feat: 智能导入——BOT自动识别报表类型/列名/期间/匹配KPI，无需手动映射

前端: 简化上传界面，自动模式(importExcelSmart) 后端: 新增/import-excel-smart端点，自动检测: - 列名: 科目/编码→kpi_code, 本期金额→value, 期间→period - 文件名: 提取期间(2026-06)和报表类型(利润表/现金流量表/资产负债表) - KPI匹配: 编码精确→别名→中文名模糊匹配
2026-07-13 15:36:22 +08:00
parent da9aceb567
commit d3edd71e60
4 changed files with 193 additions and 78 deletions
@@ -1,6 +1,6 @@
 """数据对接 API"""
 import pandas as pd
-import io, json, hashlib
+import io, json, hashlib, re
 from datetime import datetime
 from fastapi import APIRouter, Depends, HTTPException, Query, UploadFile, File
 from sqlalchemy.orm import Session
@@ -75,6 +75,185 @@ async def import_excel(file: UploadFile = File(...),
            msg += f"\n...还有{len(skipped)-10}条"
    return {"message": msg, "batch": batch, "total": count, "skipped": len(skipped)}

+
+# ── 智能导入（BOT自动识别，无需手动映射） ──
+
+_SMART_MAP = {
+    # KPI编码列匹配模式 → 标准kpi_code
+    "kpi_code_patterns": [
+        re.compile(r'^(kpi_?code|指标编码|编码)$', re.I),
+        re.compile(r'^(科目|项目|账户|报表项目|项目名称)$'),
+        re.compile(r'^(指标名称?|kpi名称?|name)$', re.I),
+    ],
+    # 期间列匹配
+    "period_patterns": [
+        re.compile(r'^(period|期间|月份?|年月|日期|会计期间)$', re.I),
+        re.compile(r'^(报表期[间]?|所属期)$'),
+    ],
+    # 数值列匹配
+    "value_patterns": [
+        re.compile(r'^(actual_?value|数值|实际值|实际金额)$', re.I),
+        re.compile(r'^(本期金额|本月数|本期|期末余额|期末数)$'),
+        re.compile(r'^(金额|数据|value)$', re.I),
+    ],
+    # 文件名→期间提取
+    "period_in_filename": re.compile(r'[-_]?(\d{4})[-_]?(\d{1,2})'),
+    # 文件名→报表类型
+    "statement_types": {
+        "利润表": "PL",
+        "利润": "PL",
+        "income": "PL",
+        "现金流量表": "CF",
+        "现金流": "CF",
+        "cashflow": "CF",
+        "cash_flow": "CF",
+        "资产负债表": "BS",
+        "资产负": "BS",
+        "balance": "BS",
+    },
+}
+
+
+def _smart_detect_kpi_col(cols: list[str]) -> str | None:
+    for pat in _SMART_MAP["kpi_code_patterns"]:
+        for c in cols:
+            if pat.match(c.strip()):
+                return c
+    return None
+
+
+def _smart_detect_period_col(cols: list[str]) -> str | None:
+    for pat in _SMART_MAP["period_patterns"]:
+        for c in cols:
+            if pat.match(c.strip()):
+                return c
+    return None
+
+
+def _smart_detect_value_col(cols: list[str]) -> str | None:
+    for pat in _SMART_MAP["value_patterns"]:
+        for c in cols:
+            if pat.match(c.strip()):
+                return c
+    return None
+
+
+def _smart_extract_period_from_filename(filename: str) -> str | None:
+    m = _SMART_MAP["period_in_filename"].search(filename)
+    if m:
+        return f"{m.group(1)}-{int(m.group(2)):02d}"
+    return None
+
+
+def _smart_detect_statement_type(filename: str) -> str | None:
+    for kw, tp in _SMART_MAP["statement_types"].items():
+        if kw in filename:
+            return tp
+    return None
+
+
+@router.post("/import-excel-smart")
+async def import_excel_smart(file: UploadFile = File(...), db: Session = Depends(get_db)):
+    """智能导入 — BOT自动识别列名/期间/报表类型，无需手动映射"""
+    content = await file.read()
+    fname = file.filename or "未知文件"
+
+    try:
+        df = pd.read_excel(io.BytesIO(content))
+    except Exception as e:
+        raise HTTPException(400, f"无法读取Excel文件: {e}")
+
+    if len(df) == 0:
+        raise HTTPException(400, "Excel文件为空")
+
+    cols = list(df.columns)
+    if len(cols) < 2:
+        raise HTTPException(400, f"Excel列数过少: {cols}")
+
+    # 4. 智能检测列
+    kpi_col = _smart_detect_kpi_col(cols) or cols[0]
+    value_col = _smart_detect_value_col(cols) or cols[-1]
+    period_col = _smart_detect_period_col(cols)
+
+    # 5. 从文件名提取期间
+    period = _smart_extract_period_from_filename(fname) if not period_col else None
+
+    # 6. 检测报表类型（用于自动生成KPI编码前缀）
+    stype = _smart_detect_statement_type(fname)
+
+    # 7. 预加载KPI字典
+    from app.models import KPIDefinition
+    kpis = {k.kpi_code: k for k in db.query(KPIDefinition).all()}
+    known_codes = set(kpis.keys())
+    # 构建别名映射（去掉空格/大小写/特殊字符）
+    alias_map: dict[str, str] = {}
+    for code in known_codes:
+        clean = re.sub(r'[\s\-_（）()]', '', code).lower()
+        alias_map[clean] = code
+
+    # 8. 遍历导入
+    batch = hashlib.md5(str(datetime.now().timestamp()).encode()).hexdigest()[:12]
+    imported = 0
+    skipped_rows = []
+
+    for idx, row in df.iterrows():
+        raw_kpi = str(row.get(kpi_col, "")).strip()
+        raw_val = row.get(value_col)
+        raw_period = str(row.get(period_col, period or "")).strip() if period_col else (period or "")
+
+        if not raw_kpi or pd.isna(raw_val):
+            skipped_rows.append(f"第{idx+2}行: 缺数据")
+            continue
+        if not raw_period:
+            skipped_rows.append(f"第{idx+2}行: 无法确定期间")
+            continue
+
+        # 智能匹配KPI编码
+        kpi_code = None
+        if raw_kpi in known_codes:
+            kpi_code = raw_kpi
+        else:
+            # 别名匹配
+            clean_key = re.sub(r'[\s\-_（）()]', '', raw_kpi).lower()
+            kpi_code = alias_map.get(clean_key)
+            # 模糊匹配（中文科目名→KPI编码）
+            if not kpi_code:
+                for code, kpi_obj in kpis.items():
+                    if raw_kpi in kpi_obj.kpi_name or kpi_obj.kpi_name in raw_kpi:
+                        kpi_code = code
+                        break
+
+        if not kpi_code:
+            skipped_rows.append(f"第{idx+2}行: 「{raw_kpi}」未匹配到KPI")
+            continue
+
+        try:
+            val = float(raw_val)
+        except:
+            skipped_rows.append(f"第{idx+2}行: 数值格式错误「{raw_val}」")
+            continue
+
+        db.add(KPIValue(
+            kpi_id=kpis[kpi_code].id,
+            period=raw_period,
+            actual_value=val,
+            source_type="excel",
+            source_batch=batch,
+            data_status="verified",
+        ))
+        imported += 1
+
+    db.commit()
+
+    # 9. 返回汇总
+    stype_label = {"PL": "利润表", "CF": "现金流量表", "BS": "资产负债表"}.get(stype or "", "数据表")
+    msg = f"✅ {stype_label}识别成功，导入{imported}条"
+    if skipped_rows:
+        msg += f"，{len(skipped_rows)}条跳过:\n" + "\n".join(skipped_rows[:8])
+        if len(skipped_rows) > 8:
+            msg += f"\n...还有{len(skipped_rows) - 8}条"
+    return {"message": msg, "batch": batch, "total": imported, "skipped": len(skipped_rows)}
+
@router.get("/sources")
 def list_sources(db: Session = Depends(get_db)):
    sources = db.query(DataSourceConfig).all()