aps-agent/server/aps_domain/project_analyze.py

# ============================================================
# 项目深度分析（moduleId: domain-project-analyze, 可重生 ✅）
# 工程目录 Excel/SQL → 写入当前项目世界 → 明细表 + 齐备度 + 知识库补洞 plan
# ============================================================
from __future__ import annotations

import os
import re
from typing import Any

from server.aps_domain.readiness import check_readiness

World = dict[str, Any]

_TABLE_EXT_RE = re.compile(r"\.(xlsx|xlsm|csv|txt)$", re.I)
_INPUT_EXT_RE = re.compile(r"\.(xlsx|xlsm|csv|txt|sql)$", re.I)


def _project_ctx(session_id: str | None) -> tuple[dict | None, str]:
    try:
        from server.state.projects import get_project_store
        snap = get_project_store().snapshot(include_messages=False)
    except Exception:
        return None, ""
    sessions = {s["id"]: s for s in (snap.get("sessions") or []) if isinstance(s, dict)}
    projects = {p["id"]: p for p in (snap.get("projects") or []) if isinstance(p, dict)}
    sess = sessions.get(session_id or "") or {}
    proj = projects.get(sess.get("projectId") or "") if sess.get("projectId") else None
    work = (proj.get("workDir") or "").strip() if proj else ""
    return proj, work


def _input_path_from_query(query: str) -> str:
    """从自然语言中提取当前机器上真实存在的文件/目录路径。"""
    text = str(query or "").strip()
    if not text:
        return ""
    candidates: list[str] = []
    for match in re.finditer(r'["“”\']([^"“”\']+)["“”\']', text):
        candidates.append(match.group(1))
    candidates.extend(re.findall(
        r"[A-Za-z]:[\\/][^\r\n\"'<>|]+?\.(?:xlsx|xlsm|csv|txt|sql)",
        text,
        flags=re.I,
    ))
    # 没带引号时，也允许整句本身就是一个目录。
    candidates.append(text)
    for raw in candidates:
        value = raw.strip().strip("`，。；;、")
        if os.path.isfile(value) and _INPUT_EXT_RE.search(value):
            return os.path.abspath(value)
        if os.path.isdir(value):
            return os.path.abspath(value)
    return ""


def _direct_table_report(
    world: World,
    paths: list[str],
    *,
    project_name: str,
    work_dir: str,
) -> dict[str, Any]:
    """直接路径旁路：复用 preview_file，但不依赖工作区里的 workDir。"""
    from server.aps_domain.folder_pack import KIND_CN
    from server.aps_domain.importers import preview_file

    required = ("orders", "materials", "routing", "equipment")
    files: list[dict[str, Any]] = []
    batches: list[dict[str, Any]] = []
    kind_counts: dict[str, int] = {}
    for path in paths:
        name = os.path.basename(path)
        try:
            with open(path, "rb") as source:
                preview = preview_file(name, source.read(), world, soft=True)
            file_batches = preview.get("batches") or []
            ok_count = int(preview.get("totalOk") or 0)
            error_count = int(preview.get("totalErrors") or 0)
            primary_kind = next(
                (str(batch.get("kind")) for batch in file_batches if batch.get("okCount")),
                str((file_batches[0] if file_batches else {}).get("kind") or ""),
            )
            field_map = next(
                (list(batch.get("fieldMap") or []) for batch in file_batches if batch.get("fieldMap")),
                [],
            )
            errors: list[str] = []
            warnings: list[str] = []
            headers: list[str] = []
            samples: list[str] = []
            sheets: list[dict[str, Any]] = []
            for batch in file_batches:
                kind = str(batch.get("kind") or primary_kind or "materials")
                count = int(batch.get("okCount") or 0)
                if count:
                    kind_counts[kind] = kind_counts.get(kind, 0) + count
                errors.extend(str(item) for item in (batch.get("errors") or [])[:2])
                warnings.extend(str(item) for item in (batch.get("warnings") or [])[:2])
                if not headers:
                    headers = [str(item) for item in (batch.get("headersRaw") or []) if item][:8]
                for row in (batch.get("okRows") or [])[:1]:
                    if isinstance(row, dict):
                        samples.append("；".join(f"{k}={v}" for k, v in list(row.items())[:6]))
                sheets.append({
                    "sheet": batch.get("sheet"), "kind": kind,
                    "kindCn": KIND_CN.get(kind, kind), "okCount": count,
                    "errorCount": int(batch.get("errorCount") or 0),
                })
                if count:
                    batches.append({
                        "kind": kind, "sheet": batch.get("sheet") or name,
                        "okRows": batch.get("okRows") or [], "okCount": count,
                        "errorCount": int(batch.get("errorCount") or 0),
                        "errors": (batch.get("errors") or [])[:8],
                        "warnings": (batch.get("warnings") or [])[:5],
                        "fieldMap": batch.get("fieldMap") or [], "sourceFile": name,
                    })
            fmap_text = "、".join(
                f"{item.get('source')}→{item.get('target')}" for item in field_map
            )
            issue = (errors or warnings or ([f"字段：{fmap_text}"] if fmap_text else []))
            files.append({
                "name": name, "size": os.path.getsize(path),
                "status": "ok" if ok_count and not error_count else ("warn" if ok_count else "fail"),
                "kind": primary_kind, "kindCn": KIND_CN.get(primary_kind, primary_kind or "未识别"),
                "okCount": ok_count, "errorCount": error_count,
                "errors": errors, "warnings": warnings, "headers": headers,
                "samples": samples, "sheets": sheets, "fieldMap": field_map,
                "fieldMapText": fmap_text, "issue": issue[0] if issue else "",
            })
        except Exception as exc:  # noqa: BLE001
            files.append({
                "name": name, "size": os.path.getsize(path) if os.path.isfile(path) else 0,
                "status": "fail", "kind": "", "kindCn": "读取失败",
                "okCount": 0, "errorCount": 1, "errors": [str(exc)],
                "warnings": [], "headers": [], "samples": [], "sheets": [],
                "fieldMap": [], "fieldMapText": "", "issue": str(exc),
            })
    coverage = {kind: kind_counts.get(kind, 0) > 0 for kind in required}
    coverage_detail = [{
        "key": kind, "label": KIND_CN[kind], "ok": coverage[kind],
        "count": kind_counts.get(kind, 0), "fieldMap": [],
        "note": (f"读到 {kind_counts[kind]} 行" if coverage[kind] else "还没有有效数据"),
    } for kind in required]
    missing = [KIND_CN[kind] for kind in required if not coverage[kind]]
    return {
        "ok": True, "projectName": project_name, "workDir": work_dir,
        "files": files, "coverage": coverage, "coverageDetail": coverage_detail,
        "kindCounts": kind_counts, "missing": missing, "softMissing": [],
        "canSchedule": not missing, "batches": batches,
        "totalOk": sum(int(item.get("okCount") or 0) for item in files),
        "totalErrors": sum(int(item.get("errorCount") or 0) for item in files),
    }


def _fill_from_knowledge(world: World, product_codes: list[str]) -> list[dict[str, Any]]:
    """缺工艺时用行业模板/知识库自动补；返回动作清单。"""
    actions: list[dict[str, Any]] = []
    try:
        from server.knowledge.routing_templates import recommend_templates, apply_template_to_product
    except Exception:
        return actions
    routes = {r.get("productCode") for r in (world.get("flexRoutings") or [])}
    mats = {m.get("code") for m in (world.get("flexMaterials") or [])}
    for pc in product_codes:
        if not pc:
            continue
        if pc not in mats:
            world.setdefault("flexMaterials", []).append({
                "id": len(world.get("flexMaterials") or []) + 1,
                "code": pc, "name": pc, "type": "FINISHED_PRODUCT", "unit": "件",
                "stock": 0, "inTransit": 0, "safetyStock": 0, "procurementLeadTime": 0,
            })
            actions.append({"type": "material_stub", "productCode": pc,
                            "detail": f"物料主数据缺失，已建产品档案占位 {pc}"})
        if pc in routes:
            continue
        name = next((m.get("name") for m in (world.get("flexMaterials") or [])
                     if m.get("code") == pc), pc)
        try:
            recs = recommend_templates(f"{pc} {name}") or []
        except Exception:
            recs = []
        if not recs:
            actions.append({"type": "need_routing", "productCode": pc,
                            "detail": f"产品 {pc} 无工艺，知识库也无匹配模板，需客户提供工艺路线"})
            continue
        tpl = recs[0]
        code = tpl.get("code") or tpl.get("templateCode")
        try:
            apply_template_to_product(world, code, pc)
            actions.append({
                "type": "template_applied", "productCode": pc,
                "template": code, "templateName": tpl.get("name"),
                "detail": f"产品 {pc} 缺工艺 → 已用知识库模板「{tpl.get('name') or code}」生成",
            })
            routes.add(pc)
        except Exception as exc:
            actions.append({"type": "template_failed", "productCode": pc,
                            "detail": f"模板 {code} 应用失败：{exc}"})
    return actions


def analyze_project_deep(
    world: World,
    session_id: str | None = None,
    *,
    apply_sql: bool = True,
    query: str = "",
    next_id=None,
) -> dict[str, Any]:
    """深度分析当前项目：目录包（SQL/Excel）+ 世界主数据 + 知识库补洞。"""
    try:
        from server.agent_core.progress import emit_thinking
    except Exception:
        def emit_thinking(*_a, **_k):  # type: ignore
            return None

    proj, work = _project_ctx(session_id)
    explicit_input = _input_path_from_query(query)
    if explicit_input:
        work = explicit_input if os.path.isdir(explicit_input) else os.path.dirname(explicit_input)
        if proj is None:
            proj = {
                "name": os.path.basename(work.rstrip("\\/")) or "当前项目",
                "workDir": work,
            }
    sources: list[str] = []
    source_paths: list[str] = []
    sql_preview: dict[str, Any] | None = None
    applied: dict[str, int] = {}
    kb_actions: list[dict[str, Any]] = []

    def apply_folder_batches(report: dict[str, Any] | None) -> None:
        batches = (report or {}).get("batches") or []
        if not batches or next_id is None:
            return
        from server.aps_domain.importers import apply_import_commit

        counts = apply_import_commit(world, next_id, batches)
        for key, value in counts.items():
            applied[key] = applied.get(key, 0) + int(value or 0)

    emit_thinking("定位工程目录", (proj or {}).get("name") or "当前项目", pct=2)
    if work and os.path.isdir(work):
        names = ([os.path.basename(explicit_input)] if os.path.isfile(explicit_input)
                 else sorted(os.listdir(work)))
        sqls = [n for n in names if n.lower().endswith(".sql") and not n.startswith("~$")]
        xls = [n for n in names if _TABLE_EXT_RE.search(n) and not n.startswith("~$")]
        source_paths = [
            os.path.join(work, name) for name in (*sqls, *xls)
            if os.path.isfile(os.path.join(work, name))
        ]
        folder = None
        emit_thinking(
            "清点目录文件",
            f"SQL {len(sqls)} · Excel/CSV {len(xls)}",
            pct=5,
        )
        if sqls:
            from server.importers.sql_pack import preview_sql_file, apply_sql_pack_to_world
            # 优先最大的 sql（完整库）
            sqls_sorted = sorted(sqls, key=lambda n: os.path.getsize(os.path.join(work, n)), reverse=True)
            path = os.path.join(work, sqls_sorted[0])
            sources.append(f"SQL:{sqls_sorted[0]}")
            try:
                sql_preview = preview_sql_file(path)
                if apply_sql and sql_preview.get("flex"):
                    emit_thinking("写入项目世界", "订单 / 物料 / 工艺 / 设备", pct=93)
                    # SQL 包是工程目录真相源，始终整包覆盖，避免旧错误工艺残留
                    applied = apply_sql_pack_to_world(
                        world, sql_preview["flex"], replace=True)
                    emit_thinking(
                        "入库完成",
                        "、".join(f"{k}{v}" for k, v in applied.items()) or "无新增",
                        status="done", pct=95,
                    )
            except Exception as exc:
                sql_preview = {"error": str(exc), "filename": sqls_sorted[0]}
                emit_thinking("SQL 解析失败", str(exc), status="warn")
        elif xls:
            # 无 SQL 时：识别 MOM 主数据收集表并写入世界（否则深度分析永远是 0）
            mom_applied = False
            try:
                from server.importers.mom_pack import is_mom_workbook, import_mom_excel
                mom_files = [
                    n for n in xls
                    if is_mom_workbook(os.path.join(work, n))
                ]
                # 文件名含 MOM/主数据 优先；否则对全部 xlsx 试探
                candidates = mom_files or xls
                for n in candidates:
                    path = os.path.join(work, n)
                    if not is_mom_workbook(path):
                        continue
                    sources.append(f"MOM:{n}")
                    emit_thinking("识别 MOM 主数据表", n, pct=90)
                    result = import_mom_excel(world, path, replace=True)
                    applied = result.get("applied") or {}
                    mom_applied = True
                    emit_thinking(
                        "MOM 入库完成",
                        "、".join(f"{k}{v}" for k, v in applied.items()) or "无新增",
                        status="done", pct=95,
                    )
                    stats = result.get("stats") or {}
                    if stats.get("note"):
                        sources.append(str(stats["note"]))
                    break
            except Exception as exc:
                emit_thinking("MOM Excel 解析失败", str(exc), status="warn")
            if not mom_applied:
                sources.append(f"Excel×{len(xls)}")
                try:
                    emit_thinking("解析并写入 Excel/CSV", f"{len(xls)} 个表格", pct=96)
                    if explicit_input:
                        folder = _direct_table_report(
                            world,
                            [os.path.join(work, name) for name in xls],
                            project_name=(proj or {}).get("name") or "当前项目",
                            work_dir=work,
                        )
                    else:
                        from server.aps_domain.folder_pack import analyze_work_dir
                        folder = analyze_work_dir(world, session_id)
                    apply_folder_batches(folder)
                except Exception:
                    folder = None
            else:
                try:
                    if explicit_input:
                        folder = _direct_table_report(
                            world,
                            [os.path.join(work, name) for name in xls],
                            project_name=(proj or {}).get("name") or "当前项目",
                            work_dir=work,
                        )
                    else:
                        from server.aps_domain.folder_pack import analyze_work_dir
                        folder = analyze_work_dir(world, session_id)
                except Exception:
                    folder = None
        else:
            folder = None

        if sqls and xls:
            sources.append(f"Excel×{len(xls)}")
            try:
                emit_thinking("核对 Excel/CSV", f"{len(xls)} 个表格", pct=96)
                if explicit_input:
                    folder = _direct_table_report(
                        world,
                        [os.path.join(work, name) for name in xls],
                        project_name=(proj or {}).get("name") or "当前项目",
                        work_dir=work,
                    )
                else:
                    from server.aps_domain.folder_pack import analyze_work_dir
                    folder = analyze_work_dir(world, session_id)
                apply_folder_batches(folder)
            except Exception:
                folder = None
    else:
        folder = None
        emit_thinking("未挂工程目录", "仅分析当前项目世界里的数据", status="warn", pct=10)

    # 知识库补洞：缺工艺的产品
    emit_thinking("检查齐备度与知识库", "缺工艺时自动匹配行业模板", pct=97)
    active = [o for o in (world.get("flexOrders") or [])
              if (o.get("status") or "") not in ("DONE", "CANCELLED")]
    pcs = list({str(o.get("productCode") or "") for o in active})
    kb_actions = _fill_from_knowledge(world, pcs)
    if kb_actions:
        emit_thinking(
            "知识库补洞",
            f"{len(kb_actions)} 项（模板/占位/待客户补）",
            status="done", pct=98,
        )

    ready = check_readiness(world)
    emit_thinking("整理分析报告", f"订单 {len(active)} 张", status="done", pct=99)
    mats = world.get("flexMaterials") or []
    routes = world.get("flexRoutings") or []
    equip = [e for e in (world.get("flexEquipment") or []) if e.get("status") == "RUNNING"]
    bom = world.get("flexBom") or []

    order_rows = [{
        "orderNo": o.get("orderNo"),
        "productCode": o.get("productCode"),
        "productName": o.get("productName") or next(
            (m.get("name") for m in mats if m.get("code") == o.get("productCode")), ""),
        "quantity": o.get("quantity"),
        "dueDate": o.get("dueDate"),
        "customerName": o.get("customerName") or "",
        "ready": next((r["ready"] for r in ready["orders"] if r["orderNo"] == o.get("orderNo")), False),
    } for o in active[:80]]

    # 主数据抽样：订单涉及的产品优先
    need_codes = {r["productCode"] for r in order_rows if r.get("productCode")}
    mat_rows = []
    for m in mats:
        if need_codes and m.get("code") not in need_codes and len(mat_rows) >= 40:
            continue
        if m.get("code") in need_codes or len(mat_rows) < 40:
            mat_rows.append({
                "code": m.get("code"), "name": m.get("name"),
                "type": m.get("type"), "unit": m.get("unit"), "stock": m.get("stock"),
            })
        if len(mat_rows) >= 60:
            break

    route_rows = []
    for r in routes:
        if need_codes and r.get("productCode") not in need_codes and len(route_rows) >= 40:
            continue
        route_rows.append({
            "productCode": r.get("productCode"),
            "seq": r.get("seq"),
            "operationCode": r.get("operationCode"),
            "operationName": r.get("operationName") or r.get("operationCode"),
            "stdMin": r.get("stdTimePerUnit"),
        })
        if len(route_rows) >= 80:
            break

    equip_rows = [{
        "code": e.get("code"), "name": e.get("name"),
        "capabilities": "、".join((e.get("capabilities") or [])[:6]),
    } for e in equip[:40]]

    # 缺口 plan：先库后客户（同类缺口合并，避免刷屏）
    plan: list[str] = []
    need_rt = [a for a in kb_actions if a.get("type") == "need_routing"]
    applied_tpl = [a for a in kb_actions if a.get("type") == "template_applied"]
    other_kb = [a for a in kb_actions if a.get("type") not in ("need_routing", "template_applied")]
    if applied_tpl:
        plan.append(f"✓ 已用知识库模板补工艺 {len(applied_tpl)} 个产品")
        for a in applied_tpl[:5]:
            plan.append(f"  · {a.get('productCode')} ← {a.get('templateName') or a.get('template')}")
        if len(applied_tpl) > 5:
            plan.append(f"  · …另有 {len(applied_tpl) - 5} 个")
    if need_rt:
        samples = "、".join(str(a.get("productCode") or "") for a in need_rt[:8])
        more = f" 等共 {len(need_rt)} 个" if len(need_rt) > 8 else f"（{len(need_rt)} 个）"
        plan.append(
            f"△ SQL/知识库仍未挂上工艺的产品：{samples}{more}。"
            f"若现场库本有工艺，请重新「分析项目」（工艺按订单 craftl 关联，不是中间件料号）"
        )
    for a in other_kb[:6]:
        plan.append(f"· {a['detail']}")
    s = ready["summary"]
    if s.get("blocked"):
        plan.append(f"△ 仍有 {s['blocked']} 张单齐备度未过，见订单明细「是否可排」列")
    if not active:
        plan.append("△ 没有订单：请在工程目录放订单表/SQL，或说「新建订单」")
    if not equip:
        plan.append("△ 没有可用设备：请提供设备台账，或从 SQL 的 md_equipment 导入")
    if not plan:
        plan.append("✓ 主数据与知识库已齐，可直接说「给我排产」")

    proj_name = (proj or {}).get("name") or "当前项目"
    md_lines = [
        f"**项目深度分析 · {proj_name}**",
        "",
        f"数据来源：{'、'.join(sources) if sources else '当前项目世界（未挂工程目录文件）'}",
    ]
    # 绑定当前登录用户
    try:
        from server.knowledge.ingest import bind_world_to_identity, ingest_project_analyze_report
        owner_meta = bind_world_to_identity(world, sources=sources)
        md_lines.append(
            f"归属：{owner_meta.get('ownerFullname') or owner_meta.get('ownerUsername')} "
            f"（用户 {owner_meta.get('ownerUserId')} · 租户 {str(owner_meta.get('tenantUuid') or '')[:8]}…）"
        )
    except Exception:
        owner_meta = {}
        ingest_project_analyze_report = None  # type: ignore

    if applied:
        md_lines.append(
            "已入库："
            + "、".join(f"{k} {v}" for k, v in applied.items())
        )
    if sql_preview and sql_preview.get("fieldMapText"):
        md_lines.append(f"SQL 包识别：{sql_preview['fieldMapText']}")
    md_lines += [
        "",
        f"订单 **{len(active)}** · 物料 **{len(mats)}** · 工艺步 **{len(routes)}** · "
        f"设备 **{len(equip)}** · BOM **{len(bom)}**",
        "",
        "### 订单明细（本项目）",
        "",
        "| 订单号 | 产品 | 名称 | 数量 | 交期 | 客户 | 可排 |",
        "| --- | --- | --- | ---: | --- | --- | --- |",
    ]
    for r in order_rows[:30]:
        md_lines.append(
            f"| {r['orderNo']} | {r['productCode']} | {str(r.get('productName') or '')[:16]} "
            f"| {r['quantity']} | {r['dueDate'] or '—'} | {str(r.get('customerName') or '')[:12]} "
            f"| {'✓' if r['ready'] else '×'} |"
        )
    if len(order_rows) > 30:
        md_lines.append(f"| … | 另有 {len(order_rows) - 30} 张 | | | | | |")

    md_lines += [
        "",
        "### 主数据（产品/物料抽样）",
        "",
        "| 编码 | 名称 | 类型 | 单位 | 库存 |",
        "| --- | --- | --- | --- | ---: |",
    ]
    for m in mat_rows[:25]:
        md_lines.append(
            f"| {m['code']} | {str(m.get('name') or '')[:20]} | {m.get('type')} "
            f"| {m.get('unit')} | {m.get('stock') or 0} |"
        )

    md_lines += ["", "### 补数 Plan（先知识库/数据库，再找客户）", ""]
    for i, p in enumerate(plan[:12], 1):
        md_lines.append(f"{i}. {p}")

    result = {
        "ok": True,
        "projectName": proj_name,
        "workDir": work,
        "sources": sources,
        "sourcePaths": source_paths,
        "applied": applied,
        "owner": {
            "userId": owner_meta.get("ownerUserId"),
            "username": owner_meta.get("ownerUsername"),
            "fullname": owner_meta.get("ownerFullname"),
            "tenantUuid": owner_meta.get("tenantUuid"),
        } if owner_meta else None,
        "sqlPreview": {
            "filename": (sql_preview or {}).get("filename"),
            "fieldMapText": (sql_preview or {}).get("fieldMapText"),
            "tables": (sql_preview or {}).get("tables") or [],
            "error": (sql_preview or {}).get("error"),
        } if sql_preview else None,
        "folder": folder,
        "orders": order_rows,
        "materials": mat_rows,
        "routings": route_rows,
        "equipment": equip_rows,
        "kbActions": kb_actions,
        "plan": plan,
        "readiness": ready,
        "summary": {
            "orders": len(active), "materials": len(mats),
            "routings": len(routes), "equipment": len(equip), "bom": len(bom),
            "ready": s.get("ready", 0), "blocked": s.get("blocked", 0),
        },
        "canSchedule": s.get("ready", 0) > 0 and not ready.get("globalIssues"),
        "markdown": "\n".join(md_lines),
    }

    # 分析结果写入当前租户知识库（平台知识模块，按登录租户隔离）
    knowledge_ingest: dict[str, Any] = {}
    try:
        has_data = bool(
            result["summary"]["materials"]
            or result["summary"]["orders"]
            or result["summary"]["equipment"]
            or result["summary"]["bom"]
            or result.get("sourcePaths")
        )
        if ingest_project_analyze_report is not None and has_data:
            knowledge_ingest = ingest_project_analyze_report(result, world=world)
            if knowledge_ingest.get("assetId"):
                md_lines.append("")
                md_lines.append(
                    f"已写入知识库：《{knowledge_ingest.get('title')}》"
                    f"（{knowledge_ingest.get('chunkCount')} 段，{knowledge_ingest.get('version')}）"
                )
                result["markdown"] = "\n".join(md_lines)
    except Exception as exc:
        knowledge_ingest = {"error": str(exc)}
    result["knowledgeIngest"] = knowledge_ingest
    return result