日常报销和差旅报销都可以走通

2026-06-12 12:06:06 +08:00
parent 10115214aa
commit 6d66a27aab
22 changed files with 1342 additions and 810 deletions
--- a/src/web/README.md
+++ b/src/web/README.md
@@ -1,5 +1,5 @@
 ---
-last_reviewed: 2026-06-09
+last_reviewed: 2026-06-11
 ---

 # src/web 模块设计说明
@@ -29,18 +29,32 @@ src/web/

 ## 数据流

-```
-用户上传文件 → 创建 session → 文件写入 uploads/<sid>/
-     ↓
-后台线程执行管道: extract_invoices() → enrich_with_llm() → save_csv()
-     ↓
-结果写入 session 目录: invoice_summary.csv / result.json / session.log
-     ↓
-前端 SSE 轮询 result.json 变化 → 显示完成状态
-     ↓
-前端加载 CSV 数据 → 可编辑表格展示 → 用户修改后保存
-     ↓
-用户点击提交 → run_financial_submit() → bot 自动填报财务系统
+```mermaid
+graph TD
+    A[用户上传文件] --> B[创建 session]
+    B --> C[文件写入 uploads/<sid>/]
+    C --> D[后台线程执行管道]
+    D --> E["extract_invoices()"]
+    E --> F["enrich_with_llm()"]
+    F --> G["save_csv()"]
+    G --> H["结果写入 session 目录"]
+    H --> I["invoice_summary.csv"]
+    H --> J["invoice_groups.json"]
+    H --> K["result.json"]
+    H --> L["session.log"]
+    E --> M{"判断报销类型"}
+    M -->|差旅| N["extract_travel_info()"]
+    M -->|普通| O["extract_normal_info()"]
+    N --> P["travel_info.json"]
+    O --> Q["normal_info.json"]
+    K --> R["前端 SSE 轮询 → 显示完成状态"]
+    R --> S["前端加载 CSV → 可编辑表格"]
+    S --> T["用户修改后保存"]
+    T --> U["用户点击提交"]
+    U --> V["run_financial_submit()"]
+    V --> W["bot 自动填报财务系统"]
+    W --> X["差旅模式: travel_info.json → 填报差旅单 → 上传差旅附件"]
+    W --> Y["普通模式: normal_info.json → 基本信息 → 录入明细 → 支付信息 → 上传附件"]
 ```

 ## API 路由
@@ -70,7 +84,16 @@ src/web/
 - **差旅发票**（高铁票/酒店住宿）：不生成易耗品出库单，走差旅报销流程
 - **普通发票**：生成易耗品出库单（Word 文档），走普通报销流程

-`classify_invoice_batch()` 根据发票内容自动分类，`_try_fill_consumable_doc()` 仅对普通发票生成出库单。
+`extract_invoices()` 在提取阶段完成分类，结果保存为 `invoice_groups.json`（包含 `travel_count`、`general_count`、`application_count`）。后续步骤（出库单生成、财务填报）统一从该文件读取分类结果，避免重复解析 CSV 和 JSON 字段。
+
+### LLM 信息提取（2026-06-11）
+
+发票提取和匹配完成后，根据类型分流调用 LLM 提取结构化报销信息：
+
+- **差旅发票**：调用 `extract_travel_info()`，提取出差事由、地点、时间、交通/住宿明细、补助清单、支付方式、附件清单，缓存为 `travel_info.json`。
+- **普通发票**：调用 `extract_normal_info()`，提取报销说明、发票总数、总金额、支付方式、附件清单，缓存为 `normal_info.json`。
+
+Bot 填报时优先使用 LLM 提取的信息（`travel_info`/`normal_info`），降级时从缓存加载原始发票数据。

 ### 移动端同步

--- a/src/web/app.py
+++ b/src/web/app.py
@@ -19,7 +19,7 @@ import threading
 import time
 import uuid
 from pathlib import Path
-from typing import Any
+from typing import Any, cast
 from urllib.parse import quote

 from flask import Flask, Response, jsonify, render_template, request, stream_with_context
@@ -46,24 +46,6 @@ from src.doc.invoice import (  # noqa: E402, I001
 )


-def _classify_invoice_batch(
-    invoices: list[dict[str, str]],
-) -> dict[str, list[dict[str, str]]]:
-    """按发票类型分组"""
-    travel: list[dict[str, str]] = []
-    general: list[dict[str, str]] = []
-    application: list[dict[str, str]] = []
-    for inv in invoices:
-        inv_type = inv.get("invoice_type", "general")
-        if inv_type == "application":
-            application.append(inv)
-        elif inv_type in ("train", "hotel"):
-            travel.append(inv)
-        else:
-            general.append(inv)
-    return {"travel": travel, "general": general, "application": application}
-
-
 fill_log = get_logger("fill_consumable_doc")
 CONSUMABLE_TEMPLATE = PROJECT_ROOT / CONSUMABLE_DOC_FILENAME

@@ -72,11 +54,32 @@ app = Flask(__name__, template_folder="templates")
 UPLOAD_BASE = PROJECT_ROOT / "src" / "web" / "uploads"
 SESSION_LOG_FILE = "session.log"
 SESSION_RESULT_FILE = "result.json"
+INVOICE_GROUPS_FILE = "invoice_groups.json"


-# ================================================================
-# 日志收集器 — 捕获管道日志到文件，SSE 端点通过 tail -f 读取
-# ================================================================
+def _save_invoice_groups(session_dir: Path, groups: dict[str, list[dict[str, str]]]) -> None:
+    """保存发票分类结果到 session 目录的 JSON 文件"""
+    groups_path = session_dir / INVOICE_GROUPS_FILE
+    # 只保存各组的数量统计，避免重复存储完整发票数据
+    data = {
+        "travel_count": len(groups.get("travel", [])),
+        "general_count": len(groups.get("general", [])),
+        "application_count": len(groups.get("application", [])),
+    }
+    with open(groups_path, "w", encoding="utf-8") as f:
+        json.dump(data, f, ensure_ascii=False, indent=2)
+
+
+def _load_invoice_groups(session_dir: Path) -> dict[str, int] | None:
+    """从 session 目录加载发票分类统计"""
+    groups_path = session_dir / INVOICE_GROUPS_FILE
+    if not groups_path.exists():
+        return None
+    try:
+        with open(groups_path, encoding="utf-8") as f:
+            return cast(dict[str, int] | None, json.load(f))
+    except Exception:
+        return None


 class _SSELogHandler(logging.Handler):
@@ -164,69 +167,33 @@ def _resolve_invoice_csv(session_dir: Path) -> Path | None:
    return None


-def _has_general_invoices(rows: list[dict[str, str]]) -> bool:
-    """检查发票列表中是否包含普通发票（需要生成易耗品出库单）"""
-    invoices = []
-    for row in rows:
-        # 支付记录格式：从 _invoices_json 还原
-        invoices_json = row.get("_invoices_json", "")
-        if invoices_json:
-            try:
-                invoices.extend(json.loads(invoices_json))
-            except json.JSONDecodeError:
-                pass
-        # 发票级别格式：直接使用
-        elif "发票类型" in row:
-            invoices.append(row)
-    if not invoices:
-        return False
-    groups = _classify_invoice_batch(invoices)
-    return len(groups["general"]) > 0
-
-
-def _get_invoice_groups(rows: list[dict[str, str]]) -> dict[str, int]:
-    """统计发票类型分布"""
-    invoices = []
-    for row in rows:
-        # 支付记录格式：从 _invoices_json 还原
-        invoices_json = row.get("_invoices_json", "")
-        if invoices_json:
-            try:
-                invoices.extend(json.loads(invoices_json))
-            except json.JSONDecodeError:
-                pass
-        # 发票级别格式：直接使用
-        elif "发票类型" in row:
-            invoices.append(row)
-    groups = _classify_invoice_batch(invoices)
-    return {
-        "travel_count": len(groups["travel"]),
-        "general_count": len(groups["general"]),
-    }
+# ================================================================
+# 出库单填写
+# ================================================================


 def _try_fill_consumable_doc(session_dir: Path, config: dict[str, Any]) -> dict[str, Any]:
    """根据 CSV 填写易耗品出库单，供会话目录下载。

-    仅当存在普通发票时才生成出库单。纯差旅发票跳过。
+    从 invoice_groups.json 读取分类结果，仅当存在普通发票时才生成出库单。
    """
    if not CONSUMABLE_TEMPLATE.exists():
        fill_log.warning("出库单模板不存在: %s", CONSUMABLE_TEMPLATE)
        return {"ok": False, "error": "出库单模板不存在，请将模板放在项目根目录"}

+    # 从统一的分类结果读取，避免重复解析 CSV/JSON
+    groups = _load_invoice_groups(session_dir)
+    if groups is None:
+        return {"ok": False, "error": "未找到发票分类数据，请先处理"}
+
+    if not groups.get("general_count", 0):
+        fill_log.info("纯差旅发票，跳过易耗品出库单生成")
+        return {"ok": False, "skipped": True, "error": "差旅发票无需生成易耗品出库单"}
+
    csv_path = _resolve_payment_csv(session_dir)
    if csv_path is None:
        return {"ok": False, "error": "未找到发票 CSV"}

-    # 检查是否有普通发票
-    rows = load_csv(csv_path)
-    if rows is None:
-        return {"ok": False, "error": "CSV 读取失败"}
-
-    if not _has_general_invoices(rows):
-        fill_log.info("纯差旅发票，跳过易耗品出库单生成")
-        return {"ok": False, "skipped": True, "error": "差旅发票无需生成易耗品出库单"}
-
    out_doc = session_dir / CONSUMABLE_DOC_FILENAME
    try:
        fill_log.info("开始填写出库单: %s", out_doc.name)
@@ -265,6 +232,10 @@ def run_pipeline_web(session_dir: Path, config: dict[str, Any]) -> dict[str, Any
    """在 Web 会话目录中执行发票提取，结果写入 session 目录下的文件

    注意：不再自动提交财务系统。提交通由 /api/submit-financial/<session_id> 触发。
+
+    在发票提取和匹配完成后立即判断报销类型：
+        - 差旅发票：调用 LLM 提取差旅信息并缓存到 travel_info.json
+        - 普通发票：无需额外提取（normal_info.json 待实现）
    """
    start = time.time()

@@ -281,6 +252,38 @@ def run_pipeline_web(session_dir: Path, config: dict[str, Any]) -> dict[str, Any
    if applications:
        save_application_json(applications, session_dir / "travel_applications.json")

+    # 保存分类结果（供后续步骤统一读取）
+    _save_invoice_groups(session_dir, groups)
+
+    # ---- Step 2: 差旅/普通信息提取 ----
+    is_travel = bool(groups.get("travel")) and not bool(groups.get("general"))
+    if is_travel:
+        from src.doc.llm_extractor import CACHE_DIR_NAME, extract_travel_info, load_cache
+
+        # 检查缓存是否已有
+        cache_map = load_cache(session_dir)
+        if not cache_map.get("travel_info"):
+            fill_log.info("开始提取差旅信息...")
+            travel_info = extract_travel_info(source_dir=session_dir)
+            cache_dir = session_dir / CACHE_DIR_NAME
+            cache_dir.mkdir(parents=True, exist_ok=True)
+            with open(cache_dir / "travel_info.json", "w", encoding="utf-8") as f:
+                json.dump(travel_info, f, ensure_ascii=False, indent=2)
+            fill_log.info("差旅信息已保存到缓存")
+    else:
+        from src.doc.llm_extractor import CACHE_DIR_NAME, extract_normal_info, load_cache
+
+        # 检查缓存是否已有
+        cache_map = load_cache(session_dir)
+        if not cache_map.get("normal_info"):
+            fill_log.info("开始提取普通发票信息...")
+            normal_info = extract_normal_info(source_dir=session_dir)
+            cache_dir = session_dir / CACHE_DIR_NAME
+            cache_dir.mkdir(parents=True, exist_ok=True)
+            with open(cache_dir / "normal_info.json", "w", encoding="utf-8") as f:
+                json.dump(normal_info, f, ensure_ascii=False, indent=2)
+            fill_log.info("普通发票信息已保存到缓存")
+
    # 统计发票总数
    invoice_count = sum(len(inv.get("_matched_invoices", [])) for inv in invoices)

@@ -302,7 +305,7 @@ def run_pipeline_web(session_dir: Path, config: dict[str, Any]) -> dict[str, Any
 def run_financial_submit(session_dir: Path, config: dict[str, Any]) -> dict[str, Any]:
    """执行财务系统填报（从前端确认后调用）

-    根据发票类型选择填报模式：
+    从 invoice_groups.json 读取分类结果，根据发票类型选择填报模式：
        - 纯差旅发票：差旅报销模式（TODO）
        - 含普通发票：普通报销模式
    """
@@ -312,14 +315,10 @@ def run_financial_submit(session_dir: Path, config: dict[str, Any]) -> dict[str,

    from src.bot import run_bot_web

-    # TODO: 改为从缓存读取或直接请求 LLM，与差旅报销保持一致
-    # bot_invoices = load_invoice_data(str(csv_path), config)
-
-    # 判断发票类型
-    rows = load_csv(csv_path)
-    if rows:
-        invoice_groups = _get_invoice_groups(rows)
-        if invoice_groups["travel_count"] and not invoice_groups["general_count"]:
+    # 从统一的分类结果读取，避免重复解析
+    groups = _load_invoice_groups(session_dir)
+    if groups:
+        if groups.get("travel_count", 0) and not groups.get("general_count", 0):
            fill_log.info("检测到纯差旅发票，使用差旅报销模式")
            # TODO: 差旅报销填报流程
        else: