完成差旅发票录入流程

2026-06-11 19:22:34 +08:00
parent cf567c22f2
commit 10115214aa
50 changed files with 3033 additions and 2756 deletions
--- a/src/web/README.md
+++ b/src/web/README.md
@@ -11,7 +11,6 @@ last_reviewed: 2026-06-09
 - **会话隔离**：每次上传生成独立 `session_id`，文件、日志、配置、结果各自隔离在 `uploads/<session_id>/` 目录下，避免并发冲突。
 - **异步处理**：耗时的 PDF 提取、LLM 调用在后台线程执行，前端通过 SSE 实时查看日志流，不阻塞 HTTP 连接。
 - **前后端分离最小化**：前端使用原生 JS + Bootstrap 5，不引入构建工具，保持单页应用轻量可维护。
- **双模式支持**：PDF 发票提取模式和 CSV 快捷上传模式，后者跳过 LLM 识别和 PDF 解析，直接处理已有发票数据。

 ## 文件结构

@@ -51,7 +50,6 @@ src/web/
 | GET | `/` | 主界面 |
 | POST | `/api/session` | 创建会话，返回 session_id |
 | POST | `/api/upload/<sid>` | 上传 PDF/图片 |
-| POST | `/api/upload-csv/<sid>` | 上传 CSV 发票数据 |
 | GET | `/api/files/<sid>` | 列出会话文件 |
 | POST | `/api/process/<sid>` | 启动管道（后台线程） |
 | GET | `/api/logs/<sid>` | SSE 日志流 |
--- a/src/web/app.py
+++ b/src/web/app.py
@@ -38,13 +38,32 @@ from src.doc.fill_consumable_doc import (  # noqa: E402, I001
    fill_consumable_from_template,
 )
 from src.doc.invoice import (  # noqa: E402, I001
-    classify_invoice_batch,
    load_csv,
    load_invoice_csv,
    save_csv as save_payment_csv,
    save_invoice_csv,
+    save_application_json,
 )

+
+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

@@ -161,7 +180,7 @@ def _has_general_invoices(rows: list[dict[str, str]]) -> bool:
            invoices.append(row)
    if not invoices:
        return False
-    groups = classify_invoice_batch(invoices)
+    groups = _classify_invoice_batch(invoices)
    return len(groups["general"]) > 0


@@ -179,7 +198,7 @@ def _get_invoice_groups(rows: list[dict[str, str]]) -> dict[str, int]:
        # 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)
+    groups = _classify_invoice_batch(invoices)
    return {
        "travel_count": len(groups["travel"]),
        "general_count": len(groups["general"]),
@@ -250,14 +269,18 @@ def run_pipeline_web(session_dir: Path, config: dict[str, Any]) -> dict[str, Any
    start = time.time()

    # ---- Step 1: 发票提取 ----
-    invoices, groups = extract_invoices(str(session_dir))
+    invoices, applications, groups = extract_invoices(str(session_dir))
    if not invoices:
        return {"ok": False, "error": "未提取到任何发票数据"}

-    # 保存两个 CSV：支付记录级别（供 bot/出库单使用）和发票级别（供人工参考）
+    # 保存 CSV：支付记录级别（供 bot/出库单使用）和发票级别（供人工参考）
    save_payment_csv(invoices, session_dir / "payment_records.csv")
    save_invoice_csv(invoices, session_dir / "invoice_summary.csv")

+    # 出差申请单单独保存
+    if applications:
+        save_application_json(applications, session_dir / "travel_applications.json")
+
    # 统计发票总数
    invoice_count = sum(len(inv.get("_matched_invoices", [])) for inv in invoices)

@@ -276,50 +299,6 @@ def run_pipeline_web(session_dir: Path, config: dict[str, Any]) -> dict[str, Any
    return result


-def run_csv_pipeline_web(session_dir: Path, config: dict[str, Any], csv_filename: str) -> dict[str, Any]:
-    """直接使用上传的 CSV 文件，跳过 PDF 提取"""
-    start = time.time()
-
-    csv_path = session_dir / csv_filename
-    if not csv_path.exists():
-        return {"ok": False, "error": "CSV 文件不存在"}
-
-    # 尝试读取支付记录格式
-    rows = load_csv(csv_path)
-    if rows is None:
-        # 尝试读取发票级别格式
-        invoice_rows = load_invoice_csv(csv_path)
-        if invoice_rows is None:
-            return {"ok": False, "error": "CSV 读取失败"}
-        # 发票级别格式：直接统计
-        type_stats = _get_invoice_groups(invoice_rows)
-        elapsed = time.time() - start
-        return {
-            "ok": True,
-            "elapsed": f"{elapsed:.1f}s",
-            "invoice_count": len(invoice_rows),
-            "csv_url": f"/api/download/{session_dir.name}/{csv_filename}",
-            "travel_count": type_stats["travel_count"],
-            "general_count": type_stats["general_count"],
-        }
-
-    # 支付记录格式：统计发票类型
-    type_stats = _get_invoice_groups(rows)
-
-    elapsed = time.time() - start
-    result = {
-        "ok": True,
-        "elapsed": f"{elapsed:.1f}s",
-        "invoice_count": type_stats["travel_count"] + type_stats["general_count"],
-        "csv_url": f"/api/download/{session_dir.name}/{csv_filename}",
-        "travel_count": type_stats["travel_count"],
-        "general_count": type_stats["general_count"],
-    }
-    doc_fill = _try_fill_consumable_doc(session_dir, config)
-    _append_doc_download(result, session_dir.name, doc_fill)
-    return result
-
-
 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）

@@ -331,9 +310,10 @@ def run_financial_submit(session_dir: Path, config: dict[str, Any]) -> dict[str,
    if not csv_path.exists():
        return {"ok": False, "error": "未找到发票数据，请先处理"}

-    from src.bot import load_invoice_data, run_bot_web
+    from src.bot import run_bot_web

-    bot_invoices = load_invoice_data(str(csv_path), config)
+    # 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)
@@ -345,7 +325,7 @@ def run_financial_submit(session_dir: Path, config: dict[str, Any]) -> dict[str,
        else:
            fill_log.info("检测到普通发票，使用普通报销模式")

-    run_bot_web(config, bot_invoices, session_dir)
+    run_bot_web(config, session_dir)
    return {"ok": True}


@@ -384,22 +364,6 @@ def upload_file(session_id: str) -> Any:
    return jsonify({"ok": True, "filename": safe_name})


-@app.route("/api/upload-csv/<session_id>", methods=["POST"])
-def upload_csv(session_id: str) -> Any:
-    """上传 CSV 发票数据文件（跳过 PDF 提取）"""
-    session_dir = _validate_session(session_id)
-    if isinstance(session_dir, tuple):
-        return session_dir
-
-    f = request.files.get("file")
-    if not f or not f.filename:
-        return jsonify({"error": "未选择文件"}), 400
-
-    safe_name = Path(f.filename).name
-    f.save(str(session_dir / safe_name))
-    return jsonify({"ok": True, "filename": safe_name})
-
-
@app.route("/api/files/<session_id>", methods=["GET"])
 def list_files(session_id: str) -> Any:
    """列出会话目录中的文件"""
@@ -420,7 +384,6 @@ def start_process(session_id: str) -> Any:
        return session_dir

    body = request.get_json(silent=True) or {}
-    mode = body.get("mode", "auto")  # "pdf", "csv", or "auto"

    # 读取配置
    config = _build_web_config(body)
@@ -435,19 +398,7 @@ def start_process(session_id: str) -> Any:
    def _run() -> None:
        result = {"ok": False, "error": "未知错误"}
        try:
-            if mode == "csv":
-                csv_files = list(session_dir.glob("*.csv"))
-                if not csv_files:
-                    result = {"ok": False, "error": "未找到 CSV 文件"}
-                else:
-                    result = run_csv_pipeline_web(session_dir, config, csv_files[0].name)
-            else:
-                csv_files = list(session_dir.glob("*.csv"))
-                pdf_files = list(session_dir.glob("*.pdf"))
-                if csv_files and not pdf_files:
-                    result = run_csv_pipeline_web(session_dir, config, csv_files[0].name)
-                else:
-                    result = run_pipeline_web(session_dir, config)
+            result = run_pipeline_web(session_dir, config)
        except BaseException as e:
            result = {"ok": False, "error": str(e)}
            if isinstance(e, KeyboardInterrupt | SystemExit):
--- a/src/web/static/README.md
+++ b/src/web/static/README.md
@@ -0,0 +1,18 @@
+---
+last_reviewed: 2026-06-11
+---
+
+# src/web/static — 静态资源目录
+
+存放 Web 界面的 CSS 样式表和 JavaScript 前端逻辑。
+
+## 文件结构
+
+| 路径 | 说明 |
+|------|------|
+| `css/index.css` | 全局样式：上传区域、日志面板、可编辑表格、状态徽章 |
+| `js/index.js` | 前端逻辑：文件上传、SSE 日志监听、发票数据编辑、配置同步、移动端扫码上传、财务提交 |
+
+## 技术栈
+
+原生 JavaScript + Bootstrap 5，无构建工具，保持单页应用轻量可维护。
--- a/src/web/static/js/index.js
+++ b/src/web/static/js/index.js
@@ -1,6 +1,5 @@
 let sessionId = null;
 const pdfFiles = [], imgFiles = [];
-let csvFile = null;
 let invoiceData = [];   // 当前编辑数据 [{__row, ...fields}]
 let csvFilename = '';    // 当前 CSV 文件名
 let lastDownloadUrls = {};  // 最近一次可下载文件链接
@@ -50,23 +49,6 @@ function renderFileList(type) {
  ).join('');
 }

-// ---- CSV 上传 ----
-function handleCsvFile(input) {
-  const file = input.files[0];
-  if (!file) return;
-  csvFile = file;
-  document.getElementById('csv-zone').classList.add('active');
-  document.getElementById('csv-list').innerHTML =
-    `<span class="file-tag">${file.name}<span class="remove" onclick="event.stopPropagation();removeCsvFile()">&times;</span></span>`;
-  input.value = '';
-}
-
-function removeCsvFile() {
-  csvFile = null;
-  document.getElementById('csv-zone').classList.remove('active');
-  document.getElementById('csv-list').innerHTML = '';
-}
-
 // ---- 配置上传 ----
 function handleConfigUpload(input) {
  const file = input.files[0];
@@ -122,22 +104,10 @@ function handleConfigUpload(input) {
  });
 });

-// CSV 拖拽
-const csvZone = document.getElementById('csv-zone');
-csvZone.addEventListener('dragover', e => { e.preventDefault(); csvZone.classList.add('dragover'); });
-csvZone.addEventListener('dragleave', () => csvZone.classList.remove('dragover'));
-csvZone.addEventListener('drop', e => {
-  e.preventDefault();
-  csvZone.classList.remove('dragover');
-  const file = Array.from(e.dataTransfer.files).find(f => f.name.toLowerCase().endsWith('.csv'));
-  if (file) handleCsvFile({ files: [file] });
-});
-
 // ---- 处理 ----
 async function startProcess() {
-  const isCsvMode = !!csvFile;
-  if (!isCsvMode && !pdfFiles.length && !imgFiles.length) {
-    alert('请先上传文件或 CSV');
+  if (!pdfFiles.length && !imgFiles.length) {
+    alert('请先上传文件或图片');
    return;
  }

@@ -152,17 +122,11 @@ async function startProcess() {
  try {
    await ensureSession();

-    if (isCsvMode) {
+    const allFiles = [...pdfFiles.map(f => ({f, t:'pdf'})), ...imgFiles.map(f => ({f, t:'img'}))];
+    for (const {f} of allFiles) {
      const fd = new FormData();
-      fd.append('file', csvFile);
-      await fetch(`/api/upload-csv/${sessionId}`, { method: 'POST', body: fd });
-    } else {
-      const allFiles = [...pdfFiles.map(f => ({f, t:'pdf'})), ...imgFiles.map(f => ({f, t:'img'}))];
-      for (const {f} of allFiles) {
-        const fd = new FormData();
-        fd.append('file', f);
-        await fetch(`/api/upload/${sessionId}`, { method: 'POST', body: fd });
-      }
+      fd.append('file', f);
+      await fetch(`/api/upload/${sessionId}`, { method: 'POST', body: fd });
    }

    document.getElementById('status').innerHTML = '<span class="badge bg-info status-badge">处理中...</span>';
@@ -174,7 +138,6 @@ async function startProcess() {
      default_card_no: document.getElementById('cfg-card').value,
      default_person_id: document.getElementById('cfg-person-id').value,
      consumable_storage: document.getElementById('cfg-storage').value,
-      mode: isCsvMode ? 'csv' : 'auto',
    };

    await fetch(`/api/process/${sessionId}`, {
@@ -248,8 +211,13 @@ function showDownloadLinks(result) {
  ).join('');

  if (warn) {
-    if (result.doc_ok === false && result.doc_error) {
+    if (result.doc_skipped) {
      warn.style.display = 'block';
+      warn.style.color = '#0d6efd';
+      warn.textContent = result.doc_message || '差旅报销无需生成易耗品出库单';
+    } else if (result.doc_ok === false && result.doc_error) {
+      warn.style.display = 'block';
+      warn.style.color = '';
      warn.textContent = '出库单未生成：' + result.doc_error;
    } else {
      warn.style.display = 'none';
@@ -257,7 +225,7 @@ function showDownloadLinks(result) {
    }
  }

-  section.style.display = items.length || (result.doc_ok === false) ? 'block' : 'none';
+  section.style.display = items.length || (result.doc_ok === false) || result.doc_skipped ? 'block' : 'none';
 }

 // ---- 发票数据编辑 ----
--- a/src/web/templates/README.md
+++ b/src/web/templates/README.md
@@ -0,0 +1,14 @@
+---
+last_reviewed: 2026-06-11
+---
+
+# src/web/templates — HTML 模板目录
+
+存放 Flask 渲染的 HTML 模板文件。
+
+## 模板清单
+
+| 文件 | 说明 |
+|------|------|
+| `index.html` | PC 端主界面：包含文件上传区、配置表单、处理按钮、SSE 日志面板、可编辑发票表格、下载链接、财务提交按钮、移动端二维码 |
+| `mobile_upload.html` | 移动端上传页面：支持拍照/相册选择，上传至当前会话 |
--- a/src/web/templates/index.html
+++ b/src/web/templates/index.html
@@ -43,17 +43,6 @@
    </div>
  </div>

-  <!-- CSV 快捷上传 -->
-  <div class="mb-4">
-    <div class="section-title">📊 CSV 快捷上传 <span class="text-muted fw-normal" style="font-size:12px">（已有发票数据 CSV 可直接上传，跳过提取和 LLM 识别）</span></div>
-    <div class="upload-zone" id="csv-zone" onclick="document.getElementById('csv-input').click()">
-      <div class="icon">📊</div>
-      <div class="text-muted" style="font-size:13px">点击或拖拽上传 CSV 文件</div>
-      <div id="csv-list" class="mt-2"></div>
-    </div>
-    <input type="file" id="csv-input" accept=".csv" hidden onchange="handleCsvFile(this)">
-  </div>
-
  <!-- 配置表单 -->
  <div class="card mb-4">
    <div class="card-body">
@@ -111,7 +100,7 @@
  <div class="card mb-4" id="edit-section" style="display:none">
    <div class="card-body">
      <div class="section-title d-flex justify-content-between align-items-center">
-        <span>📝 发票数据（可编辑）</span>
+        <span>📝 付款记录（可编辑）</span>
        <div class="d-flex justify-content-end align-items-center">
          <button class="btn btn-primary" id="btn-submit" onclick="submitFinancial()">🚀 提交到财务系统</button>
        </div>