shanxia2.0/backend/scripts/migrate_crm_clue.py

#!/usr/bin/env python3
"""将 sx 库 CRM 线索相关表迁入 shanxia2.0。

顺序：crm_clue → crm_clue_follow
用户外键经 user_mapping 转换；附件 OSS ID → 目标 sys_oss 相对 URL。

用法：
  cd backend
  venv/bin/python scripts/migrate_crm_clue.py --dry-run --env-file .env.production
  venv/bin/python scripts/migrate_crm_clue.py --env-file .env.production
"""
from __future__ import annotations

import argparse
import csv
import os
import sys
from dataclasses import dataclass, field
from datetime import datetime
from pathlib import Path
from typing import Any, Dict, List, Optional, Tuple
from urllib.parse import urlparse, urlunparse

from sqlalchemy import create_engine, text
from sqlalchemy.engine import Engine

BACKEND_ROOT = Path(__file__).resolve().parents[1]
MIGRATION_DIR = BACKEND_ROOT / "scripts" / "migration"
if str(BACKEND_ROOT) not in sys.path:
    sys.path.insert(0, str(BACKEND_ROOT))
if str(MIGRATION_DIR) not in sys.path:
    sys.path.insert(0, str(MIGRATION_DIR))

from minio_url import resolve_oss_id_csv  # noqa: E402

DEFAULT_TENANT_NO = "shanxia2.0"
CRM_ADMIN_SOURCE_USER_ID = 1

CUSTOMER_TYPE_MAP = {
    "company": "company",
    "person": "person",
    "未分类": None,
    "a类国央企单位": "A类国央企业",
    "A类国央企单位": "A类国央企业",
    "A类国央企业": "A类国央企业",
    "b类股份制企业": "B类股份制企业",
    "B类股份制企业": "B类股份制企业",
    "c类私营单位": "C类私营企业",
    "C类私营企业": "C类私营企业",
    "d外商投资企业": "D外商投资企业",
    "D外商投资企业": "D外商投资企业",
    "e类国资委企业": "5",
    "5": "5",
}

FOLLOW_TYPE_MAP = {
    "电话": "phone",
    "phone": "phone",
    "微信": "wechat",
    "wechat": "wechat",
    "邮件": "email",
    "email": "email",
    "拜访": "visit",
    "visit": "visit",
    "其他": "other",
    "other": "other",
}

MIGRATION_STEPS = (
    ("crm_clue", "clue"),
    ("crm_clue_follow", "clue_follow"),
)


@dataclass
class StepStats:
    source_count: int = 0
    inserted: int = 0
    updated: int = 0
    skipped: int = 0


@dataclass
class MigrationStats:
    steps: Dict[str, StepStats] = field(default_factory=dict)
    warnings: List[str] = field(default_factory=list)

    def step(self, name: str) -> StepStats:
        if name not in self.steps:
            self.steps[name] = StepStats()
        return self.steps[name]


def legacy_id_to_str(legacy_id: Any) -> Optional[str]:
    if legacy_id is None or str(legacy_id).strip() == "":
        return None
    try:
        return str(int(legacy_id))
    except (TypeError, ValueError):
        return str(legacy_id).strip()


def derive_source_url(target_url: str, source_db: str = "sx") -> str:
    return urlunparse(urlparse(target_url)._replace(path=f"/{source_db}"))


def load_settings_env(env_file: Optional[str]) -> None:
    if env_file:
        os.environ["ENV_FILE"] = env_file
    from dotenv import load_dotenv

    candidates: List[Path] = []
    if env_file:
        p = Path(env_file)
        candidates.append(p if p.is_absolute() else BACKEND_ROOT / p)
    candidates.extend([BACKEND_ROOT / ".env.production", BACKEND_ROOT / ".env"])
    for path in candidates:
        if path.is_file():
            load_dotenv(path, override=True)
            break


def load_runtime_settings():
    from app.core.config import Settings

    return Settings()


def load_user_mapping(path: Path) -> Tuple[Dict[int, str], Optional[str]]:
    crm_map: Dict[int, str] = {}
    admin_id: Optional[str] = None
    with path.open(encoding="utf-8-sig", newline="") as f:
        for row in csv.DictReader(f):
            new_id = (row.get("new_user_id") or "").strip()
            user_no = (row.get("user_no") or "").strip()
            crm_raw = (row.get("crm_user_id") or "").strip()
            if user_no == "admin" and new_id:
                admin_id = new_id
            if crm_raw and new_id:
                try:
                    crm_map[int(crm_raw)] = new_id
                except ValueError:
                    pass
    return crm_map, admin_id


def fetch_portal_admin_id(target_engine: Engine) -> Optional[str]:
    with target_engine.connect() as conn:
        row = conn.execute(
            text("SELECT id FROM sys_user WHERE user_no='admin' AND del_flag=0 LIMIT 1")
        ).first()
        return str(row[0]) if row and row[0] else None


def resolve_portal_user_id(
    source_user_id: Any,
    crm_user_map: Dict[int, str],
    admin_id: Optional[str],
    stats: MigrationStats,
    label: str,
) -> Optional[str]:
    if source_user_id is None or str(source_user_id).strip() == "":
        return None
    try:
        uid = int(source_user_id)
    except (TypeError, ValueError):
        stats.warnings.append(f"{label}: 非法用户 id {source_user_id!r}")
        return None
    if uid == CRM_ADMIN_SOURCE_USER_ID:
        return admin_id
    mapped = crm_user_map.get(uid)
    if not mapped:
        stats.warnings.append(f"{label}: crm_user_id={uid} 无映射")
    return mapped


def load_oss_id_to_url(target_engine: Engine, tenant_no: str) -> Dict[str, str]:
    with target_engine.connect() as conn:
        rows = conn.execute(
            text("SELECT id, url FROM sys_oss WHERE tenant_no=:t AND del_flag=0"),
            {"t": tenant_no},
        ).mappings().all()
    return {str(r["id"]): (r["url"] or "").strip() for r in rows if r["id"]}


def normalize_customer_type(raw: Any, stats: MigrationStats, label: str) -> Optional[str]:
    value = (str(raw).strip() if raw is not None else "") or ""
    if not value:
        return None
    if value in CUSTOMER_TYPE_MAP:
        mapped = CUSTOMER_TYPE_MAP[value]
        if mapped is None:
            stats.warnings.append(f"{label}: customer_type={value!r} 已置空")
        return mapped
    lowered = value.lower()
    for key, mapped in CUSTOMER_TYPE_MAP.items():
        if key.lower() == lowered:
            return mapped
    stats.warnings.append(f"{label}: customer_type={value!r} 未识别，已置空")
    return None


def normalize_follow_type(raw: Any) -> str:
    value = (str(raw).strip() if raw is not None else "") or "other"
    return FOLLOW_TYPE_MAP.get(value, FOLLOW_TYPE_MAP.get(value.lower(), "other"))


def _str_or_none(value: Any, max_len: int = 0) -> Optional[str]:
    if value is None:
        return None
    s = str(value).strip()
    if not s:
        return None
    return s[:max_len] if max_len else s


def fetch_source_rows(engine: Engine, table: str, include_deleted: bool) -> List[dict]:
    where = "" if include_deleted else "WHERE del_flag = 0"
    sql = f"SELECT * FROM `{table}` {where} ORDER BY id ASC"
    with engine.connect() as conn:
        return [dict(r._mapping) for r in conn.execute(text(sql))]


def target_row_exists(conn, table: str, row_id: str) -> bool:
    return int(conn.execute(text(f"SELECT COUNT(*) FROM `{table}` WHERE id=:id"), {"id": row_id}).scalar_one()) > 0


def transform_clue(
    row: dict,
    tenant_no: str,
    crm_user_map: Dict[int, str],
    admin_id: Optional[str],
    stats: MigrationStats,
) -> dict:
    rid = legacy_id_to_str(row["id"])
    label = f"clue#{rid}"

    def map_user(field_val: Any) -> Optional[str]:
        return resolve_portal_user_id(field_val, crm_user_map, admin_id, stats, label)

    return {
        "id": rid,
        "clue_name": (row.get("clue_name") or "")[:100],
        "mobile": (row.get("mobile") or "")[:20],
        "company": _str_or_none(row.get("company"), 200),
        "customer_type": normalize_customer_type(row.get("customer_type"), stats, label),
        "telephone": _str_or_none(row.get("telephone"), 30),
        "email": _str_or_none(row.get("email"), 100),
        "title": _str_or_none(row.get("title"), 10),
        "position": _str_or_none(row.get("position"), 50),
        "source": (row.get("source") or "")[:20],
        "level": (row.get("level") or "unrated")[:10],
        "industry": _str_or_none(row.get("industry"), 50),
        "park_area": _str_or_none(row.get("park_area"), 100),
        "province": _str_or_none(row.get("province"), 50),
        "city": _str_or_none(row.get("city"), 50),
        "district": _str_or_none(row.get("district"), 50),
        "address": _str_or_none(row.get("address"), 255),
        "website": _str_or_none(row.get("website"), 500),
        "intent_products": _str_or_none(row.get("intent_products"), 500),
        "expect_time": row.get("expect_time"),
        "budget": _str_or_none(row.get("budget"), 20),
        "requirement": row.get("requirement"),
        "status": (row.get("status") or "new")[:20],
        "owner_user_id": map_user(row.get("owner_user_id")),
        "owner_user_name": _str_or_none(row.get("owner_user_name"), 50),
        "last_time": row.get("last_time"),
        "next_time": row.get("next_time"),
        "follow_count": int(row.get("follow_count") or 0),
        "is_converted": int(row.get("is_converted") or 0),
        "converted_time": row.get("converted_time"),
        "customer_id": legacy_id_to_str(row.get("customer_id")),
        "converted_by": map_user(row.get("converted_by")),
        "assign_time": row.get("assign_time"),
        "assign_by": map_user(row.get("assign_by")),
        "tenant_no": tenant_no,
        "order_num": 0,
        "remark": _str_or_none(row.get("remark"), 500),
        "create_by": map_user(row.get("create_by")),
        "create_dept_id": "",
        "create_time": row.get("create_time") or datetime.now(),
        "update_by": map_user(row.get("update_by")),
        "update_time": row.get("update_time") or row.get("create_time") or datetime.now(),
        "del_flag": int(row.get("del_flag") or 0),
    }


def transform_clue_follow(
    row: dict,
    tenant_no: str,
    crm_user_map: Dict[int, str],
    admin_id: Optional[str],
    oss_map: Dict[str, str],
    stats: MigrationStats,
) -> dict:
    rid = legacy_id_to_str(row["id"])
    label = f"clue_follow#{rid}"
    owner_id = resolve_portal_user_id(row.get("create_by"), crm_user_map, admin_id, stats, label)

    return {
        "id": rid,
        "clue_id": legacy_id_to_str(row.get("clue_id")),
        "clue_name": _str_or_none(row.get("clue_name"), 100),
        "follow_type": normalize_follow_type(row.get("follow_type")),
        "follow_content": row.get("follow_content") or "",
        "next_time": row.get("next_time"),
        "attachments": resolve_oss_id_csv(row.get("attachments"), oss_map) or None,
        "create_by_name": _str_or_none(row.get("create_by_name"), 50),
        "tenant_no": tenant_no,
        "order_num": 0,
        "remark": _str_or_none(row.get("remark"), 500),
        "create_by": owner_id,
        "create_dept_id": "",
        "create_time": row.get("create_time") or datetime.now(),
        "update_by": resolve_portal_user_id(row.get("update_by"), crm_user_map, admin_id, stats, label),
        "update_time": row.get("update_time") or row.get("create_time") or datetime.now(),
        "del_flag": int(row.get("del_flag") or 0),
    }


INSERT_CLUE_SQL = text(
    """
    INSERT INTO crm_clue (
        id, clue_name, mobile, company, customer_type, telephone, email, title, position,
        source, level, industry, park_area, province, city, district, address, website,
        intent_products, expect_time, budget, requirement, status, owner_user_id, owner_user_name,
        last_time, next_time, follow_count, is_converted, converted_time, customer_id,
        converted_by, assign_time, assign_by, tenant_no, order_num, remark,
        create_by, create_dept_id, create_time, update_by, update_time, del_flag
    ) VALUES (
        :id, :clue_name, :mobile, :company, :customer_type, :telephone, :email, :title, :position,
        :source, :level, :industry, :park_area, :province, :city, :district, :address, :website,
        :intent_products, :expect_time, :budget, :requirement, :status, :owner_user_id, :owner_user_name,
        :last_time, :next_time, :follow_count, :is_converted, :converted_time, :customer_id,
        :converted_by, :assign_time, :assign_by, :tenant_no, :order_num, :remark,
        :create_by, :create_dept_id, :create_time, :update_by, :update_time, :del_flag
    )
    """
)

INSERT_CLUE_FOLLOW_SQL = text(
    """
    INSERT INTO crm_clue_follow (
        id, clue_id, clue_name, follow_type, follow_content, next_time, attachments,
        create_by_name, tenant_no, order_num, remark, create_by, create_dept_id,
        create_time, update_by, update_time, del_flag
    ) VALUES (
        :id, :clue_id, :clue_name, :follow_type, :follow_content, :next_time, :attachments,
        :create_by_name, :tenant_no, :order_num, :remark, :create_by, :create_dept_id,
        :create_time, :update_by, :update_time, :del_flag
    )
    """
)

STEP_INSERT_SQL = {
    "crm_clue": INSERT_CLUE_SQL,
    "crm_clue_follow": INSERT_CLUE_FOLLOW_SQL,
}


def write_mapping_csv(source_rows: List[dict], path: Path) -> None:
    path.parent.mkdir(parents=True, exist_ok=True)
    migrated_at = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    with path.open("w", encoding="utf-8", newline="") as f:
        w = csv.DictWriter(f, fieldnames=["source_id", "new_id", "migrated_at"])
        w.writeheader()
        for row in source_rows:
            sid = legacy_id_to_str(row["id"])
            w.writerow({"source_id": sid, "new_id": sid, "migrated_at": migrated_at})


def migrate_table(
    source_engine: Engine,
    target_engine: Engine,
    table: str,
    *,
    tenant_no: str,
    crm_user_map: Dict[int, str],
    admin_id: Optional[str],
    oss_map: Dict[str, str],
    stats: MigrationStats,
    dry_run: bool,
    update_existing: bool,
    include_deleted: bool,
) -> List[dict]:
    step = stats.step(table)
    source_rows = fetch_source_rows(source_engine, table, include_deleted)
    step.source_count = len(source_rows)

    transformers = {
        "crm_clue": lambda r: transform_clue(r, tenant_no, crm_user_map, admin_id, stats),
        "crm_clue_follow": lambda r: transform_clue_follow(
            r, tenant_no, crm_user_map, admin_id, oss_map, stats
        ),
    }
    payloads = [transformers[table](r) for r in source_rows]

    if dry_run:
        step.inserted = len(payloads)
        return source_rows

    insert_sql = STEP_INSERT_SQL[table]
    with target_engine.begin() as conn:
        for payload in payloads:
            rid = payload["id"]
            if target_row_exists(conn, table, rid):
                if update_existing:
                    step.skipped += 1
                else:
                    step.skipped += 1
            else:
                conn.execute(insert_sql, payload)
                step.inserted += 1
    return source_rows


def print_report(stats: MigrationStats, dry_run: bool) -> None:
    mode = "DRY-RUN" if dry_run else "COMMITTED"
    print(f"\n=== CRM 线索表迁移 [{mode}] ===")
    for table, _ in MIGRATION_STEPS:
        s = stats.step(table)
        print(f"{table}: 源={s.source_count} 插入={s.inserted} 跳过={s.skipped}")
    if stats.warnings:
        print(f"警告 ({len(stats.warnings)}):")
        for w in stats.warnings[:20]:
            print(f"  - {w}")
        if len(stats.warnings) > 20:
            print(f"  ... 另有 {len(stats.warnings) - 20} 条")


def run_migration(
    source_engine: Engine,
    target_engine: Engine,
    *,
    tenant_no: str,
    user_mapping_path: Path,
    mapping_dir: Path,
    dry_run: bool,
    update_existing: bool,
    include_deleted: bool,
    only_tables: Optional[List[str]],
) -> MigrationStats:
    stats = MigrationStats()
    crm_user_map, admin_id = load_user_mapping(user_mapping_path)
    if not admin_id:
        admin_id = fetch_portal_admin_id(target_engine)
    oss_map = load_oss_id_to_url(target_engine, tenant_no)
    print(f"sys_oss 映射条数: {len(oss_map)}")

    selected = [t for t, _ in MIGRATION_STEPS if not only_tables or t in only_tables]
    for table in selected:
        print(f"\n>> 迁移 {table} ...")
        source_rows = migrate_table(
            source_engine,
            target_engine,
            table,
            tenant_no=tenant_no,
            crm_user_map=crm_user_map,
            admin_id=admin_id,
            oss_map=oss_map,
            stats=stats,
            dry_run=dry_run,
            update_existing=update_existing,
            include_deleted=include_deleted,
        )
        if table == "crm_clue" and not dry_run:
            write_mapping_csv(source_rows, mapping_dir / "crm_clue_id_mapping.csv")

    print_report(stats, dry_run)
    return stats


def main() -> int:
    parser = argparse.ArgumentParser(description="Migrate CRM clue tables from sx to portal")
    parser.add_argument("--source-url", default="")
    parser.add_argument("--target-url", default="")
    parser.add_argument("--tenant-no", default=DEFAULT_TENANT_NO)
    parser.add_argument(
        "--user-mapping",
        default=str(BACKEND_ROOT.parent / "docs/data-migration/mappings/user_mapping_result.csv"),
    )
    parser.add_argument("--dry-run", action="store_true")
    parser.add_argument("--update", action="store_true")
    parser.add_argument("--include-deleted", action="store_true")
    parser.add_argument("--tables", default="", help="逗号分隔，默认全部两表")
    parser.add_argument("--env-file", default=os.environ.get("ENV_FILE", ""))
    args = parser.parse_args()

    load_settings_env(args.env_file or None)
    settings = load_runtime_settings()
    target_url = args.target_url or settings.DATABASE_URL
    source_url = args.source_url or os.environ.get("SX_SOURCE_DATABASE_URL") or derive_source_url(target_url)
    only_tables = [t.strip() for t in args.tables.split(",") if t.strip()] or None

    print(f"源库: {urlparse(source_url).path}")
    print(f"目标库: {urlparse(target_url).path}")

    run_migration(
        create_engine(source_url, pool_pre_ping=True),
        create_engine(target_url, pool_pre_ping=True),
        tenant_no=args.tenant_no,
        user_mapping_path=Path(args.user_mapping),
        mapping_dir=BACKEND_ROOT.parent / "docs/data-migration/mappings",
        dry_run=args.dry_run,
        update_existing=args.update,
        include_deleted=args.include_deleted,
        only_tables=only_tables,
    )
    return 0


if __name__ == "__main__":
    raise SystemExit(main())