319 lines
14 KiB
Python
319 lines
14 KiB
Python
|
"""
|
|||
|
|
把 Artalk 导出的 .artrans 转成可直接灌进 Cloudflare D1 的 SQL。
|
|||
|
|
|
|||
|
|
为什么不用 Worker 的 /transfer/import：
|
|||
|
|
3440 条评论逐条 INSERT 会产生 3440 次 D1 往返，Worker 免费版单请求 CPU 只有 10ms，
|
|||
|
|
很容易直接超时。批量导入走 wrangler d1 execute --file 最稳、最快。
|
|||
|
|
|
|||
|
|
用法：
|
|||
|
|
python tools/import_artrans.py # 默认只导「优世界」
|
|||
|
|
python tools/import_artrans.py --site 优世界 --src <path.artrans> --out out/
|
|||
|
|
# 然后：
|
|||
|
|
# npx wrangler d1 execute artalk-cf --remote --file=out/import-01-users.sql
|
|||
|
|
# ... 按生成的 run.sh 顺序执行
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
import argparse
|
|||
|
|
import json
|
|||
|
|
import pathlib
|
|||
|
|
import sys
|
|||
|
|
from collections import OrderedDict
|
|||
|
|
|
|||
|
|
DEFAULT_SRC = "" # 不写死机器路径；用 --src <path.artrans> 显式传入
|
|||
|
|
DEFAULT_SITE = "优世界"
|
|||
|
|
DEFAULT_SITE_URL = "https://usj.cc"
|
|||
|
|
|
|||
|
|
CHUNK = 400 # 每个 SQL 文件最多多少条语句，避免单次 execute 过大
|
|||
|
|
|
|||
|
|
|
|||
|
|
def sql_str(v) -> str:
|
|||
|
|
if v is None:
|
|||
|
|
return "NULL"
|
|||
|
|
s = str(v)
|
|||
|
|
return "'" + s.replace("'", "''") + "'"
|
|||
|
|
|
|||
|
|
|
|||
|
|
def sql_bool(v) -> str:
|
|||
|
|
return "1" if str(v).lower() in ("true", "1", "yes") else "0"
|
|||
|
|
|
|||
|
|
|
|||
|
|
def sql_int(v, dft=0) -> str:
|
|||
|
|
try:
|
|||
|
|
return str(int(str(v).strip()))
|
|||
|
|
except Exception:
|
|||
|
|
return str(dft)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def parse_dt(s: str) -> int:
|
|||
|
|
"""'2021-09-11 20:33:56 +0800 +0800' -> unix 毫秒（+0800）"""
|
|||
|
|
s = (s or "").strip()
|
|||
|
|
if len(s) < 19:
|
|||
|
|
return 0
|
|||
|
|
try:
|
|||
|
|
import datetime as dt
|
|||
|
|
|
|||
|
|
naive = dt.datetime.strptime(s[:19], "%Y-%m-%d %H:%M:%S")
|
|||
|
|
aware = naive.replace(tzinfo=dt.timezone(dt.timedelta(hours=8)))
|
|||
|
|
ms = int(aware.timestamp() * 1000)
|
|||
|
|
return ms if ms > 0 else 0
|
|||
|
|
except Exception:
|
|||
|
|
return 0
|
|||
|
|
|
|||
|
|
|
|||
|
|
def write_chunks(out_dir: pathlib.Path, name: str, stmts: list) -> list:
|
|||
|
|
"""把语句按 CHUNK 切成多个 .sql，返回生成的文件名列表"""
|
|||
|
|
files = []
|
|||
|
|
for i in range(0, len(stmts), CHUNK):
|
|||
|
|
part = stmts[i : i + CHUNK]
|
|||
|
|
fn = f"{name}-{i // CHUNK + 1:03d}.sql"
|
|||
|
|
(out_dir / fn).write_text("\n".join(part) + "\n", encoding="utf-8", newline="\n")
|
|||
|
|
files.append(fn)
|
|||
|
|
return files
|
|||
|
|
|
|||
|
|
|
|||
|
|
def main() -> int:
|
|||
|
|
ap = argparse.ArgumentParser()
|
|||
|
|
ap.add_argument("--src", default=DEFAULT_SRC)
|
|||
|
|
ap.add_argument("--site", default=DEFAULT_SITE, help="只导这个站点名，逗号分隔可多个；all = 全导")
|
|||
|
|
ap.add_argument("--site-url", default=DEFAULT_SITE_URL)
|
|||
|
|
ap.add_argument("--out", default="tools/import-out")
|
|||
|
|
ap.add_argument("--db", default="artalk-cf", help="wrangler d1 的数据库名")
|
|||
|
|
args = ap.parse_args()
|
|||
|
|
|
|||
|
|
src = pathlib.Path(args.src)
|
|||
|
|
if not args.src:
|
|||
|
|
print("请用 --src <path.artrans> 指定导出的 .artrans 文件路径", file=sys.stderr)
|
|||
|
|
return 1
|
|||
|
|
if not src.exists():
|
|||
|
|
print(f"找不到源文件: {src}", file=sys.stderr)
|
|||
|
|
return 1
|
|||
|
|
|
|||
|
|
data = json.loads(src.read_text(encoding="utf-8"))
|
|||
|
|
want = None if args.site.strip().lower() == "all" else [s.strip() for s in args.site.split(",") if s.strip()]
|
|||
|
|
site_name = want[0] if want else DEFAULT_SITE
|
|||
|
|
|
|||
|
|
items = [c for c in data if (want is None or c.get("site_name") in want)]
|
|||
|
|
print(f"源文件 {len(data)} 条，按站点筛选后 {len(items)} 条 -> 归入站点「{site_name}」")
|
|||
|
|
if not items:
|
|||
|
|
print("筛选后为空，检查 --site", file=sys.stderr)
|
|||
|
|
return 1
|
|||
|
|
|
|||
|
|
out_dir = pathlib.Path(args.out)
|
|||
|
|
out_dir.mkdir(parents=True, exist_ok=True)
|
|||
|
|
|
|||
|
|
# ---------------- 站点
|
|||
|
|
head = [
|
|||
|
|
"-- =====================================================================",
|
|||
|
|
"-- ⚠️ 这个文件会先清空 comments / pages / users / sites 四张表。",
|
|||
|
|
"-- 只在**首次导入到全新数据库**时执行；库里已有数据请勿再跑。",
|
|||
|
|
"-- =====================================================================",
|
|||
|
|
"DELETE FROM comments;",
|
|||
|
|
"DELETE FROM pages;",
|
|||
|
|
"DELETE FROM users;",
|
|||
|
|
"DELETE FROM sites;",
|
|||
|
|
f"INSERT INTO sites (id, name, urls, created_at, updated_at) "
|
|||
|
|
f"VALUES (1, {sql_str(site_name)}, {sql_str(args.site_url)}, "
|
|||
|
|
f"{parse_dt(max((c.get('created_at') or '') for c in items)) or 0}, 0);",
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
# ---------------- 用户（按 nick+email 去重）
|
|||
|
|
users = OrderedDict()
|
|||
|
|
for c in items:
|
|||
|
|
nick = (c.get("nick") or "").strip()
|
|||
|
|
email = (c.get("email") or "").strip()
|
|||
|
|
if not nick or not email:
|
|||
|
|
continue
|
|||
|
|
users.setdefault(f"{nick}\u0000{email}", {"nick": nick, "email": email, "link": c.get("link") or "",
|
|||
|
|
"badge_name": c.get("badge_name") or "",
|
|||
|
|
"badge_color": c.get("badge_color") or ""})
|
|||
|
|
|
|||
|
|
user_id = {}
|
|||
|
|
user_stmts = ["-- 用户（原数据没有注册账号，全部按 昵称+邮箱 去重重建）"]
|
|||
|
|
for idx, (key, u) in enumerate(users.items(), start=1):
|
|||
|
|
user_id[key] = idx
|
|||
|
|
ts = next((parse_dt(c.get("created_at")) for c in items
|
|||
|
|
if (c.get("nick") or "").strip() == u["nick"] and (c.get("email") or "").strip() == u["email"]), 0)
|
|||
|
|
user_stmts.append(
|
|||
|
|
"INSERT INTO users (id, name, email, link, badge_name, badge_color, receive_email, created_at, updated_at) "
|
|||
|
|
f"VALUES ({idx}, {sql_str(u['nick'])}, {sql_str(u['email'])}, {sql_str(u['link'])}, "
|
|||
|
|
f"{sql_str(u['badge_name'])}, {sql_str(u['badge_color'])}, 1, {ts or 0}, {ts or 0});"
|
|||
|
|
)
|
|||
|
|
print(f"用户 {len(users)} 个")
|
|||
|
|
|
|||
|
|
# ---------------- 页面
|
|||
|
|
pages = OrderedDict()
|
|||
|
|
for c in items:
|
|||
|
|
key = (c.get("page_key") or "").strip()
|
|||
|
|
if not key:
|
|||
|
|
continue
|
|||
|
|
pages.setdefault(key, {"title": c.get("page_title") or "", "admin_only": c.get("page_admin_only"),
|
|||
|
|
"created_at": parse_dt(c.get("created_at"))})
|
|||
|
|
|
|||
|
|
page_id = {}
|
|||
|
|
page_stmts = ["-- 页面"]
|
|||
|
|
for idx, (key, p) in enumerate(pages.items(), start=1):
|
|||
|
|
page_id[key] = idx
|
|||
|
|
page_stmts.append(
|
|||
|
|
"INSERT INTO pages (id, key, site_name, title, admin_only, created_at, updated_at) "
|
|||
|
|
f"VALUES ({idx}, {sql_str(key)}, {sql_str(site_name)}, {sql_str(p['title'])}, "
|
|||
|
|
f"{sql_bool(p['admin_only'])}, {p['created_at'] or 0}, {p['created_at'] or 0});"
|
|||
|
|
)
|
|||
|
|
print(f"页面 {len(pages)} 个")
|
|||
|
|
|
|||
|
|
# ---------------- 评论（保留原始 id，保证 rid 关系不变）
|
|||
|
|
rid_of = {}
|
|||
|
|
rows = []
|
|||
|
|
skip_no_id = skip_no_page = skip_no_user = 0
|
|||
|
|
for c in items:
|
|||
|
|
try:
|
|||
|
|
cid = int(str(c.get("id")))
|
|||
|
|
except Exception:
|
|||
|
|
skip_no_id += 1
|
|||
|
|
continue
|
|||
|
|
try:
|
|||
|
|
rid = int(str(c.get("rid") or 0))
|
|||
|
|
except Exception:
|
|||
|
|
rid = 0
|
|||
|
|
key = f"{(c.get('nick') or '').strip()}\u0000{(c.get('email') or '').strip()}"
|
|||
|
|
pk = (c.get("page_key") or "").strip()
|
|||
|
|
if not pk:
|
|||
|
|
skip_no_page += 1
|
|||
|
|
continue
|
|||
|
|
if key not in user_id:
|
|||
|
|
skip_no_user += 1
|
|||
|
|
continue
|
|||
|
|
rid_of[cid] = rid
|
|||
|
|
rows.append({
|
|||
|
|
"id": cid, "rid": rid, "uid": user_id[key], "pid": page_id[pk], "page_key": pk,
|
|||
|
|
"content": c.get("content") or "",
|
|||
|
|
"is_collapsed": c.get("is_collapsed"), "is_pending": c.get("is_pending"),
|
|||
|
|
"is_pinned": c.get("is_pinned"), "vote_up": c.get("vote_up"), "vote_down": c.get("vote_down"),
|
|||
|
|
"ua": c.get("ua") or "", "ip": c.get("ip") or "",
|
|||
|
|
"created_at": parse_dt(c.get("created_at")), "updated_at": parse_dt(c.get("updated_at")),
|
|||
|
|
})
|
|||
|
|
|
|||
|
|
# 只保留指向本批次内评论的 rid，避免指到没导进来的兄弟站点评论
|
|||
|
|
ids = {r["id"] for r in rows}
|
|||
|
|
for r in rows:
|
|||
|
|
if r["rid"] and r["rid"] not in ids:
|
|||
|
|
r["rid"] = 0
|
|||
|
|
|
|||
|
|
# 计算 root（沿 rid 链上溯到「rid==0 的那条顶层评论」）
|
|||
|
|
#
|
|||
|
|
# ★ 这里必须返回顶层评论自身的 id，而不是 0。
|
|||
|
|
# 对应官方 dao.FindCommentRootID：
|
|||
|
|
# for rootId != 0 { if comment.Rid == 0 { return rootId }; rootId = comment.Rid }
|
|||
|
|
# 即「父链上第一个 rid 为 0 的那条评论」。
|
|||
|
|
# 注意语义是：顶层评论 root_id=0，它的所有子孙 root_id=该顶层评论的 id。
|
|||
|
|
root_cache = {}
|
|||
|
|
|
|||
|
|
def root_of(cid: int) -> int:
|
|||
|
|
if cid in root_cache:
|
|||
|
|
return root_cache[cid]
|
|||
|
|
chain = []
|
|||
|
|
cur = cid
|
|||
|
|
seen = set()
|
|||
|
|
while cur and cur not in root_cache and cur not in seen:
|
|||
|
|
seen.add(cur)
|
|||
|
|
parent = rid_of.get(cur, 0)
|
|||
|
|
if parent == 0:
|
|||
|
|
break # cur 就是顶层评论
|
|||
|
|
chain.append(cur)
|
|||
|
|
cur = parent
|
|||
|
|
root = root_cache.get(cur, cur)
|
|||
|
|
for n in chain:
|
|||
|
|
root_cache[n] = root
|
|||
|
|
root_cache[root] = root
|
|||
|
|
return root
|
|||
|
|
|
|||
|
|
# 先全部插入成顶层，再统一回填 rid / root_id —— 与导入顺序无关
|
|||
|
|
ins, fix = [], []
|
|||
|
|
for r in rows:
|
|||
|
|
# is_verified 在 .artrans 里没有这个字段（官方导出不带）。
|
|||
|
|
# 前端只在「没有徽章」时才把 is_verified 渲染成小勾，所以这里统一给 0：
|
|||
|
|
# 有徽章的 328 条（博主）照样显示徽章，其余 3000+ 匿名评论不会多出勾。
|
|||
|
|
ins.append(
|
|||
|
|
"INSERT INTO comments (id, content, page_key, site_name, user_id, rid, root_id, "
|
|||
|
|
"is_collapsed, is_pending, is_pinned, is_verified, vote_up, vote_down, ua, ip, created_at, updated_at) "
|
|||
|
|
f"VALUES ({r['id']}, {sql_str(r['content'])}, {sql_str(r['page_key'])}, {sql_str(site_name)}, "
|
|||
|
|
f"{r['uid']}, 0, 0, {sql_bool(r['is_collapsed'])}, {sql_bool(r['is_pending'])}, {sql_bool(r['is_pinned'])}, "
|
|||
|
|
f"0, {sql_int(r['vote_up'])}, {sql_int(r['vote_down'])}, {sql_str(r['ua'])}, {sql_str(r['ip'])}, "
|
|||
|
|
f"{r['created_at']}, {r['updated_at'] or r['created_at']});"
|
|||
|
|
)
|
|||
|
|
if r["rid"]:
|
|||
|
|
fix.append(f"UPDATE comments SET rid = {r['rid']}, root_id = {root_of(r['rid'])} WHERE id = {r['id']};")
|
|||
|
|
print(f"评论 {len(rows)} 条（其中回复 {len(fix)} 条）")
|
|||
|
|
if skip_no_page or skip_no_user or skip_no_id:
|
|||
|
|
print(
|
|||
|
|
f"跳过 {skip_no_page + skip_no_user + skip_no_id} 条："
|
|||
|
|
f"page_key 为空 {skip_no_page}、昵称或邮箱为空 {skip_no_user}、id 非法 {skip_no_id}"
|
|||
|
|
)
|
|||
|
|
if skip_no_page:
|
|||
|
|
print(" ↑ page_key 为空的评论在官方 Artalk 里同样无法挂到任何页面，属于历史脏数据")
|
|||
|
|
|
|||
|
|
# ---------------- 落盘
|
|||
|
|
files = []
|
|||
|
|
(out_dir / "00-reset-and-site.sql").write_text("\n".join(head) + "\n", encoding="utf-8", newline="\n")
|
|||
|
|
files.append("00-reset-and-site.sql")
|
|||
|
|
|
|||
|
|
files += write_chunks(out_dir, "01-users", user_stmts)
|
|||
|
|
files += write_chunks(out_dir, "02-pages", page_stmts)
|
|||
|
|
files += write_chunks(out_dir, "03-comments", ins)
|
|||
|
|
files += write_chunks(out_dir, "04-rid-fix", fix)
|
|||
|
|
|
|||
|
|
# 为了让 wrangler d1 execute 的 SQLite 序列号往后走
|
|||
|
|
tail = ["-- 让 AUTOINCREMENT 从最大值之后继续", f"UPDATE sqlite_sequence SET seq = "
|
|||
|
|
f"(SELECT MAX(id) FROM comments) WHERE name = 'comments';",
|
|||
|
|
f"UPDATE sqlite_sequence SET seq = (SELECT MAX(id) FROM users) WHERE name = 'users';",
|
|||
|
|
f"UPDATE sqlite_sequence SET seq = (SELECT MAX(id) FROM pages) WHERE name = 'pages';",
|
|||
|
|
"-- 自检",
|
|||
|
|
"SELECT 'sites' AS t, COUNT(*) AS n FROM sites",
|
|||
|
|
"UNION ALL SELECT 'pages', COUNT(*) FROM pages",
|
|||
|
|
"UNION ALL SELECT 'users', COUNT(*) FROM users",
|
|||
|
|
"UNION ALL SELECT 'comments', COUNT(*) FROM comments",
|
|||
|
|
"UNION ALL SELECT 'replies', COUNT(*) FROM comments WHERE rid != 0;"]
|
|||
|
|
(out_dir / "99-post.sql").write_text("\n".join(tail) + "\n", encoding="utf-8", newline="\n")
|
|||
|
|
files.append("99-post.sql")
|
|||
|
|
|
|||
|
|
# 顺序执行脚本
|
|||
|
|
# -y 必须加：remote 执行会先问一次确认，非交互环境下不加会直接报错退出
|
|||
|
|
# 每个文件重试 3 次：跨境的 fetch 偶发失败（实测在 03-comments-007 断过一次）
|
|||
|
|
lines = [
|
|||
|
|
"#!/usr/bin/env bash",
|
|||
|
|
"set -uo pipefail",
|
|||
|
|
f"DB={args.db}",
|
|||
|
|
"MODE=${1:---remote}",
|
|||
|
|
"export WRANGLER_SEND_METRICS=false",
|
|||
|
|
"WR=\"node node_modules/wrangler/bin/wrangler.js\"",
|
|||
|
|
'[ -f "node_modules/wrangler/bin/wrangler.js" ] || WR="npx wrangler"',
|
|||
|
|
"",
|
|||
|
|
"FAILED=0",
|
|||
|
|
]
|
|||
|
|
for f in files:
|
|||
|
|
lines.append(f'echo "==> {f}"')
|
|||
|
|
lines.append("ok=0")
|
|||
|
|
lines.append("for try in 1 2 3; do")
|
|||
|
|
lines.append(f' if $WR d1 execute "$DB" "$MODE" -y --file={out_dir.as_posix()}/{f} >/dev/null 2>&1; then ok=1; break; fi')
|
|||
|
|
lines.append(' echo " 第 $try 次失败，重试（跨境 fetch 偶发失败）"')
|
|||
|
|
lines.append(" sleep 3")
|
|||
|
|
lines.append("done")
|
|||
|
|
lines.append('if [ "$ok" = "1" ]; then echo " ok"; else echo " FAIL"; FAILED=1; fi')
|
|||
|
|
lines.append("")
|
|||
|
|
lines.append('echo "核对条数："')
|
|||
|
|
lines.append(
|
|||
|
|
f'$WR d1 execute "$DB" "$MODE" -y --command '
|
|||
|
|
'"SELECT (SELECT COUNT(*) FROM sites) AS sites, (SELECT COUNT(*) FROM pages) AS pages,'
|
|||
|
|
' (SELECT COUNT(*) FROM users) AS users, (SELECT COUNT(*) FROM comments) AS comments,'
|
|||
|
|
' (SELECT COUNT(*) FROM comments WHERE rid!=0) AS replies;"'
|
|||
|
|
)
|
|||
|
|
lines.append("")
|
|||
|
|
lines.append('[ "$FAILED" = "0" ] && echo "全部导入成功" || echo "有文件失败，看上面 FAIL 那几行"')
|
|||
|
|
(out_dir / "run.sh").write_text("\n".join(lines) + "\n", encoding="utf-8", newline="\n")
|
|||
|
|
|
|||
|
|
print(f"\n生成 {len(files)} 个 SQL 于 {out_dir}")
|
|||
|
|
print(f"顺序执行： bash {out_dir.as_posix()}/run.sh --remote")
|
|||
|
|
return 0
|
|||
|
|
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
raise SystemExit(main())
|