diff --git a/backend/app/api/__pycache__/data.cpython-312.pyc b/backend/app/api/__pycache__/data.cpython-312.pyc index a167b66d..cb682c8e 100644 Binary files a/backend/app/api/__pycache__/data.cpython-312.pyc and b/backend/app/api/__pycache__/data.cpython-312.pyc differ diff --git a/backend/app/api/data.py b/backend/app/api/data.py index 85b22abe..1748479c 100644 --- a/backend/app/api/data.py +++ b/backend/app/api/data.py @@ -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() diff --git a/frontend/src/api/index.ts b/frontend/src/api/index.ts index b830d5de..6203a994 100644 --- a/frontend/src/api/index.ts +++ b/frontend/src/api/index.ts @@ -67,6 +67,11 @@ export const dataApi = { form.append('file', file) return api.post(`/data/import-excel${qs ? '?' + qs : ''}`, form) }, + importExcelSmart: (file: File) => { + const form = new FormData() + form.append('file', file) + return api.post('/data/import-excel-smart', form, { timeout: 60000 }) + }, listSources: () => api.get('/data/sources'), createSource: (data: any) => api.post('/data/sources', data), updateSource: (id: number, data: any) => api.put(`/data/sources/${id}`, data), diff --git a/frontend/src/views/DataManage.vue b/frontend/src/views/DataManage.vue index bad10f3f..ce5693b3 100644 --- a/frontend/src/views/DataManage.vue +++ b/frontend/src/views/DataManage.vue @@ -5,52 +5,17 @@ - +
拖拽或点击上传Excel文件
-
支持 .xlsx .xls，可一次选择多个文件（按住Ctrl/Shift多选）
+
支持 .xlsx .xls，自动识别利润表/现金流量表/资产负债表/KPI数据表
{{ f.name }}
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 导入 {{ files.length }} 个文件 -
+ 🤖 智能导入 {{ files.length }} 个文件 +
@@ -77,7 +42,7 @@ @@ -135,14 +100,10 @@ const activeTab = ref('import') const files = ref([]) const uploading = ref(false) const result = ref('') -const detectedCols = ref([]) -const colMap = ref({ kpi: 'kpi_code', period: 'period', value: 'actual_value', defaultPeriod: '' }) function handleFile(f: any) { if (f.raw && !files.value.some(ex => ex.name === f.raw.name && ex.size === f.raw.size)) { files.value.push(f.raw) - // 从第一个文件检测列名 - if (files.value.length === 1) detectColumns(f.raw) } } function handleRemove(f: any) { @@ -151,51 +112,21 @@ function handleRemove(f: any) { function removeFile(i: number) { files.value.splice(i, 1) } -async function detectColumns(file: File) { - // 用 Web 方式读 Excel 列名（仅第一行），供用户映射 - try { - const buf = await file.arrayBuffer() - const XLSX = (await import('xlsx')).default - const wb = XLSX.read(buf, { type: 'array' }) - const ws = wb.Sheets[wb.SheetNames[0]] - const rows: any[] = XLSX.utils.sheet_to_json(ws, { header: 1 }) - if (rows.length > 0) { - detectedCols.value = (rows[0] as string[]).filter(Boolean) - // 尝试智能匹配 - const all = detectedCols.value.map(c => c.toLowerCase().replace(/[\\s　]/g, '')) - const kpiIdx = all.findIndex(c => /^(kpi_?code|编码|科目|项目|指标名称?)$/.test(c)) - const periodIdx = all.findIndex(c => /^(period|期间|月份?|日期|年月)$/.test(c)) - const valIdx = all.findIndex(c => /^(actual_?value|金额|数值|本月数|本期金额?|实际值)$/.test(c)) - if (kpiIdx >= 0) colMap.value.kpi = detectedCols.value[kpiIdx] - if (periodIdx >= 0) colMap.value.period = detectedCols.value[periodIdx] - if (valIdx >= 0) colMap.value.value = detectedCols.value[valIdx] - } - } catch (_) { /* 预览列名失败不影响导入 */ } -} async function doImport() { if (files.value.length === 0) return uploading.value = true result.value = '' const msgs: string[] = [] - const params: Record = { - kpi_col: colMap.value.kpi || 'kpi_code', - value_col: colMap.value.value || 'actual_value', - } - if (colMap.value.period && colMap.value.period !== '__fixed__') params['period_col'] = colMap.value.period - if (colMap.value.period === '__fixed__' && colMap.value.defaultPeriod) params['default_period'] = colMap.value.defaultPeriod - const qs = new URLSearchParams(params).toString() for (const f of files.value) { try { - const r: any = await dataApi.importExcel(f, qs) - const skipped = r.skipped || 0 - const total = r.total || 0 - msgs.push(`📄 ${f.name}: ${total}条导入${skipped > 0 ? `, ${skipped}条跳过` : ''}`) + const r: any = await dataApi.importExcelSmart(f) + const msg = r.message || '' + msgs.push(`📄 ${f.name}: ${msg}`) } catch (e: any) { msgs.push(`❌ ${f.name}: ${e?.response?.data?.detail || '导入失败'}`) } } files.value = [] - detectedCols.value = [] result.value = msgs.join('\n') uploading.value = false }