inkreach-official-website/apps/api/src/product-families/organize.service.ts

import { Injectable, Logger } from '@nestjs/common';
import { PrismaService } from '../prisma/prisma.service';
import { FamilyRecomputeService } from './family-recompute.service';
import { ProductFamiliesService } from './product-families.service';
import { PublicCacheService } from '../public/public-cache.service';
import { parseOriginName } from './origin-name.parser';
import {
  DERIVED_TAG_GROUP_SPECS,
  deriveLinkTagNames,
  isAutoTagGroupName,
  normalizeCraftTag,
} from './auto-tag-rules';

/**
 * 整理服务（解析去运行时化的唯一解析入口）：
 * 所有"按上游链接名解析/派生"的逻辑集中于此，由显式人工动作触发——
 * CLI（pnpm --filter @inkreach/api organize）或后台「整理」按钮（POST /product-families/organize）。
 *
 * 运行时（同步/重算/公开读）永不解析名称：
 * - 同步 = 纯镜像；族重算 = 结构化聚合（成员变体 + 链接标签 + 覆盖价）。
 *
 * 人工接管（tagsManual=true）的链接派生永不触碰；幂等可重跑。
 */
@Injectable()
export class OrganizeService {
  private readonly logger = new Logger(OrganizeService.name);

  constructor(
    private readonly prisma: PrismaService,
    private readonly recompute: FamilyRecomputeService,
    private readonly families: ProductFamiliesService,
    private readonly publicCache: PublicCacheService,
  ) {}

  async organize() {
    const labels = await this.backfillLabels();
    const tags = await this.deriveAllTags();
    const grouped = await this.families.autoGroup(true);
    const fragments = await this.consolidateFragments();
    const families = await this.prisma.productFamily.findMany({ select: { id: true } });
    for (const f of families) {
      await this.recompute.recomputeFamily(f.id);
    }
    const result = {
      labelsParsed: labels.parsed,
      labelsUnparsable: labels.unparsable,
      linksUpdated: tags.linksUpdated,
      goodsUpdated: tags.goodsUpdated,
      familiesCreated: grouped.applied,
      familiesMerged: grouped.merged,
      familiesSkipped: grouped.skipped?.length ?? 0,
      fragmentsConsolidated: fragments.consolidated,
      fragmentsManualReview: fragments.manualReview.length,
      familiesRecomputed: families.length,
    };
    this.logger.log(`organize done: ${JSON.stringify(result)}`);
    // 整理是全量标签/归族/矩阵重写动作，三域全失效（末尾逐族重算只覆盖 goods+matrix，
    // 标签镜像与标签组创建落在 meta 域）
    this.publicCache.bump('meta', 'goods', 'matrix');
    return result;
  }

  /**
   * 碎片族合并：同一 SDS 分类出现多个族时（历史 autoGroup 只建不并所致），
   * 把「纯碎片族」（autoManaged、无商品、无覆盖价）的成员并入最老族并删除空族；
   * 带商品/覆盖价或人工锁定的碎片族保留，写进人工复审报告（由后台手动移动成员）。
   * keeper 选择：同簇中最早带商品的族，否则最老的 autoManaged 族。
   */
  async consolidateFragments(): Promise<{
    consolidated: number;
    manualReview: Array<{ keeperFamilyId: string; fragmentFamilyId: string; reason: string }>;
  }> {
    const families = await this.prisma.productFamily.findMany({
      select: { id: true, autoManaged: true },
      orderBy: { id: 'asc' },
    });
    const members = await this.prisma.originGood.findMany({
      where: { familyId: { not: null }, delisted: false },
      select: { familyId: true, sdsCategoryId: true },
    });
    const goodCounts = await this.prisma.good.groupBy({
      by: ['familyId'],
      _count: { _all: true },
      where: { familyId: { not: null } },
    });
    const goodsByFamily = new Map(goodCounts.map((g) => [g.familyId!.toString(), g._count._all]));
    const overrideCounts = await this.prisma.familyPriceOverride.groupBy({
      by: ['familyId'],
      _count: { _all: true },
    });
    const overridesByFamily = new Map(
      overrideCounts.map((o) => [o.familyId.toString(), o._count._all]),
    );
    const autoManagedById = new Map(families.map((f) => [f.id.toString(), f.autoManaged]));
    const familyCatIds = new Map<string, Set<string>>();
    for (const m of members) {
      if (!m.sdsCategoryId) continue;
      const key = m.familyId!.toString();
      familyCatIds.set(key, (familyCatIds.get(key) ?? new Set()).add(m.sdsCategoryId));
    }

    // 按 SDS 分类聚簇：同分类的多个族互为碎片
    const clusterByFamily = new Map<string, Set<string>>();
    const catOwners = new Map<string, string[]>();
    for (const f of families) {
      const cats = familyCatIds.get(f.id.toString()) ?? new Set();
      for (const cat of cats) {
        const owners = catOwners.get(cat) ?? [];
        owners.push(f.id.toString());
        catOwners.set(cat, owners);
      }
    }
    for (const owners of catOwners.values()) {
      if (owners.length < 2) continue;
      for (const id of owners) {
        const cluster = clusterByFamily.get(id) ?? new Set();
        owners.forEach((o) => cluster.add(o));
        clusterByFamily.set(id, cluster);
      }
    }

    let consolidated = 0;
    const manualReview: Array<{ keeperFamilyId: string; fragmentFamilyId: string; reason: string }> = [];
    const processedClusters = new Set<string>();
    for (const [familyIdStr, cluster] of clusterByFamily) {
      const sorted = [...cluster].sort((a, b) => Number(BigInt(a) - BigInt(b)));
      const clusterKey = sorted.join(',');
      if (processedClusters.has(clusterKey)) continue;
      processedClusters.add(clusterKey);
      // keeper：最早带商品的族，否则最老的 autoManaged 族
      const withGoods = sorted.find((id) => (goodsByFamily.get(id) ?? 0) > 0);
      const keeper =
        withGoods ??
        sorted.find((id) => autoManagedById.get(id) === true) ??
        sorted[0];
      for (const id of sorted) {
        if (id === keeper) continue;
        const reasons: string[] = [];
        if ((goodsByFamily.get(id) ?? 0) > 0) reasons.push('has-goods');
        if ((overridesByFamily.get(id) ?? 0) > 0) reasons.push('has-overrides');
        if (autoManagedById.get(id) !== true) reasons.push('manual-locked');
        if (reasons.length) {
          manualReview.push({
            keeperFamilyId: keeper,
            fragmentFamilyId: id,
            reason: reasons.join(','),
          });
          continue;
        }
        // 纯碎片：成员并入 keeper，删除空族
        const keeperId = BigInt(keeper);
        await this.prisma.originGood.updateMany({
          where: { familyId: BigInt(id) },
          data: { familyId: keeperId },
        });
        await this.prisma.good.updateMany({
          where: { familyId: BigInt(id) },
          data: { familyId: keeperId },
        });
        await this.prisma.productFamily.delete({ where: { id: BigInt(id) } });
        consolidated += 1;
      }
      await this.recompute.recomputeFamily(BigInt(keeper));
    }
    return { consolidated, manualReview };
  }

  /**
   * 回填结构化解析列（skuCode/logisticsLabel/craftLabel/warehouseLabel）。
   * 只补 NULL 列——存量正确数据不覆盖（同步已不再写入这些列）。
   */
  async backfillLabels(): Promise<{ parsed: number; unparsable: number }> {
    const ogs = await this.prisma.originGood.findMany({
      where: {
        OR: [
          { skuCode: null },
          { logisticsLabel: null },
          { craftLabel: null },
          { warehouseLabel: null },
        ],
      },
      select: { id: true, goodName: true, skuCode: true, logisticsLabel: true, craftLabel: true, warehouseLabel: true },
    });
    let parsed = 0;
    let unparsable = 0;
    for (const og of ogs) {
      const p = parseOriginName(og.goodName);
      const next = {
        skuCode: og.skuCode ?? p.skuCode,
        logisticsLabel: og.logisticsLabel ?? p.logisticsLabel,
        craftLabel: og.craftLabel ?? p.craftLabel,
        warehouseLabel: og.warehouseLabel ?? p.warehouseLabel,
      };
      if (!p.skuCode && !p.craftLabel) unparsable += 1;
      await this.prisma.originGood.update({ where: { id: og.id }, data: next });
      parsed += 1;
    }
    // 结构化标签列是 CUSTOM 成员的矩阵归因来源（下次重算生效），保守失效 matrix+goods
    this.publicCache.bump('goods', 'matrix');
    return { parsed, unparsable };
  }

  /** 全量派生：未人工接管的 SDS 链接按名称刷新自动标签，人工接管不动；随后镜像商品并重算受影响族 */
  async deriveAllTags(): Promise<{ linksUpdated: number; goodsUpdated: number; familiesRecomputed: number }> {
    const families = await this.prisma.productFamily.findMany({
      select: { id: true },
      orderBy: { id: 'asc' },
    });
    let linksUpdated = 0;
    let goodsUpdated = 0;
    const touchedFamilies: bigint[] = [];
    for (const f of families) {
      const r = await this.deriveFamilyTags(f.id);
      linksUpdated += r.linksUpdated;
      goodsUpdated += r.goodsUpdated;
      if (r.linksUpdated > 0 || r.goodsUpdated > 0) touchedFamilies.push(f.id);
    }
    // 散链接（无族）也派生并镜像，保证族化之前标签已就绪
    const loose = await this.prisma.originGood.findMany({
      where: { familyId: null, delisted: false, source: 'SDS', tagsManual: false },
      select: { id: true },
    });
    for (const og of loose) {
      const r = await this.deriveTagsForOg(og.id);
      linksUpdated += r.linksUpdated;
    }
    for (const fid of touchedFamilies) {
      await this.recompute.recomputeFamily(fid);
    }
    // 标签镜像（good_tags）落 meta 域；散链接无族不会被重算覆盖，入口统一失效
    this.publicCache.bump('meta', 'goods', 'matrix');
    return { linksUpdated, goodsUpdated, familiesRecomputed: touchedFamilies.length };
  }

  /**
   * 族 → 标签派生（标签与「产品链接」一一对应）：
   * 1) 链接级：未人工接管（tagsManual=false）的 SDS 链接，按链接名称刷新
   *    origin_good_tags 的派生行（manual=false）；人工行（manual=true）永远保留；
   * 2) 商品级镜像：good 标签 = 自身链接的有效标签 ∪ 非自动组的既有标签。
   * 仅更新发生变化的行，幂等。
   */
  async deriveFamilyTags(
    familyId: bigint,
  ): Promise<{ goodsUpdated: number; linksUpdated: number }> {
    const tagMap = await this.ensureDerivedTagMap();
    const family = await this.prisma.productFamily.findUnique({
      where: { id: familyId },
      include: {
        originGoods: {
          where: { delisted: false },
          include: { originGoodTags: true },
        },
      },
    });
    if (!family) return { goodsUpdated: 0, linksUpdated: 0 };

    let linksUpdated = 0;
    for (const og of family.originGoods) {
      if (og.tagsManual || og.source !== 'SDS') continue;
      const derivedIds = this.resolveDerivedIds(og.goodName, tagMap);
      const autoRows = og.originGoodTags.filter((r) => !r.manual);
      const currentIds = autoRows.map((r) => r.tagId).sort((a, b) => Number(a - b));
      const same =
        derivedIds.length === currentIds.length &&
        derivedIds.every((id, i) => id === currentIds[i]);
      if (same) continue;
      await this.prisma.$transaction([
        this.prisma.originGoodTag.deleteMany({
          where: { originGoodId: og.id, manual: false },
        }),
        ...(!derivedIds.length
          ? []
          : [
              this.prisma.originGoodTag.createMany({
                data: derivedIds.map((tagId) => ({
                  originGoodId: og.id,
                  tagId,
                  manual: false,
                })),
              }),
            ]),
      ]);
      linksUpdated += 1;
    }

    // 商品级镜像：派生写入后重新读取链接标签（上面的 include 是派生前快照）
    const familyOgIds = family.originGoods.map((o) => o.id);
    const freshRows = familyOgIds.length
      ? await this.prisma.originGoodTag.findMany({
          where: { originGoodId: { in: familyOgIds } },
        })
      : [];
    const tagsByOg = new Map<string, bigint[]>();
    for (const r of freshRows) {
      const key = r.originGoodId.toString();
      tagsByOg.set(key, [...(tagsByOg.get(key) ?? []), r.tagId]);
    }

    const goods = await this.prisma.good.findMany({
      where: { familyId },
      include: {
        goodTags: { include: { tag: { select: { id: true, tagGroupId: true } } } },
        originGood: { select: { id: true } },
      },
    });
    const strayOgIds = [
      ...new Set(
        goods
          .map((g) => g.originGood?.id.toString())
          .filter((id): id is string => !!id && !tagsByOg.has(id)),
      ),
    ];
    if (strayOgIds.length) {
      const rows = await this.prisma.originGoodTag.findMany({
        where: { originGoodId: { in: strayOgIds.map((v) => BigInt(v)) } },
      });
      for (const r of rows) {
        const key = r.originGoodId.toString();
        tagsByOg.set(key, [...(tagsByOg.get(key) ?? []), r.tagId]);
      }
    }

    const { autoGroupIds } = await this.autoGroupIds();
    let goodsUpdated = 0;
    for (const good of goods) {
      const linkTagIds = good.originGood
        ? (tagsByOg.get(good.originGood.id.toString()) ?? [])
        : [];
      const keep = good.goodTags
        .filter((gt) => !autoGroupIds.has(gt.tag.tagGroupId?.toString() ?? ''))
        .map((gt) => gt.tagId);
      const target = [...new Set([...keep, ...linkTagIds])].sort((a, b) =>
        Number(a - b),
      );
      const current = good.goodTags.map((gt) => gt.tagId).sort((a, b) => Number(a - b));
      const same =
        target.length === current.length && target.every((id, i) => id === current[i]);
      if (same) continue;
      await this.prisma.$transaction([
        this.prisma.goodTag.deleteMany({ where: { goodId: good.id } }),
        ...(!target.length
          ? []
          : [
              this.prisma.goodTag.createMany({
                data: target.map((tagId) => ({ goodId: good.id, tagId })),
              }),
            ]),
      ]);
      goodsUpdated += 1;
    }
    this.publicCache.bump('meta', 'goods');
    return { goodsUpdated, linksUpdated };
  }

  /**
   * 单链接派生（供「恢复自动」等显式人工动作复用）：
   * 未人工接管时按名称刷新派生标签，并把有效标签镜像到其名下商品。
   */
  async deriveTagsForOg(ogId: bigint): Promise<{ linksUpdated: number }> {
    const og = await this.prisma.originGood.findUnique({
      where: { id: ogId },
      include: { originGoodTags: true },
    });
    if (!og) return { linksUpdated: 0 };
    let linksUpdated = 0;
    if (!og.tagsManual && og.source === 'SDS') {
      const tagMap = await this.ensureDerivedTagMap();
      const derivedIds = this.resolveDerivedIds(og.goodName, tagMap);
      await this.prisma.$transaction([
        this.prisma.originGoodTag.deleteMany({
          where: { originGoodId: og.id, manual: false },
        }),
        ...(!derivedIds.length
          ? []
          : [
              this.prisma.originGoodTag.createMany({
                data: derivedIds.map((tagId) => ({
                  originGoodId: og.id,
                  tagId,
                  manual: false,
                })),
              }),
            ]),
      ]);
      linksUpdated = 1;
    }
    await this.recompute.mirrorLinkTagsToGoods(og.id);
    this.publicCache.bump('meta', 'goods');
    return { linksUpdated };
  }

  /**
   * 人工标签缺维补齐：三个定价维度组（印花数量/工艺/物流）任一组在当前标签里
   * 没有封闭词表取值时，按链接名称派生补上；工艺维度经别名归一后判断（热转印≈烫画）。
   * 人工已勾的维度永不覆盖；名称派生不出该维度时不补（由调用方提示）。
   */
  async fillMissingDimTags(
    goodName: string | null,
    currentTagIds: bigint[],
  ): Promise<{ tagIds: bigint[]; names: string[] }> {
    const tagMap = await this.ensureDerivedTagMap();
    const current = currentTagIds.length
      ? await this.prisma.tag.findMany({
          where: { id: { in: currentTagIds } },
          select: { tagName: true },
        })
      : [];
    const currentNames = new Set(current.map((t) => normalizeCraftTag(t.tagName)));
    const derivedNames = deriveLinkTagNames(goodName);
    const missingNames: string[] = [];
    for (const spec of DERIVED_TAG_GROUP_SPECS) {
      if (spec.tags.some((name) => currentNames.has(name))) continue;
      const fromName = spec.tags.find((name) => derivedNames.includes(name));
      if (fromName) missingNames.push(fromName);
    }
    const tagIds = missingNames
      .map((name) => tagMap.get(name))
      .filter((id): id is bigint => id !== undefined);
    return { tagIds, names: missingNames };
  }

  private async autoGroupIds(): Promise<{ autoGroupIds: Set<string> }> {
    const groups = await this.prisma.tagGroup.findMany({
      select: { id: true, groupName: true },
    });
    return {
      autoGroupIds: new Set(
        groups
          .filter((g) => isAutoTagGroupName(g.groupName))
          .map((g) => g.id.toString()),
      ),
    };
  }

  private resolveDerivedIds(
    name: string | null | undefined,
    tagMap: Map<string, bigint>,
  ): bigint[] {
    return [
      ...new Set(
        deriveLinkTagNames(name)
          .map((n) => tagMap.get(n))
          .filter((id): id is bigint => id !== undefined),
      ),
    ].sort((a, b) => Number(a - b));
  }

  /** 确保派生标签组与标签存在，返回「标签名 → 标签 id」映射（并发下取最小 id，天然去重） */
  private async ensureDerivedTagMap(): Promise<Map<string, bigint>> {
    const map = new Map<string, bigint>();
    for (const spec of DERIVED_TAG_GROUP_SPECS) {
      const findGroups = () =>
        this.prisma.tagGroup.findMany({
          where: { groupName: { contains: spec.group } },
          orderBy: { id: 'asc' },
        });
      let group = (await findGroups())[0] ?? null;
      if (!group) {
        try {
          group = await this.prisma.tagGroup.create({ data: { groupName: spec.group } });
        } catch {
          group = (await findGroups())[0] ?? null;
        }
      }
      if (!group) continue;

      const tags = await this.prisma.tag.findMany({
        where: { tagGroupId: group.id, tagName: { in: spec.tags } },
        orderBy: { id: 'asc' },
      });
      for (const tagName of spec.tags) {
        const existing = tags.find((t) => t.tagName === tagName);
        if (existing) {
          map.set(tagName, existing.id);
          continue;
        }
        try {
          const created = await this.prisma.tag.create({
            data: { tagGroupId: group.id, tagName },
          });
          map.set(tagName, created.id);
        } catch {
          const fallback = await this.prisma.tag.findFirst({
            where: { tagGroupId: group.id, tagName },
            orderBy: { id: 'asc' },
          });
          if (fallback) map.set(tagName, fallback.id);
        }
      }
    }
    return map;
  }
}