# ============================================================
# 工程目录数据包分析（moduleId: domain-folder-pack, 可重生 ✅）
# 读取项目 workDir 下 Excel/CSV：表头/行数/样例/角色 → 排产齐备度校验
# ============================================================
from __future__ import annotations

import os
import re
from typing import Any

from server.aps_domain.importers import preview_file
from server.aps_domain.readiness import check_readiness

World = dict[str, Any]

KIND_CN = {
    "orders": "订单", "materials": "物料", "bom": "BOM 用料",
    "routing": "工艺路线/工时", "equipment": "设备", "molds": "模具",
    "operations": "工序库", "zones": "区域",
}

_FIELD_CN = {
    "productCode": "产品/料号", "quantity": "数量", "deliveryDate": "交期",
    "customerName": "客户/项目", "orderNo": "订单号", "code": "编码",
    "name": "名称", "operationCode": "工序", "seq": "顺序",
    "stdTimePerUnit": "工时", "capabilities": "可执行工序",
    "materialCode": "子件", "unit": "单位",
}

_NAME_KIND = [
    (r"订单|order", "orders"),
    (r"物料|材料|material", "materials"),
    (r"^bom|用料|物料清单", "bom"),
    (r"工艺|路线|routing|工时", "routing"),
    (r"设备|机器|equipment", "equipment"),
    (r"模具|mold", "molds"),
    (r"工序", "operations"),
    (r"区域|zone", "zones"),
]

_REQUIRED = ("orders", "materials", "routing", "equipment")
_HELPFUL = ("bom", "molds", "operations")

# 锐扬 MOM 收集表等现场模板中的非排产块：不导入，其问题行不计为数据错误
_MOM_SKIP_BLOCKS = ("生产模型", "质检方案", "仓储模型", "人力资源", "客户管理", "供应商管理")


def _is_mom_skip_block(sheet: str | None) -> bool:
    s = str(sheet or "")
    return any(b in s for b in _MOM_SKIP_BLOCKS)


def _guess_kind_by_name(name: str) -> str | None:
    stem = re.sub(r"\.(xlsx|xlsm|csv|txt)$", "", name, flags=re.I)
    for pat, kind in _NAME_KIND:
        if re.search(pat, stem, re.I):
            return kind
    return None


def _project_work_dir(session_id: str | None) -> tuple[dict[str, Any] | 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 _sample_cells(row: dict[str, Any], limit: int = 5) -> str:
    parts = []
    for k, v in list(row.items())[:limit]:
        if v is None or v == "":
            continue
        parts.append(f"{k}={v}")
    return "，".join(parts)


def _fmt_size(n: int) -> str:
    if n < 1024:
        return f"{n} B"
    if n < 1024 * 1024:
        return f"{n / 1024:.1f} KB"
    return f"{n / (1024 * 1024):.1f} MB"


def _fmt_field_map(fmap: list[dict[str, str]]) -> str:
    if not fmap:
        return ""
    return "；".join(
        f"{m.get('source')}→{_FIELD_CN.get(m.get('target') or '', m.get('target'))}"
        for m in fmap[:6]
    )


def analyze_work_dir(
    world: World,
    session_id: str | None = None,
    *,
    force_sql_replace: bool = False,
) -> dict[str, Any]:
    """深度解析工程目录：每张表读内容 + 动态字段映射 + 汇总能否开排。

    force_sql_replace=True 时（「根据这个排产」）强制用 SQL 包整表覆盖项目世界，
    避免旧世界残留错误工艺映射后永远不更新。
    """
    proj, work = _project_work_dir(session_id)
    if not proj:
        return {
            "ok": False, "error": "当前话题不在工程项目下，请先在左侧选一个项目。",
            "files": [], "coverage": {}, "missing": list(_REQUIRED),
            "canSchedule": False, "batches": [], "markdown":
                "当前话题不在工程项目下。请先在左侧选一个项目，或建项目时指定工程目录。",
        }
    if not work:
        return {
            "ok": False, "error": "这个项目还没设定工程目录。",
            "projectName": proj.get("name"), "files": [], "coverage": {},
            "missing": list(_REQUIRED), "canSchedule": False, "batches": [],
            "markdown": "这个项目还没设定工程目录。建项目时选一个放 Excel 的文件夹。",
        }
    if not os.path.isdir(work):
        return {
            "ok": False, "error": f"工程目录访问不到：{work}",
            "projectName": proj.get("name"), "workDir": work,
            "files": [], "coverage": {}, "missing": list(_REQUIRED),
            "canSchedule": False, "batches": [],
            "markdown": f"工程目录访问不到：`{work}`（路径变了或盘符未挂上）。",
        }

    names = sorted(os.listdir(work))
    table_names = [n for n in names if re.search(r"\.(xlsx|xlsm|csv|txt)$", n, re.I)
                   and not n.startswith("~$") and not n.startswith(".")]
    sql_names = [n for n in names if n.lower().endswith(".sql") and not n.startswith("~$")]

    file_reports: list[dict[str, Any]] = []
    all_batches: list[dict[str, Any]] = []
    all_diagnostics: list[dict[str, Any]] = []
    kind_ok: dict[str, int] = {}
    kind_fields: dict[str, list[dict[str, str]]] = {}

    # SQL 完整库优先：映射进当前世界并计入覆盖度（只取最大的一份完整库）
    sql_applied = False
    sql_stats: dict[str, Any] = {}
    if sql_names:
        sql_names = sorted(
            sql_names,
            key=lambda n: os.path.getsize(os.path.join(work, n)) if os.path.isfile(os.path.join(work, n)) else 0,
            reverse=True,
        )
    for name in sql_names[:1]:
        path = os.path.join(work, name)
        try:
            size = os.path.getsize(path)
        except OSError:
            size = 0
        try:
            from server.importers.sql_pack import preview_sql_file, apply_sql_pack_to_world
            prev = preview_sql_file(path)
            flex = prev.get("flex") or {}
            st = (flex.get("stats") or {})
            sql_stats = st
            if st.get("orders") or st.get("materials") or st.get("routing"):
                # 工程目录里的 SQL = 项目真相源，整包覆盖（避免旧错误工艺残留）
                apply_sql_pack_to_world(world, flex, replace=True)
                sql_applied = True
            for k, key in (("orders", "orders"), ("materials", "materials"),
                           ("routing", "routing"), ("equipment", "equipment"), ("bom", "bom")):
                n_ok = int(st.get(key) or 0)
                if n_ok:
                    kind_ok[k] = kind_ok.get(k, 0) + n_ok
            file_reports.append({
                "name": name, "size": size, "status": "ok" if prev.get("okCount") else "warn",
                "kind": "sql-pack", "kindCn": "SQL 数据包",
                "okCount": prev.get("okCount") or 0, "errorCount": 0,
                "errors": [], "warnings": [],
                "headers": [t.get("table") for t in (prev.get("tables") or [])[:8]],
                "samples": prev.get("samples") or [],
                "sheets": prev.get("tables") or [],
                "required": True,
                "fieldMap": [], "fieldMapText": prev.get("fieldMapText") or "",
                "issue": prev.get("fieldMapText") or (
                    f"SQL→订单{st.get('orders', 0)}/工艺{st.get('routing', 0)}"
                    f"/已挂工艺产品{st.get('routedProducts', 0)}"
                ),
            })
        except Exception as exc:  # noqa: BLE001
            file_reports.append({
                "name": name, "size": size, "status": "fail",
                "kind": "sql-pack", "kindCn": "SQL 数据包",
                "okCount": 0, "errorCount": 1, "errors": [str(exc)],
                "headers": [], "samples": [], "sheets": [], "required": True,
                "fieldMap": [], "fieldMapText": "", "issue": str(exc),
            })

    # 第一遍：先读订单，建立 订单号→料号 映射，供工艺/BOM 的 sheet 名反查
    product_by_order: dict[str, str] = {}
    for name in table_names:
        if _guess_kind_by_name(name) != "orders":
            continue
        path = os.path.join(work, name)
        try:
            with open(path, "rb") as f:
                raw = f.read()
            preview = preview_file(name, raw, world, soft=True, kind_hint="orders")
        except Exception:
            continue
        for b in preview.get("batches") or []:
            for row in b.get("okRows") or []:
                ono = str(row.get("orderNo") or "").strip()
                pc = str(row.get("productCode") or "").strip()
                if ono and pc:
                    product_by_order[ono] = pc

    for name in table_names:
        path = os.path.join(work, name)
        try:
            size = os.path.getsize(path)
        except OSError:
            size = 0
        kind_hint = _guess_kind_by_name(name)
        try:
            with open(path, "rb") as f:
                raw = f.read()
            preview = preview_file(
                name, raw, world, soft=True,
                product_by_order=product_by_order, kind_hint=kind_hint,
            )
        except Exception as exc:  # noqa: BLE001
            file_reports.append({
                "name": name, "size": size, "status": "fail",
                "kind": kind_hint,
                "kindCn": KIND_CN.get(kind_hint or "", "读失败"),
                "okCount": 0, "errorCount": 1, "errors": [str(exc)],
                "headers": [], "samples": [], "sheets": [], "required": False,
                "fieldMap": [], "fieldMapText": "",
            })
            continue

        sheets = []
        headers: list[str] = []
        samples: list[str] = []
        errors: list[str] = []
        warnings: list[str] = []
        file_diagnostics: list[dict[str, Any]] = []
        field_map: list[dict[str, str]] = []
        ok_total = 0
        err_total = 0
        skip_total = 0
        primary_kind = kind_hint

        for b in preview.get("batches") or []:
            kind = b.get("kind") or primary_kind or "materials"
            if not primary_kind:
                primary_kind = kind
            cover_kind = primary_kind or kind
            n_ok = int(b.get("okCount") or 0)
            if n_ok:
                kind_ok[cover_kind] = kind_ok.get(cover_kind, 0) + n_ok
                if kind != cover_kind:
                    kind_ok[kind] = kind_ok.get(kind, 0) + n_ok

            if not field_map and b.get("fieldMap"):
                field_map = list(b["fieldMap"])
            if primary_kind and b.get("fieldMap"):
                kind_fields.setdefault(primary_kind, list(b["fieldMap"]))

            is_skip = _is_mom_skip_block(b.get("sheet"))
            original_error_count = int(b.get("errorCount") or 0)
            batch_diagnostics = [
                dict(item) for item in (b.get("diagnostics") or [])
                if isinstance(item, dict)
            ]
            if is_skip:
                skip_total += original_error_count
                if not batch_diagnostics:
                    batch_diagnostics = [
                        {
                            "sheet": b.get("physicalSheet") or b.get("sheet") or name,
                            "excelRow": None,
                            "parserIndex": index,
                            "kind": kind,
                            "code": "NON_SCHEDULING_BLOCK",
                            "severity": "ignored",
                            "message": str(message),
                            "rawSummary": {},
                        }
                        for index, message in enumerate(b.get("errors") or [], 1)
                    ]
                else:
                    batch_diagnostics = [
                        {
                            **item,
                            "code": "NON_SCHEDULING_BLOCK",
                            "severity": "ignored",
                            "message": "非排产数据块，已跳过且不计入问题行",
                        }
                        for item in batch_diagnostics
                    ]
                real_err = 0
            elif batch_diagnostics:
                real_err = sum(
                    1 for item in batch_diagnostics
                    if item.get("severity") == "blocking"
                )
            else:
                real_err = original_error_count

            batch_counts = {
                severity: sum(
                    1 for item in batch_diagnostics
                    if item.get("severity") == severity
                )
                for severity in ("ignored", "warning", "blocking")
            }
            file_diagnostics.extend(batch_diagnostics)
            all_diagnostics.extend(batch_diagnostics)

            sheets.append({
                "sheet": b.get("sheet"), "kind": kind,
                "kindCn": KIND_CN.get(kind, kind),
                "okCount": n_ok,
                "errorCount": real_err,
                "skip": is_skip,
                "diagnosticCounts": batch_counts,
            })
            ok_total += n_ok
            err_total += real_err
            for row in (b.get("okRows") or [])[:2]:
                if isinstance(row, dict):
                    samples.append(_sample_cells(row))
                    if not headers:
                        headers = list(row.keys())[:8]
            if not is_skip:
                for e in (b.get("errors") or [])[:3]:
                    errors.append(str(e))
                for w in (b.get("warnings") or [])[:2]:
                    warnings.append(str(w))
            if not headers and b.get("headersRaw"):
                headers = [str(h) for h in b["headersRaw"] if h][:8]
            all_batches.append({
                "kind": b["kind"], "sheet": b.get("sheet") or name,
                "physicalSheet": b.get("physicalSheet") or b.get("sheet") or name,
                "okRows": b.get("okRows") or [], "okCount": n_ok,
                "errorCount": real_err,
                "errors": (b.get("errors") or [])[:8],
                "warnings": (b.get("warnings") or [])[:5],
                "diagnostics": batch_diagnostics,
                "diagnosticCounts": batch_counts,
                "fieldMap": b.get("fieldMap") or [],
                "sourceFile": name,
                "skip": is_skip,
            })

        status = "ok" if ok_total > 0 and err_total == 0 else ("warn" if ok_total > 0 else "fail")
        fmap_text = _fmt_field_map(field_map)
        issue = ""
        blocking_diagnostic = next((
            item for item in file_diagnostics
            if item.get("severity") == "blocking"
        ), None)
        if blocking_diagnostic:
            excel_row = blocking_diagnostic.get("excelRow")
            row_prefix = f"Excel 第{excel_row}行：" if excel_row else ""
            issue = row_prefix + str(blocking_diagnostic.get("message") or "数据校验未通过")
        elif errors:
            issue = errors[0]
        elif warnings:
            issue = warnings[0]
        elif fmap_text:
            issue = f"字段：{fmap_text}"
        elif samples:
            issue = f"样例：{samples[0]}"
        file_counts = {
            severity: sum(
                1 for item in file_diagnostics
                if item.get("severity") == severity
            )
            for severity in ("ignored", "warning", "blocking")
        }
        file_reports.append({
            "name": name, "size": size, "status": status,
            "kind": primary_kind, "kindCn": KIND_CN.get(primary_kind or "", primary_kind or "未识别"),
            "okCount": ok_total, "errorCount": err_total, "skipRows": skip_total,
            "errors": errors, "warnings": warnings,
            "diagnostics": file_diagnostics, "diagnosticCounts": file_counts,
            "headers": headers, "samples": samples[:3],
            "sheets": sheets, "required": (primary_kind in _REQUIRED) if primary_kind else False,
            "fieldMap": field_map, "fieldMapText": fmap_text, "issue": issue,
        })

    coverage = {k: kind_ok.get(k, 0) > 0 for k in (*_REQUIRED, *_HELPFUL)}
    for f in file_reports:
        k = f.get("kind")
        if k and int(f.get("okCount") or 0) > 0:
            coverage[k] = True
            kind_ok[k] = max(kind_ok.get(k, 0), int(f.get("okCount") or 0))

    missing = [KIND_CN[k] for k in _REQUIRED if not coverage.get(k)]
    soft_missing: list[str] = []
    if not (world.get("flexCalendar") or []):
        soft_missing.append("班次日历（没有可用系统默认班次）")
    for k in _HELPFUL:
        if not coverage.get(k):
            soft_missing.append(f"{KIND_CN[k]}（有更好，没有也能先试）")

    # 齐备度明细：每项带上识别到的关键字段
    coverage_detail: list[dict[str, Any]] = []
    for k in _REQUIRED:
        hit = bool(coverage.get(k))
        fmap = kind_fields.get(k) or []
        for f in file_reports:
            if f.get("kind") == k and f.get("fieldMap"):
                fmap = f["fieldMap"]
                break
        note = _fmt_field_map(fmap) if fmap else ""
        if hit:
            detail = f"读到 {kind_ok.get(k, 0)} 行"
            if sql_applied and int(sql_stats.get(k) or 0) > 0:
                detail = f"来自 SQL {sql_stats.get(k, 0)} 行"
            if note:
                detail += f"；识别 {note}"
        else:
            detail = "还没有有效数据"
            if note:
                detail += f"（已见表头 {note}，但行校验未过）"
            elif any(f.get("kind") == k for f in file_reports):
                detail = "有文件但关键字段对不上，请看文件清单里的问题列"
        coverage_detail.append({
            "key": k, "label": KIND_CN[k], "ok": hit,
            "count": kind_ok.get(k, 0), "fieldMap": fmap, "note": detail,
        })

    can_schedule = len(missing) == 0
    # SQL 已挂订单工艺时，即使 Excel 缺表也可开排
    if sql_applied and all(coverage.get(k) for k in ("orders", "routing", "equipment")):
        can_schedule = True
        missing = []
    world_ready = check_readiness(world)
    md = _to_markdown(
        proj_name=proj.get("name") or "未命名", work=work, files=file_reports,
        coverage=coverage, coverage_detail=coverage_detail,
        missing=missing, soft_missing=soft_missing,
        can_schedule=can_schedule, kind_ok=kind_ok, world_ready=world_ready,
    )
    excel_ok = sum(int(b.get("okCount") or 0) for b in all_batches)
    sql_ok_n = int((file_reports[0].get("okCount") or 0) if sql_applied and file_reports else 0)
    diagnostic_counts = {
        severity: sum(
            1 for item in all_diagnostics
            if item.get("severity") == severity
        )
        for severity in ("ignored", "warning", "blocking")
    }
    return {
        "ok": True, "projectName": proj.get("name"), "workDir": work,
        "files": file_reports, "coverage": coverage, "coverageDetail": coverage_detail,
        "kindCounts": kind_ok,
        "missing": missing, "softMissing": soft_missing,
        "canSchedule": can_schedule,
        "batches": [b for b in all_batches if b.get("okRows")],
        "totalOk": excel_ok + sql_ok_n,
        "totalErrors": sum(int(b.get("errorCount") or 0) for b in all_batches),
        "skippedRows": sum(int(f.get("skipRows") or 0) for f in file_reports),
        "diagnostics": all_diagnostics,
        "diagnosticCounts": diagnostic_counts,
        "diagnosticsVersion": 1,
        "sqlApplied": sql_applied,
        "sqlStats": sql_stats,
        "worldReadySummary": world_ready.get("summary"),
        "productByOrder": product_by_order,
        "markdown": md,
        "forceSqlReplace": force_sql_replace,
    }


def _to_markdown(
    *, proj_name: str, work: str, files: list[dict], coverage: dict,
    coverage_detail: list[dict],
    missing: list[str], soft_missing: list[str], can_schedule: bool,
    kind_ok: dict[str, int], world_ready: dict,
) -> str:
    lines = [
        f"**工程目录数据包 · {proj_name}**",
        "",
        f"目录：`{work}`",
        "",
        "### 我读到的表格",
        "",
    ]
    if not files:
        lines.append("目录里还没有 Excel/CSV。把订单、物料、工艺、设备表放进来再叫我。")
    else:
        lines += [
            "| 文件 | 类型 | 大小 | 有效行 | 问题行 | 识别字段 / 问题 |",
            "| --- | --- | ---: | ---: | ---: | --- |",
        ]
        for f in files:
            err = (f.get("issue") or "；".join((f.get("errors") or [])[:2])
                   or f.get("fieldMapText") or "—")
            err = str(err).replace("|", "/")
            if len(err) > 48:
                err = err[:48] + "…"
            lines.append(
                f"| {f.get('name')} | {f.get('kindCn') or '—'} | {_fmt_size(int(f.get('size') or 0))} "
                f"| {f.get('okCount', 0)} | {f.get('errorCount', 0)} | {err} |"
            )
        skip_total = sum(int(f.get("skipRows") or 0) for f in files)
        if skip_total:
            lines.append(
                f"\n> 另有 {skip_total} 行来自非排产块（工厂/质检/仓储/人力/客户/供应商等表），"
                "已跳过，不计入问题行。"
            )
        diagnostics = [
            item
            for file_report in files
            for item in (file_report.get("diagnostics") or [])
            if isinstance(item, dict)
        ]
        structural_ignored = sum(
            item.get("code") in {"SECONDARY_SEQUENCE_HEADER", "EMBEDDED_SECTION_ROW"}
            for item in diagnostics
        )
        general_defaults = sum(
            item.get("code") == "EQUIPMENT_CAPABILITIES_DEFAULTED"
            for item in diagnostics
        )
        alias_recoveries = sum(
            item.get("code") == "DUPLICATE_ALIAS_EMPTY_IGNORED"
            for item in diagnostics
        )
        diagnostic_notes: list[str] = []
        if structural_ignored:
            diagnostic_notes.append(f"忽略 {structural_ignored} 行内嵌表头/字典结构")
        if general_defaults:
            diagnostic_notes.append(f"{general_defaults} 台设备暂按 GENERAL 工序能力导入")
        if alias_recoveries:
            diagnostic_notes.append(f"恢复 {alias_recoveries} 行重复编码列")
        if diagnostic_notes:
            lines.append("\n> 诊断说明：" + "；".join(diagnostic_notes) + "。")
        sample_rows = [(f.get("name"), (f.get("samples") or [None])[0])
                       for f in files if f.get("samples")]
        if sample_rows:
            lines += ["", "### 样例数据（每表一行）", "",
                      "| 文件 | 样例 |", "| --- | --- |"]
            for name, sample in sample_rows[:8]:
                s = str(sample).replace("|", "/")
                if len(s) > 64:
                    s = s[:64] + "…"
                lines.append(f"| {name} | {s} |")

    lines += [
        "",
        "### 排产必备齐不齐",
        "",
        "| 必备项 | 状态 | 说明 |",
        "| --- | --- | --- |",
    ]
    for d in coverage_detail:
        st = "✓ 已有" if d.get("ok") else "× 缺少"
        note = str(d.get("note") or "").replace("|", "/")
        if len(note) > 56:
            note = note[:56] + "…"
        lines.append(f"| {d.get('label')} | {st} | {note} |")
    for s in soft_missing[:4]:
        lines.append(f"| （可选） | · | {s} |")

    lines.append("")
    if can_schedule:
        lines.append("**结论：按文件内容看，基本具备开排条件。**")
        lines.append("你可以说「根据这些数据排产」——我先收进系统，再校验后试排。")
    else:
        lines.append("**结论：现在还不能稳妥开排。**")
        lines.append("还缺：" + ("、".join(missing) if missing else "有效数据行"))
        lines.append("把缺的表补进工程目录（或改好报错行）后再叫我。")

    ws = (world_ready or {}).get("summary") or {}
    if ws:
        lines += [
            "",
            f"（系统里当前已有待排单 {ws.get('total', 0)} 张，"
            f"可排 {ws.get('ready', 0)}，卡住 {ws.get('blocked', 0)}。"
            f"导入目录后会按新数据重新看。）",
        ]
    return "\n".join(lines)


def confirmation_for_folder_schedule(report: dict[str, Any]) -> tuple[str, list[str]]:
    title = f"导入工程目录并试排 · {report.get('projectName') or ''}"
    lines = [
        f"目录：{report.get('workDir') or ''}",
        f"有效行合计：{report.get('totalOk') or 0}",
    ]
    for k in _REQUIRED:
        n = (report.get("kindCounts") or {}).get(k, 0)
        if n:
            lines.append(f"· {KIND_CN.get(k, k)} {n} 行")
    lines.append("确认后写入柔性主数据并试排一版（可回滚）")
    return title, lines