
  ].join("\n");
  const rows = parseResourceImportFile(
    "bulk-resources.csv",
    new TextEncoder().encode(csv),
  );

  assert.equal(RESOURCE_IMPORT_MAX_ROWS, 10_000);
  assert.equal(rows.length, 3_000);
  assert.equal(rows[0].rowNumber, 2);
  assert.equal(rows.at(-1)?.rowNumber, 3_001);
  assert.equal(rows.every((row) => row.errors.length === 0), true);
});

test("parses several thousand accounts from an XLSX workbook", () => {
  const workbook = buildRecoveryWorkbook({
    sheetName: "KOC资源导入",
    headers: ["账号主页", "账号昵称", "账号ID", "IP属地", "粉丝数", "合作来源"],
    columnWidths: [48, 24, 20, 16, 14, 24],
    rows: Array.from({ length: 3_000 }, (_, index) => {
      const id = String(index + 1).padStart(6, "0");
      return {
        cells: [
          `https://www.xiaohongshu.com/user/profile/xlsx${id}`,
          `账号${id}`,
          id,
          "北京",
          200,
          "Excel批量资源",
        ],
        images: [],
      };
    }),
  });
  const rows = parseResourceImportFile("bulk-resources.xlsx", workbook);

  assert.equal(rows.length, 3_000);
  assert.equal(rows[0].profileUrl.endsWith("xlsx000001"), true);
  assert.equal(rows.at(-1)?.profileUrl.endsWith("xlsx003000"), true);
});

test("keeps a bounded 10,000-row safety limit", () => {
  const csv = [
    "账号主页",
    ...Array.from(
      { length: RESOURCE_IMPORT_MAX_ROWS + 1 },
      (_, index) => `https://www.douyin.com/user/bulk-account-${index + 1}`,
    ),
  ].join("\n");

  assert.throws(
    () =>
      parseResourceImportFile(
        "too-many-resources.csv",
        new TextEncoder().encode(csv),
      ),
    /单次最多导入 10000 个账号/,
  );
});

test("parses CSV resources and normalizes public profile data", () => {
  const csv = [
    "账号主页,合作来源",
    '"主页：https://www.xiaohongshu.com/user/profile/abc123?xsec_token=secret",林林KOC社群',
  ].join("\n");
  const rows = parseResourceImportFile("resources.csv", new TextEncoder().encode(csv));
  assert.equal(rows.length, 1);
  assert.deepEqual(rows[0], {
    rowNumber: 2,
    platform: "小红书",
    nickname: "",
    publicAccountId: "",
    profileUrl: "https://www.xiaohongshu.com/user/profile/abc123",
    ipLocation: "",
    followers: 0,
    followersResolved: false,
    gender: "",
    bio: "",
    tags: [],
    cooperationSource: "林林KOC社群",
    errors: [],
  });
  assert.equal(resourcePlatformUid(rows[0]), "abc123");
});

test("uses optional account fields directly and only requires the profile URL", () => {
  const csv = [
    "账号链接,账号昵称,账号ID,IP属地,粉丝数,性别,简介,标签,合作来源",
    "https://www.xiaohongshu.com/user/profile/abc123,番茄不炒蛋,4171542126,江西,10+,女,分享江西本地生活,本地生活、美食探店,历史资源",
  ].join("\n");
  const [row] = parseResourceImportFile(
    "resources.csv",
    new TextEncoder().encode(csv),
  );
  assert.equal(row.nickname, "番茄不炒蛋");
  assert.equal(row.publicAccountId, "4171542126");
  assert.equal(row.ipLocation, "江西");
  assert.equal(row.followers, 10);
  assert.equal(row.followersResolved, true);
  assert.equal(row.gender, "女");
  assert.equal(row.bio, "分享江西本地生活");
  assert.deepEqual(row.tags, ["本地生活", "美食探店"]);
  assert.deepEqual(resourceImportMissingFields(row), []);
});

test("validates optional gender", () => {
  const csv = [
    "账号链接,性别,标签",
    "https://www.xiaohongshu.com/user/profile/abc123,其他,美食探店",
  ].join("\n");
  const [row] = parseResourceImportFile(
    "resources.csv",
    new TextEncoder().encode(csv),
  );
  assert.match(row.errors.join("；"), /性别格式不正确/);
});

test("rejects more than five tags in one optional tag cell", () => {
  const csv = [
    "账号链接,标签",
    'https://www.xiaohongshu.com/user/profile/abc123,"美食探店,旅游出行,数码产品,本地生活,婚嫁备婚,美妆护肤"',
  ].join("\n");
  const [row] = parseResourceImportFile(
    "resources.csv",
    new TextEncoder().encode(csv),
  );
  assert.match(row.errors.join("；"), /最多填写 5 个标签/);
});

test("normalizes common follower formats and identifies missing enrichment fields", () => {
  assert.deepEqual(parseResourceFollowers("1.3万"), {
    value: 13_000,
    resolved: true,
    valid: true,
  });
  assert.deepEqual(parseResourceFollowers("10+"), {
    value: 10,
    resolved: true,
    valid: true,
  });
  assert.deepEqual(parseResourceFollowers(""), {
    value: 0,
    resolved: false,
    valid: true,
  });
});

test("parses the first matching worksheet from an XLSX workbook", () => {
  const workbook = buildRecoveryWorkbook({
    sheetName: "KOC资源导入",
    headers: ["账号主页", "合作来源"],
    columnWidths: [48, 24],
    rows: [
      {
        cells: ["https://www.xiaohongshu.com/user/profile/abc123", "存量资源包"],
        images: [],
      },
    ],
  });
  const rows = parseResourceImportFile("resources.xlsx", workbook);
  assert.equal(rows[0].platform, "小红书");
  assert.equal(rows[0].cooperationSource, "存量资源包");
  assert.equal(rows[0].errors.length, 0);
  assert.equal(rows[0].followersResolved, false);
});

test("keeps values in their columns after a self-closing blank XLSX cell", () => {
  const workbook = buildRecoveryWorkbook({
    sheetName: "KOC资源导入",
    headers: ["账号主页", "账号昵称", "账号ID", "IP属地", "粉丝数", "合作来源"],
    columnWidths: [48, 24, 20, 16, 14, 24],
    rows: [
      {
        cells: [
          "https://www.xiaohongshu.com/user/profile/blank-ip-cell",
          "空白IP账号",
          "123456789",
          "",
          10,
          "",
        ],
        images: [],
      },
    ],
  });
  const entries = unzipSync(workbook);
  const sheetPath = "xl/worksheets/sheet1.xml";
  const sheetXml = strFromU8(entries[sheetPath]);
  entries[sheetPath] = strToU8(
    sheetXml.replace('<c r="E2"', '<c r="D2"/><c r="E2"'),
  );

  const [row] = parseResourceImportFile(
    "self-closing-blank.xlsx",
    zipSync(entries),
  );
  assert.equal(row.ipLocation, "");
  assert.equal(row.followers, 10);
  assert.equal(row.followersResolved, true);
  assert.deepEqual(row.errors, []);
});

test("reports invalid required fields without hiding valid rows", () => {
  const csv = "账号主页,合作来源\n,历史资源\nhttps://www.douyin.com/user/demo,社群\nhttps://example.com/user/demo,其他";
  const rows = parseResourceImportFile("resources.csv", new TextEncoder().encode(csv));
  assert.match(rows[0].errors.join("；"), /账号主页不能为空/);
  assert.equal(rows[1].platform, "抖音");
  assert.equal(rows[1].errors.length, 0);
  assert.match(rows[2].errors.join("；"), /仅支持小红书或抖音账号主页/);
});

test("rejects invalid optional follower values without requiring other optional fields", () => {
  const csv = [
    "账号链接,粉丝数",
    "https://www.xiaohongshu.com/user/profile/abc123,很多",
  ].join("\n");
  const [row] = parseResourceImportFile(
    "resources.csv",
    new TextEncoder().encode(csv),
  );
  assert.match(row.errors.join("；"), /粉丝数格式不正确/);
});

test("rejects a numeric value entered as an IP location", () => {
  const csv = [
    "账号链接,IP属地,粉丝数",
    "https://www.xiaohongshu.com/user/profile/abc123,10,100",
  ].join("\n");
  const [row] = parseResourceImportFile(
    "resources.csv",
    new TextEncoder().encode(csv),
  );
  assert.match(row.errors.join("；"), /IP属地格式不正确/);
});

test("normalizes profile URLs and merges cooperation sources", () => {
  assert.equal(
    normalizeProfileUrl("https://www.xiaohongshu.com/user/profile/abc/?foo=1#top"),
    "https://www.xiaohongshu.com/user/profile/abc",
  );
  assert.equal(
    mergeCooperationSources("林林社群、木子", "木子；历史表格"),
    "林林社群、木子、历史表格",
  );
});