Files
koc-loop/app/api/resources-import/route.ts
2026-08-11 23:07:26 +08:00

303 lines
11 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import { isManagerRequest, managerForbidden } from "../../../lib/user-auth";
import { ensureSchema, getRawDb } from "../../../lib/mvp-db";
import {
resolveCollectionMcpConfig,
resolveXhsProfileDetailsFromMcp,
resolveXhsPublicAccountDetails,
type CollectionMcpBindings,
} from "../../../lib/mcp-collection-client";
import { getRuntimeEnv } from "../../../lib/runtime-env";
import {
mergeCooperationSources,
normalizeProfileUrl,
parseResourceImportFile,
RESOURCE_IMPORT_MAX_BYTES,
resourcePlatformUid,
type ResourceImportRow,
} from "../../../lib/resource-import";
type AccountRow = {
id: string;
platform: string;
platform_uid: string;
public_account_id: string;
nickname: string;
profile_url: string;
ip_location: string;
followers: number;
cooperation_source: string;
};
type AnalyzedRow = ResourceImportRow & {
action: "create" | "update" | "error";
accountId: string;
platformUid: string;
cooperationSource: string;
};
function identityKey(platform: string, value: string) {
return `${platform.trim().toLocaleLowerCase("zh-CN")}|${value
.trim()
.toLocaleLowerCase("zh-CN")}`;
}
async function loadAccounts() {
return getRawDb()
.prepare(
`SELECT id, platform, platform_uid, public_account_id, nickname,
profile_url, ip_location, followers, cooperation_source
FROM accounts`,
)
.all<AccountRow>();
}
async function mapConcurrent<T, R>(
items: T[],
limit: number,
worker: (item: T) => Promise<R>,
) {
const results = new Array<R>(items.length);
let cursor = 0;
await Promise.all(
Array.from({ length: Math.min(limit, items.length) }, async () => {
while (cursor < items.length) {
const index = cursor;
cursor += 1;
results[index] = await worker(items[index]);
}
}),
);
return results;
}
async function enrichRows(rows: ResourceImportRow[], accounts: AccountRow[]) {
const existingByProfile = new Map<string, AccountRow>();
for (const account of accounts) {
const profileUrl = normalizeProfileUrl(account.profile_url || "");
if (profileUrl) {
existingByProfile.set(identityKey(account.platform, profileUrl), account);
}
}
const mcpConfig = resolveCollectionMcpConfig(
getRuntimeEnv() as unknown as CollectionMcpBindings,
);
return mapConcurrent(rows, 4, async (row) => {
if (row.errors.length > 0 || !row.profileUrl || row.platform !== "小红书") {
return row;
}
const existing = existingByProfile.get(identityKey(row.platform, row.profileUrl));
if (existing?.nickname && existing.public_account_id) {
return {
...row,
nickname: existing.nickname,
publicAccountId: existing.public_account_id,
ipLocation: existing.ip_location || "待识别",
followers: Number(existing.followers || 0),
};
}
let details = await resolveXhsProfileDetailsFromMcp(row.profileUrl, mcpConfig)
.catch(() => resolveXhsPublicAccountDetails(row.profileUrl));
if (!details.nickname || !details.redId || details.followers === null) {
const publicDetails = await resolveXhsPublicAccountDetails(row.profileUrl);
details = {
nickname: details.nickname || publicDetails.nickname,
redId: details.redId || publicDetails.redId,
followers: details.followers ?? publicDetails.followers,
ipLocation: details.ipLocation || publicDetails.ipLocation,
};
}
const errors = [...row.errors];
const nickname = details.nickname?.trim() || existing?.nickname || "";
const publicAccountId = details.redId?.trim() || existing?.public_account_id || "";
if (!nickname) errors.push("无法识别账号名称,请确认主页可公开访问");
if (!publicAccountId) errors.push("无法识别小红书号,请确认主页可公开访问");
return {
...row,
nickname,
publicAccountId,
ipLocation: details.ipLocation?.trim() || existing?.ip_location || "待识别",
followers: details.followers ?? Number(existing?.followers || 0),
errors,
};
});
}
function analyzeRows(rows: ResourceImportRow[], accountRows: AccountRow[]) {
const profileMap = new Map<string, AccountRow>();
const publicIdMap = new Map<string, AccountRow>();
const platformUidMap = new Map<string, AccountRow>();
for (const account of accountRows) {
const profileUrl = normalizeProfileUrl(account.profile_url || "");
if (profileUrl) profileMap.set(identityKey(account.platform, profileUrl), account);
if (account.public_account_id) {
publicIdMap.set(identityKey(account.platform, account.public_account_id), account);
}
platformUidMap.set(identityKey(account.platform, account.platform_uid), account);
}
return rows.map<AnalyzedRow>((row) => {
const platformUid = resourcePlatformUid(row);
const profileMatch = row.profileUrl
? profileMap.get(identityKey(row.platform, row.profileUrl))
: undefined;
const publicIdMatch = row.publicAccountId
? publicIdMap.get(identityKey(row.platform, row.publicAccountId))
: undefined;
const uidMatch = platformUidMap.get(identityKey(row.platform, platformUid));
const matches = [profileMatch, publicIdMatch, uidMatch].filter(
(account): account is AccountRow => Boolean(account),
);
const matchedIds = [...new Set(matches.map((account) => account.id))];
const errors = [...row.errors];
if (matchedIds.length > 1) {
errors.push("账号主页和账号ID匹配到不同的现有账号请先核对");
}
const existing = matchedIds.length === 1 ? matches[0] : undefined;
const accountId = existing?.id ?? `account-${crypto.randomUUID().slice(0, 12)}`;
const analyzed: AnalyzedRow = {
...row,
errors,
action: errors.length > 0 ? "error" : existing ? "update" : "create",
accountId,
platformUid: existing?.platform_uid ?? platformUid,
cooperationSource: mergeCooperationSources(
existing?.cooperation_source ?? "",
row.cooperationSource,
),
};
if (analyzed.action !== "error") {
const virtual: AccountRow = {
id: accountId,
platform: row.platform,
platform_uid: analyzed.platformUid,
public_account_id: row.publicAccountId || existing?.public_account_id || "",
nickname: row.nickname,
profile_url: row.profileUrl || existing?.profile_url || "",
ip_location: row.ipLocation || existing?.ip_location || "待识别",
followers: row.followers || existing?.followers || 0,
cooperation_source: analyzed.cooperationSource,
};
if (row.profileUrl) profileMap.set(identityKey(row.platform, row.profileUrl), virtual);
if (row.publicAccountId) {
publicIdMap.set(identityKey(row.platform, row.publicAccountId), virtual);
}
platformUidMap.set(identityKey(row.platform, analyzed.platformUid), virtual);
}
return analyzed;
});
}
function summarize(rows: AnalyzedRow[]) {
return {
total: rows.length,
create: rows.filter((row) => row.action === "create").length,
update: rows.filter((row) => row.action === "update").length,
error: rows.filter((row) => row.action === "error").length,
};
}
export async function POST(request: Request) {
if (!(await isManagerRequest(request))) return managerForbidden();
try {
await ensureSchema();
const form = await request.formData();
const file = form.get("file");
const mode = String(form.get("mode") ?? "preview");
if (!(file instanceof File)) {
return Response.json({ error: "请选择需要导入的 Excel 文件" }, { status: 400 });
}
if (file.size <= 0 || file.size > RESOURCE_IMPORT_MAX_BYTES) {
return Response.json({ error: "文件不能为空,且不能超过 5MB" }, { status: 400 });
}
const rows = parseResourceImportFile(file.name, new Uint8Array(await file.arrayBuffer()));
const accounts = await loadAccounts();
const enriched = await enrichRows(rows, accounts.results);
const analyzed = analyzeRows(enriched, accounts.results);
const summary = summarize(analyzed);
if (mode !== "commit") {
return Response.json({
summary,
rows: analyzed.slice(0, 100).map((row) => ({
rowNumber: row.rowNumber,
platform: row.platform,
nickname: row.nickname,
publicAccountId: row.publicAccountId,
profileUrl: row.profileUrl,
ipLocation: row.ipLocation,
followers: row.followers,
cooperationSource: row.cooperationSource,
action: row.action,
errors: row.errors,
})),
truncated: analyzed.length > 100,
});
}
if (summary.error > 0) {
return Response.json(
{ error: `${summary.error} 行数据未通过校验,请修正后重新上传`, summary },
{ status: 400 },
);
}
const db = getRawDb();
const statements = analyzed.map((row) =>
row.action === "update"
? db
.prepare(
`UPDATE accounts SET
nickname = ?,
public_account_id = CASE WHEN ? != '' THEN ? ELSE public_account_id END,
profile_url = CASE WHEN ? != '' THEN ? ELSE profile_url END,
ip_location = CASE
WHEN ? != '' AND ? != '待识别' THEN ? ELSE ip_location END,
followers = CASE WHEN ? > 0 OR followers = 0 THEN ? ELSE followers END,
cooperation_source = ?,
last_seen_at = CURRENT_TIMESTAMP
WHERE id = ?`,
)
.bind(
row.nickname,
row.publicAccountId,
row.publicAccountId,
row.profileUrl,
row.profileUrl,
row.ipLocation,
row.ipLocation,
row.ipLocation,
row.followers,
row.followers,
row.cooperationSource,
row.accountId,
)
: db
.prepare(
`INSERT INTO accounts
(id, platform, platform_uid, public_account_id, nickname,
profile_url, ip_location, followers, post_count, avg_views,
cooperation_source)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, 0, 0, ?)`,
)
.bind(
row.accountId,
row.platform,
row.platformUid,
row.publicAccountId,
row.nickname,
row.profileUrl,
row.ipLocation,
row.followers,
row.cooperationSource,
),
);
if (statements.length > 0) await db.batch(statements);
return Response.json({
summary,
message: `已导入 ${summary.create} 个新账号,更新 ${summary.update} 个已有账号`,
});
} catch (error) {
const message = error instanceof Error ? error.message : "导入失败";
return Response.json({ error: message }, { status: 400 });
}
}