未到数据按站独立 + 百世并入汇总 + 全量跑比对（失败容错）

- state_store：site_status 加 undelivered_ready 字段（旧库 ALTER 迁移）；init_db 提早到启动最前（server lifespan + launch_and_prepare 第0步），避免 /api/status 早于迁移报错 - expected_undelivered：重构为 process(name)/process_baishi/write_site_file/build_full_report；build_summary 支持百世（仅未到件、无基数，不计入合计/图表）与失败容错（未成功站保留行无数据） - runtime：4 站 ("站","undelivered") = 下应到+实到 → 比对写 <站>-未到数据.xlsx；("__compare__","compare") 改 run_all（顺序跑5站、记成功清单 → build_full_report，未登录/失败跳过）；DATA_FILENAMES 加 undelivered、心跳探测之；_site_undelivered_handler 用 is not False 与 dispatch 一致 - site_shunxin：shunxin_expected/actual_download 改为 return with_retry 结果（修复返回 None 致调用方误判失败、以及 with_retry 失败被当成功的潜在 bug） - server：lifespan 启动时 init_db Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-17 23:19:21 +08:00
parent 26a94999dc
commit 82c80fc859
5 changed files with 272 additions and 82 deletions
--- a/expected_undelivered.py
+++ b/expected_undelivered.py
@@ -41,6 +41,13 @@ DOWNLOADS = os.path.join(BASE, "downloads")
 OUTPUT = os.path.join(BASE, "output")
 OUTFILE = os.path.join(OUTPUT, "应到未到数据.xlsx")

+# 汇总报表覆盖的全部站点（4 站在前、百世在末；汇总页图表只取 4 站）
+ALL_REPORT_SITES = ["顺心", "中通", "韵达", "安能", "百世"]
+# 4 站单站未到明细文件名（百世未到文件由站点直接产出，名为 BAISHI_FILE）
+SITE_UNDELIVERED_FILE = "{name}-未到数据.xlsx"
+BAISHI_FILE = "百世-应到未到货物数据.xlsx"
+BAISHI_COLUMNS = ["类型", "子单号", "运单号", "最新扫描记录"]
+

 # ============================ 比对逻辑 ============================

@@ -134,8 +141,16 @@ STATIONS = [
 ]


-def process(cfg):
-    """返回 (列名list, 明细行list[dict], 统计dict)；源文件缺失时返回 None。"""
+def _site_cfg(name):
+    """按名称取 4 站配置（百世不在 STATIONS，返回 None）。"""
+    return next((c for c in STATIONS if c["name"] == name), None)
+
+
+def process(name):
+    """4 站单站比对：返回 (列名list, 明细行list[dict], 统计dict)；源文件缺失或非 4 站返回 None。"""
+    cfg = _site_cfg(name)
+    if cfg is None:
+        return None
    exp_path = os.path.join(DOWNLOADS, cfg["exp"])
    act_path = os.path.join(DOWNLOADS, cfg["act"])
    if not os.path.exists(exp_path) or not os.path.exists(act_path):
@@ -268,6 +283,78 @@ def write_station(ws, columns, rows):
    ws.print_title_rows = "1:1"


+# ============================ 单站 / 全量产出 ============================
+
+
+def process_baishi():
+    """百世：读站点直供的未到明细，返回 (columns, rows, stats)；文件缺失返回 None。
+    百世文件本身即未到结果（无应到/已到基数），统计只能给出未到件数。"""
+    path = os.path.join(DOWNLOADS, BAISHI_FILE)
+    if not os.path.exists(path):
+        return None
+    df = pd.read_excel(path, dtype=str).fillna("")
+    rows = df.to_dict("records")
+    wb_count = df["运单号"].nunique() if "运单号" in df.columns else len(rows)
+    stats = {
+        "运单数": wb_count,
+        "应到件": None,
+        "已到件": None,
+        "未到件": len(rows),
+        "涉及运单": wb_count,
+        "完全未到": None,
+        "部分未到": None,
+        "重复运单": 0,
+    }
+    return (BAISHI_COLUMNS, rows, stats)
+
+
+def write_site_file(name):
+    """4 站：把该站未到明细写到 downloads/<站>-未到数据.xlsx。
+    应到/实到缺（process 返回 None）→ 删旧文件、返回 False；成功返回 True。"""
+    path = os.path.join(DOWNLOADS, SITE_UNDELIVERED_FILE.format(name=name))
+    out = process(name)
+    if out is None:
+        if os.path.exists(path):
+            os.remove(path)
+        return False
+    columns, rows, _stats = out
+    wb = Workbook()
+    wb.remove(wb.active)
+    ws = wb.create_sheet(name)
+    write_station(ws, columns, rows)
+    wb.save(path)
+    return True
+
+
+def build_full_report(include):
+    """生成全站汇总报表 output/应到未到数据.xlsx。
+    include: 本次成功的站点集合；未成功站点在汇总里保留行、无数据（不影响他站）。
+    返回 {站点: 未到件或None} 供日志。"""
+    os.makedirs(OUTPUT, exist_ok=True)
+    wb = Workbook()
+    wb.remove(wb.active)
+    summary_ws = wb.create_sheet("汇总报表")  # 首页占位
+
+    summary = []  # (name, stats_or_None)，顺序：4 站 + 百世
+    for name in ALL_REPORT_SITES:
+        if name == "百世":
+            out = process_baishi() if "百世" in include else None
+            columns = BAISHI_COLUMNS
+        else:
+            out = process(name) if name in include else None
+            cfg = _site_cfg(name)
+            columns = cfg["columns"] if cfg else []
+        stats = out[2] if out is not None else None
+        rows = out[1] if out is not None else []
+        summary.append((name, stats))
+        ws = wb.create_sheet(name)
+        write_station(ws, columns, rows)
+
+    build_summary(summary_ws, summary, datetime.now().strftime("%Y-%m-%d %H:%M"))
+    wb.save(OUTFILE)
+    return {n: (s["未到件"] if s else None) for (n, s) in summary}
+
+
 # ============================ 写汇总报表 ============================


@@ -275,12 +362,15 @@ def build_summary(ws, results, generated_at):
    center = Alignment(horizontal="center", vertical="center")
    left = Alignment(horizontal="left", vertical="center", indent=1)

-    t_wb = sum(s["运单数"] for _, s in results)
-    t_exp = sum(s["应到件"] for _, s in results)
-    t_arr = sum(s["已到件"] for _, s in results)
-    t_miss = sum(s["未到件"] for _, s in results)
-    t_full = sum(s["完全未到"] for _, s in results)
-    t_part = sum(s["部分未到"] for _, s in results)
+    # 合计/KPI 只算 4 站中本次成功的（百世无应到基数、失败站无数据，均不计入）
+    four = [(n, s) for (n, s) in results if n != "百世"]
+    ok = [s for _, s in four if s]
+    t_wb = sum(s["运单数"] for s in ok)
+    t_exp = sum(s["应到件"] for s in ok)
+    t_arr = sum(s["已到件"] for s in ok)
+    t_miss = sum(s["未到件"] for s in ok)
+    t_full = sum(s["完全未到"] for s in ok)
+    t_part = sum(s["部分未到"] for s in ok)
    rate = (t_miss / t_exp) if t_exp else 0

    ws.sheet_view.showGridLines = False
@@ -387,20 +477,27 @@ def build_summary(ws, results, generated_at):
        cell.border = BORDER
    ws.row_dimensions[9].height = 22

-    # —— 各站数据行 ——
+    # —— 各站数据行（4 站 + 百世）——
    r = 10
    for idx, (name, s) in enumerate(results):
-        srate = (s["未到件"] / s["应到件"]) if s["应到件"] else 0
-        vals = [
-            name,
-            s["运单数"],
-            s["应到件"],
-            s["已到件"],
-            s["未到件"],
-            srate,
-            s["完全未到"],
-            s["部分未到"],
-        ]
+        is_baishi = name == "百世"
+        srate = 0
+        if s is None:
+            vals = [f"{name}（无数据）", 0, 0, 0, 0, 0, 0, 0]
+        elif is_baishi:
+            vals = [name, s["运单数"], "—", "—", s["未到件"], "—", "—", "—"]
+        else:
+            srate = (s["未到件"] / s["应到件"]) if s["应到件"] else 0
+            vals = [
+                name,
+                s["运单数"],
+                s["应到件"],
+                s["已到件"],
+                s["未到件"],
+                srate,
+                s["完全未到"],
+                s["部分未到"],
+            ]
        for i, v in enumerate(vals):
            col = chr(ord("B") + i)
            cell = ws[f"{col}{r}"]
@@ -408,12 +505,13 @@ def build_summary(ws, results, generated_at):
            cell.font = BODY_FONT
            cell.border = BORDER
            cell.alignment = left if i == 0 else center
-            if idx % 2 == 1 and i != 5:
+            if s is None:
+                cell.fill = PatternFill("solid", fgColor="EFEFEF")
+            elif not is_baishi and idx % 2 == 1 and i != 5:
                cell.fill = PatternFill("solid", fgColor=ZEBRA)
-            if i in (1, 2, 3, 4, 6, 7):
-                cell.number_format = "#,##0"
-            if i == 5:
-                cell.number_format = "0.0%"
+            if isinstance(v, (int, float)):
+                cell.number_format = "0.0%" if i == 5 else "#,##0"
+            if i == 5 and s is not None and not is_baishi:
                cell.fill = PatternFill("solid", fgColor=heat(srate))
        ws.row_dimensions[r].height = 19
        r += 1
@@ -435,7 +533,7 @@ def build_summary(ws, results, generated_at):
        if i == 5:
            cell.number_format = "0.0%"
    ws.row_dimensions[r].height = 20
-    last_data_row = 9 + len(results)
+    last_data_row = 9 + len(four)  # 图表只取 4 站（百世无应到/已到基数，不绘图）
    chart_anchor = r + 2

    # —— 堆叠柱状图：各站已到 / 未到 ——
@@ -464,7 +562,9 @@ def build_summary(ws, results, generated_at):
    note_row = chart_anchor + 19
    notes = [
        "指标口径：未到率 ＝ 未到件数 ÷ 应到件数；完全未到运单 ＝ 整单零到货；部分未到运单 ＝ 部分到货、部分缺件。",
-        "明细见各站点工作表；缺件的子单号 / 扫描单号按各站编号规则生成，并非实到原始记录。",
+        "合计 / 图表仅含 4 站（顺心/中通/韵达/安能，应到−实到口径）；百世为站点直供未到、无应到基数，单列不计入合计。",
+        "本次下载失败的站点标注为（无数据）并计 0，不影响其余站点统计。",
+        "明细见各站点工作表；4 站缺件的子单号 / 扫描单号按各站编号规则生成，并非实到原始记录。",
    ]
    for k, text in enumerate(notes):
        rr = note_row + k
@@ -486,37 +586,32 @@ def build_summary(ws, results, generated_at):


 def main():
-    os.makedirs(OUTPUT, exist_ok=True)
-    wb = Workbook()
-    wb.remove(wb.active)
-    summary_ws = wb.create_sheet("汇总报表")  # 首页占位
-
-    print("应到未到比对结果")
+    """菜单 [9] / 离线入口：用 downloads/ 下现有文件生成全站汇总报告（有文件的站即纳入）。"""
+    print("应到未到比对（全站汇总）")
    print("-" * 56)
-    results = []
-    for cfg in STATIONS:
-        out = process(cfg)
-        if out is None:
-            continue
-        columns, rows, stats = out
-        ws = wb.create_sheet(cfg["name"])
-        write_station(ws, columns, rows)
-        results.append((cfg["name"], stats))
-        extra = f"，应到重复运单 {stats['重复运单']}" if stats["重复运单"] else ""
-        print(
-            f"{cfg['name']}：应到运单 {stats['运单数']}，应到件 {stats['应到件']}，"
-            f"已到 {stats['已到件']}，未到 {stats['未到件']} 件"
-            f"（涉及运单 {stats['涉及运单']}：完全未到 {stats['完全未到']} / 部分未到 {stats['部分未到']}）{extra}"
-        )
-
-    if not results:
+    include = set()
+    for name in ALL_REPORT_SITES:
+        if name == "百世":
+            if os.path.exists(os.path.join(DOWNLOADS, BAISHI_FILE)):
+                include.add(name)
+        else:
+            cfg = _site_cfg(name)
+            if (
+                cfg
+                and os.path.exists(os.path.join(DOWNLOADS, cfg["exp"]))
+                and os.path.exists(os.path.join(DOWNLOADS, cfg["act"]))
+            ):
+                include.add(name)
+    if not include:
        print("未处理任何站点：请确认 downloads/ 下存在源数据文件。")
        return
-
-    build_summary(summary_ws, results, datetime.now().strftime("%Y-%m-%d %H:%M"))
-
+    undel = build_full_report(include)
    print("-" * 56)
-    wb.save(OUTFILE)
+    for name in ALL_REPORT_SITES:
+        if name in include:
+            print(f"{name}：未到 {undel.get(name)} 件")
+        else:
+            print(f"{name}：无数据，跳过")
    print(f"已输出：{OUTFILE}")