backend/tests/test_import_and_model_errors.py

@@ -24,6 +24,8 @@ def test_scan_selected_student_folder_prefills_cover_identity(tmp_path, monkeypa
     assert project["status"] == "needs_confirmation"
     assert len(project["files"]) == 5
     assert project["missing"] == []
+    assert project["folder_identity"] == {"student_no": "", "name": "", "topic": ""}
+    assert all(file["detected_identity"]["student_no"] == "9000000001" for file in project["files"])
     assert scan("test", root=tmp_path)["projects"] == result["projects"]
 
 
@@ -39,6 +41,26 @@ def test_scan_conflicting_covers_need_confirmation(tmp_path, monkeypatch):
     assert project["student_no"] == ""
     assert project["warnings"]
     assert project["status"] == "needs_confirmation"
+    assert "学号" in project["warnings"][0]
+    assert "student_no" not in project["warnings"][0]
+    assert {file["detected_identity"]["student_no"] for file in project["files"]} == {"9000000001", "9000000002"}
+
+
+def test_scan_unreadable_cover_has_no_stale_identity(tmp_path, monkeypatch):
+    from wisegrade import storage
+    folder = tmp_path / "9000000001_学生甲_机器人系统"
+    folder.mkdir()
+    (folder / "阶段报告1.pdf").write_bytes(b"fixture")
+    (folder / "阶段报告2.pdf").write_bytes(b"broken")
+    def read(path):
+        if path.name.endswith("2.pdf"):
+            raise ValueError("损坏PDF")
+        return "学号：9000000001\n姓名：学生甲\n题目：机器人系统"
+    monkeypatch.setattr(storage, "first_text", read)
+    project = scan(".", root=tmp_path)["projects"][0]
+    assert project["folder_identity"]["student_no"] == "9000000001"
+    assert project["files"][0]["detected_identity"]["student_no"] == "9000000001"
+    assert project["files"][1]["detected_identity"] == {}
 
 
 def test_scan_parent_skips_empty_folders(tmp_path, monkeypatch):

backend/tests/test_import_validation.py

@@ -0,0 +1,36 @@
+import pytest
+from pydantic import ValidationError
+
+from wisegrade.api import ImportConfirm, ProjectConfirm
+
+
+def project(**changes):
+    return {"relative_dir": "test/student", "student_no": "9000000001", "name": "学生甲", "topic": "机器人项目",
+            "files": [{"relative_path": "test/student/最终报告.pdf", "category": "final_report", "sha256": "a" * 64}], **changes}
+
+
+def test_confirm_normalizes_identity_before_validating():
+    result = ProjectConfirm.model_validate(project(student_no=" 9000000001 ", name=" 学生甲 ", topic=" 机器人项目 "))
+    assert (result.student_no, result.name, result.topic) == ("9000000001", "学生甲", "机器人项目")
+
+
+@pytest.mark.parametrize("changes", [
+    {"name": "   "}, {"topic": "   "}, {"student_no": "９００００００００１"}, {"files": []},
+    {"files": [{"relative_path": "test/student/a.pdf", "category": "unknown", "sha256": "a" * 64}]},
+    {"files": [{"relative_path": "test/student/a.pdf", "category": "final_report", "sha256": "a" * 64, "status": "ignored"}]},
+    {"files": [{"relative_path": f"test/student/{i}.pdf", "category": "final_report", "sha256": "a" * 64} for i in range(2)]},
+])
+def test_confirm_rejects_invalid_identity_or_selection(changes):
+    with pytest.raises(ValidationError):
+        ProjectConfirm.model_validate(project(**changes))
+
+
+def test_empty_import_is_rejected():
+    with pytest.raises(ValidationError):
+        ImportConfirm(course_version_id=1, projects=[])
+
+
+def test_ignored_unknown_material_does_not_block_valid_selection():
+    data = project()
+    data["files"].append({"relative_path": "test/student/foreign.pdf", "category": "unknown", "sha256": "b" * 64, "status": "ignored"})
+    assert len(ProjectConfirm.model_validate(data).files) == 2

backend/wisegrade/api.py

@@ -3,7 +3,7 @@ from pathlib import Path
 
 from fastapi import APIRouter, Depends, HTTPException
 from fastapi.responses import FileResponse
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, field_validator, model_validator
 from sqlalchemy import func, select
 from sqlalchemy.orm import Session
 
@@ -67,16 +67,33 @@ class FileConfirm(BaseModel):
 
 class ProjectConfirm(BaseModel):
     relative_dir: str
-    student_no: str = Field(pattern=r"^\d{5,20}$")
+    student_no: str = Field(pattern=r"^[0-9]{5,20}$")
     name: str = Field(min_length=1)
     topic: str = Field(min_length=1)
     direction: str = ""
-    files: list[FileConfirm]
+    files: list[FileConfirm] = Field(min_length=1)
+
+    @field_validator("student_no", "name", "topic", "direction", mode="before")
+    @classmethod
+    def trim_identity(cls, value):
+        return value.strip() if isinstance(value, str) else value
+
+    @model_validator(mode="after")
+    def validate_selection(self):
+        selected = [file for file in self.files if file.status != "ignored"]
+        if not selected:
+            raise ValueError("至少选择1份资料")
+        categories = [file.category for file in selected]
+        if any(category not in CATEGORIES for category in categories):
+            raise ValueError("请选择有效材料类型")
+        if len(set(categories)) != len(categories):
+            raise ValueError("每类材料只允许选择1份，其余请设为忽略")
+        return self
 
 
 class ImportConfirm(BaseModel):
     course_version_id: int
-    projects: list[ProjectConfirm]
+    projects: list[ProjectConfirm] = Field(min_length=1)
 
 
 class BatchInput(BaseModel):

backend/wisegrade/storage.py

@@ -11,6 +11,7 @@ from .config import get_settings
 CATEGORIES = ("stage1", "stage2", "stage3", "final_report", "presentation")
 SUPPORTED = {".pdf", ".docx", ".pptx"}
 NAMES = {"stage1": "阶段报告1", "stage2": "阶段报告2", "stage3": "阶段报告3", "final_report": "最终报告", "presentation": "汇报PPT"}
+IDENTITY_LABELS = {"student_no": "学号", "name": "姓名", "topic": "选题"}
 
 
 def secure_path(relative: str, *, root: Path | None = None, must_exist=True) -> Path:
@@ -114,6 +115,7 @@ def scan(relative: str, *, root: Path | None = None):
         if item.is_dir() and not item.is_symlink() and has_materials(item)]
     for folder in folders:
         info = parse_student_folder(folder.name)
+        folder_identity = {key: info[key] for key in IDENTITY_LABELS}
         files = []
         extracted = {}
         identity_values = {}
@@ -124,6 +126,7 @@ def scan(relative: str, *, root: Path | None = None):
             if candidate.suffix.lower() not in SUPPORTED:
                 continue
             error = ""
+            identity = {}
             try:
                 text = first_text(candidate)
                 category, status = classify(candidate, text)
@@ -137,6 +140,7 @@ def scan(relative: str, *, root: Path | None = None):
             files.append({"relative_path": candidate.relative_to(base).as_posix(), "category": category, "status": status,
                           "size": stat.st_size, "mtime": stat.st_mtime, "sha256": sha256(candidate),
                           "mime_type": mimetypes.guess_type(candidate.name)[0] or "application/octet-stream", "error": error,
+                          "detected_identity": identity,
                           "first_text": text[:500] if not error else ""})
         for category in CATEGORIES:
             matches = [file for file in files if file["category"] == category]
@@ -145,17 +149,18 @@ def scan(relative: str, *, root: Path | None = None):
                     file["status"] = "duplicate"
         for key, values in identity_values.items():
             if len(values) > 1:
-                warnings.append(f"不同材料封面的{key}不一致，请核对后填写")
+                warnings.append(f"不同材料封面的{IDENTITY_LABELS[key]}不一致，请核对后填写")
             else:
                 extracted[key] = next(iter(values))
         for key, value in extracted.items():
             if info.get(key) and value != info[key]:
-                warnings.append(f"封面{key}“{value}”与目录名“{info[key]}”不一致")
+                warnings.append(f"封面{IDENTITY_LABELS[key]}“{value}”与目录名“{info[key]}”不一致")
             elif not info.get(key):
                 info[key] = value
         if warnings:
             info["status"] = "needs_confirmation"
         info.update({"relative_dir": folder.relative_to(base).as_posix(), "files": files,
+                     "folder_identity": folder_identity,
                      "detected_identity": extracted, "warnings": warnings,
                      "missing": [category for category in CATEGORIES if not any(file["category"] == category for file in files)]})
         projects.append(info)

docs/IMPORT_MODEL_FIX_2026-10-14.md

@@ -25,3 +25,15 @@
 `test/示例/汇报PPT.pdf` 首页实际显示“课程导学／自动化专业综合实践”。应在评分前确认它是否属于学生汇报稿，而不是课程说明。本次只导入和索引该示例资料包，未创建或启动它的新评分批次。
 
 运行证据保存在工作区 `.wisegrade-testing/docker-preview/`，包括 `import-model-live.json`、`import-test-sample-2026-10-14.json`、浏览器截图和构建/部署日志。实际入库与批次重试的最终状态见该目录 `import-model-final-2026-10-14.json`。
+
+## 后续：确认导入的校验与封面来源
+
+按钮被禁用的原因原来隐藏在网页布尔表达式中；扫描只返回合并后的身份，冲突时清空字段，但未提供逐文件来源，忽略文件后也不重新计算。这使用户无法从页面判断如何完成合法导入。
+
+- `d7bd152`（2 个文件）：扫描返回每份文件的封面身份和原目录身份，警告使用中文字段名；读取失败的文件不沿用上一份身份。
+- `b24930b`（3 个文件）：显示具体阻碍原因和逐文件身份；只根据当前选中文件重算身份和冲突，忽略异项目文件后可重新预填。保留人工修改，提供“使用所选资料的封面信息”入口。材料类别未知、同类多份或没有选中材料时直接提示。
+- `36bf473`（2 个文件）：API 在写入前统一去除身份字段首尾空白，要求 5–20 位 ASCII 数字学号，拒绝空白姓名/选题、空项目、全部忽略及无效/重复材料类型。忽略的未知类型文件不阻碍合法选择。
+- 后端隔离测试 **74 passed**，网页测试 **17 passed**，TypeScript/Vite 构建通过；新增用例在修复前失败。API、网页和空闲 worker 已更新，本轮没有新增数据库迁移。
+- 实际网页无接口模拟验证：输入 `1` 显示学号规则；忽略异项目 PPT 并采用剩余报告封面信息后，身份冲突清除且确认按钮可用。没有提交真实导入或调用评分模型。空项目 API 请求返回 422。证据见工作区 `docker-preview/import-root-live.json` 和对应截图。
+
+本轮修复不放宽学号格式要求，也不把不同学生的材料自动改成同一身份。已有项目若先前被人工填写为测试身份，需要核对所选资料并重新确认导入才能更新数据库中的身份。

frontend/src/App.tsx

@@ -5,6 +5,7 @@ import { DashboardOutlined, BookOutlined, FileSearchOutlined, FolderOpenOutlined
 import { api, post, put } from './api';
 import { Batches } from './Batches';
 import { projectLabel, projectsInBatch } from './batchProjects';
+import { fillImportIdentity, importErrors, reviewImport } from './importReview';
 const Chat = lazy(() => import('./Chat'));
 
 const { Header, Sider, Content } = Layout;
@@ -103,14 +104,26 @@ function Import({ openImported, scoreImported }: { openImported: (ids: number[])
   useEffect(() => { load('/courses', setCourses); }, []);
   useEffect(() => { setScanData(undefined); setImported(undefined); load(`/storage/directories?relative=${encodeURIComponent(path)}`, setDirs); }, [path]);
   useEffect(() => { if (courseId) load(`/courses/${courseId}/versions`, setVersions); }, [courseId]);
-  const editProject = (index: number, key: string, value: any) => { const next = structuredClone(scanData); next.projects[index][key] = value; setScanData(next); };
+  const errors = importErrors(scanData?.projects, versionId);
-  const editFile = (projectIndex: number, fileIndex: number, key: string, value: any) => { const next = structuredClone(scanData); next.projects[projectIndex].files[fileIndex][key] = value; setScanData(next); };
+  const editProject = (index: number, key: string, value: any) => {
+    const next = structuredClone(scanData), project = next.projects[index];
+    project[key] = value;
+    if (['student_no', 'name', 'topic'].includes(key)) project.identity_edits = { ...project.identity_edits, [key]: true };
+    setScanData(next);
+  };
+  const editFile = (projectIndex: number, fileIndex: number, key: string, value: any) => {
+    const next = structuredClone(scanData), project = next.projects[projectIndex];
+    project.files[fileIndex][key] = value; fillImportIdentity(project); setScanData(next);
+  };
+  const useCover = (index: number) => {
+    const next = structuredClone(scanData); fillImportIdentity(next.projects[index], true); setScanData(next);
+  };
   const confirm = async () => {
-    if (!versionId || !scanData?.projects?.length) return;
+    if (errors.length || importing) { message.error(errors[0] || '正在导入，请稍候'); return; }
     setImporting(true);
     try {
-      const projects = scanData.projects.map((p: any) => ({ relative_dir: p.relative_dir, student_no: p.student_no,
+      const projects = scanData.projects.map((p: any) => ({ relative_dir: p.relative_dir, student_no: p.student_no.trim(),
-        name: p.name, topic: p.topic, direction: p.direction || '',
+        name: p.name.trim(), topic: p.topic.trim(), direction: (p.direction || '').trim(),
         files: p.files.map((f: any) => ({ relative_path: f.relative_path, category: f.category,
           status: f.status === 'ignored' ? 'ignored' : 'recognized', sha256: f.sha256 })) }));
       const result = await post('/import/confirm', { course_version_id: versionId, projects });
@@ -119,14 +132,60 @@ function Import({ openImported, scoreImported }: { openImported: (ids: number[])
     } catch (error) { fail(error); }
     finally { setImporting(false); }
   };
-  return <><Title level={2}>挂载目录扫描与导入确认</Title><Paragraph>浏览 <code>/data/inbox</code> 下的目录，可选择包含学生子文件夹的总目录，也可直接进入放有 PDF、DOCX、PPTX 的资料目录扫描。封面信息会预填，请核对学号、姓名和选题后确认导入。</Paragraph><Space><Button disabled={path === '.'} onClick={() => setPath(path.includes('/') ? path.slice(0, path.lastIndexOf('/')) : '.')}>上一级</Button><Text code>{path}</Text><Button type="primary" onClick={async () => { try { setImported(undefined); setScanData(await post('/import/scan', { relative_dir: path })); } catch (e) { fail(e); } }}>扫描此目录</Button></Space><div className="folder-list">{dirs.map(dir => <Button key={dir.relative_path} onClick={() => setPath(dir.relative_path)}>📁 {dir.name}</Button>)}</div>
+  const projectIndex = (project: any) => scanData.projects.findIndex((item: any) => item.relative_dir === project.relative_dir);
+  const identityInput = (project: any, key: string, label: string) => <Input aria-label={`${label} ${project.relative_dir}`}
+    status={key === 'student_no' ? (!/^[0-9]{5,20}$/.test((project[key] || '').trim()) ? 'error' : undefined) : (!project[key]?.trim() ? 'error' : undefined)}
+    placeholder={key === 'student_no' ? '5–20位数字' : `请填写${label}`} value={project[key]}
+    onChange={event => editProject(projectIndex(project), key, event.target.value)} />;
+  return <><Title level={2}>挂载目录扫描与导入确认</Title>
+    <Paragraph>浏览 <code>/data/inbox</code> 下的目录，可选择学生总目录或直接存放资料的目录。请核对封面身份；不属于当前项目的文件可设为“忽略”。</Paragraph>
+    <Space><Button disabled={path === '.'} onClick={() => setPath(path.includes('/') ? path.slice(0, path.lastIndexOf('/')) : '.')}>上一级</Button><Text code>{path}</Text>
+      <Button type="primary" onClick={async () => { try {
+        setImported(undefined); const data = await post('/import/scan', { relative_dir: path });
+        data.projects = data.projects.map((project: any) => fillImportIdentity(project)); setScanData(data);
+      } catch (error) { fail(error); } }}>扫描此目录</Button></Space>
+    <div className="folder-list">{dirs.map(dir => <Button key={dir.relative_path} onClick={() => setPath(dir.relative_path)}>📁 {dir.name}</Button>)}</div>
     {imported && imported.projectIds.length > 0 && <Alert className="top-gap" type="success" showIcon
-      message={`已导入 ${imported.projectIds.length} 个学生资料包`}
+      message={`已导入 ${imported.projectIds.length} 个学生资料包`} description="查看已导入资料核对解析状态，或去评分选择这次导入的资料。"
-      description="点击查看已导入资料核对文件与解析状态，或去评分选择这次导入的资料。"
       action={<Space wrap><Button onClick={() => openImported(imported.projectIds)}>查看已导入资料</Button>
         <Button type="primary" onClick={() => scoreImported(imported.courseVersionId, imported.projectIds)}>去评分</Button></Space>} />}
-    {scanData && <><Divider />{!scanData.projects.length && <Alert className="top-gap" type="warning" showIcon message="未找到可导入资料" description="当前目录及其下一级学生目录中没有 PDF、DOCX 或 PPTX；请进入放有这些文件的目录再扫描。" />}<Space><Select aria-label="导入课程" style={{ width: 260 }} placeholder="课程" options={options(courses, c => c.name)} value={courseId} onChange={id => { setCourseId(id); setVersionId(undefined); setVersions([]); setImported(undefined); }} /><Select aria-label="导入课程版本" style={{ width: 270 }} placeholder="已发布课程版本" options={options(versions.filter(v => v.published), v => `v${v.version} ${v.title}`)} value={versionId} onChange={setVersionId} /><Button type="primary" loading={importing} disabled={!versionId || importing || !scanData.projects.length || scanData.projects.some((p: any) => !/^\d{5,20}$/.test(p.student_no) || !p.name?.trim() || !p.topic?.trim() || !p.files.some((f: any) => f.status !== 'ignored'))} onClick={confirm}>确认导入</Button></Space><Table className="top-gap" rowKey="relative_dir" dataSource={scanData.projects} pagination={{ pageSize: 10 }} columns={[{ title: '学号', render: (_, p, index) => <Input value={p.student_no} onChange={e => editProject(scanData.projects.findIndex((x: any) => x.relative_dir === p.relative_dir), 'student_no', e.target.value)} /> }, { title: '姓名', render: (_, p, index) => <Input value={p.name} onChange={e => editProject(scanData.projects.findIndex((x: any) => x.relative_dir === p.relative_dir), 'name', e.target.value)} /> }, { title: '选题', render: (_, p, index) => <Input value={p.topic} onChange={e => editProject(scanData.projects.findIndex((x: any) => x.relative_dir === p.relative_dir), 'topic', e.target.value)} /> }, { title: '选题方向', render: (_, p) => <Input value={p.direction || ''} placeholder="可修正" onChange={e => editProject(scanData.projects.findIndex((x: any) => x.relative_dir === p.relative_dir), 'direction', e.target.value)} /> }, { title: '待处理', render: (_, p) => <Space wrap>{p.status !== 'recognized' && <Tag color="orange">身份信息需确认</Tag>}{p.missing.map((c: string) => <Tag color="red" key={c}>缺{categories[c]}</Tag>)}{p.warnings?.map((w: string) => <Tag color="orange" key={w}>{w}</Tag>)}</Space> }]}
+    {scanData && <><Divider />{errors.length > 0 && <Alert className="top-gap" type="warning" showIcon
-      expandable={{ defaultExpandAllRows: true, expandedRowRender: (p: any) => { const pi = scanData.projects.findIndex((item: any) => item.relative_dir === p.relative_dir); return <Table<any> size="small" rowKey="relative_path" pagination={false} dataSource={p.files} columns={[{ title: '文件', dataIndex: 'relative_path' }, { title: '类型', render: (_, f, fi) => <Select style={{ width: 170 }} value={f.category} options={[{ value: 'unknown', label: '未识别' }, ...Object.entries(categories).map(([value, label]) => ({ value, label }))]} onChange={value => editFile(pi, fi, 'category', value)} /> }, { title: '处理', render: (_, f, fi) => <Select style={{ width: 120 }} value={f.status === 'ignored' ? 'ignored' : 'recognized'} options={[{ value: 'recognized', label: '导入' }, { value: 'ignored', label: '忽略' }]} onChange={value => editFile(pi, fi, 'status', value)} /> }, { title: '扫描结果', render: (_, f) => <Tag color={f.status === 'recognized' ? 'green' : 'orange'}>{f.status}</Tag> }, { title: '异常', dataIndex: 'error' }]} />; } }} /></>}
+      message={scanData.projects.length ? '暂不能确认导入' : '未找到可导入资料'}
+      description={<ul>{errors.map((error, index) => <li key={index}>{error}</li>)}</ul>} />}
+      <Space className="top-gap" wrap>
+        <Select aria-label="导入课程" style={{ width: 260 }} placeholder="课程" options={options(courses, c => c.name)} value={courseId}
+          onChange={id => { setCourseId(id); setVersionId(undefined); setVersions([]); setImported(undefined); }} />
+        <Select aria-label="导入课程版本" style={{ width: 270 }} placeholder="已发布课程版本" options={options(versions.filter(v => v.published), v => `v${v.version} ${v.title}`)} value={versionId} onChange={setVersionId} />
+        <Button type="primary" loading={importing} disabled={errors.length > 0 || importing} onClick={confirm}>确认导入</Button>
+      </Space>
+      <Table className="top-gap" rowKey="relative_dir" dataSource={scanData.projects} pagination={{ pageSize: 10 }} columns={[
+        { title: '学号', render: (_, project) => identityInput(project, 'student_no', '学号') },
+        { title: '姓名', render: (_, project) => identityInput(project, 'name', '姓名') },
+        { title: '选题', render: (_, project) => identityInput(project, 'topic', '选题') },
+        { title: '选题方向', render: (_, project) => <Input value={project.direction || ''} placeholder="可修正" onChange={event => editProject(projectIndex(project), 'direction', event.target.value)} /> },
+        { title: '待处理', render: (_, project) => { const review = reviewImport(project); return <Space direction="vertical">
+          <Space wrap>{review.errors.length > 0 ? <Tag color="red">请修正导入信息</Tag> : <Tag color="green">导入信息已填写</Tag>}
+            {review.missing.map(category => <Tag key={category}>缺{categories[category]}</Tag>)}</Space>
+          {review.warnings.map(warning => <Text key={warning} type="warning">{warning}</Text>)}
+          {review.metadata && Object.values(review.identity).some(Boolean) && <Button size="small" onClick={() => useCover(projectIndex(project))}>使用所选资料的封面信息</Button>}
+        </Space>; } },
+      ]} expandable={{ defaultExpandAllRows: true, expandedRowRender: (project: any) => {
+        const pi = projectIndex(project); return <Table<any> size="small" rowKey="relative_path" pagination={false} dataSource={project.files} columns={[
+          { title: '文件', dataIndex: 'relative_path' },
+          { title: '封面身份', render: (_, file) => <Space direction="vertical">
+            <Text>{file.detected_identity?.name ? `${file.detected_identity.name}（${file.detected_identity.student_no || '未识别学号'}）` : '首页未识别身份'}</Text>
+            <Text type="secondary">{file.detected_identity?.topic || ''}</Text></Space> },
+          { title: '类型', render: (_, file, fi) => <Select aria-label={`材料类型 ${file.relative_path}`} style={{ width: 170 }} value={file.category}
+            options={[{ value: 'unknown', label: '未识别' }, ...Object.entries(categories).map(([value, label]) => ({ value, label }))]} onChange={value => editFile(pi, fi, 'category', value)} /> },
+          { title: '处理', render: (_, file, fi) => <Select aria-label={`处理 ${file.relative_path}`} style={{ width: 120 }} value={file.status === 'ignored' ? 'ignored' : 'recognized'}
+            options={[{ value: 'recognized', label: '导入' }, { value: 'ignored', label: '忽略' }]} onChange={value => editFile(pi, fi, 'status', value)} /> },
+          { title: '扫描结果', render: (_, file) => <Tag color={file.status === 'recognized' ? 'green' : 'orange'}>
+            {({ recognized: '已识别', needs_confirmation: '需确认类型', duplicate: '同类多份', unparseable: '无法读取', ignored: '已忽略' } as Record<string, string>)[file.status] || file.status}</Tag> },
+          { title: '异常', dataIndex: 'error' },
+        ]} />;
+      } }} />
+      <Paragraph type="secondary">封面冲突请核对上表来源。允许缺少某类材料，相关评分项会标记为待处理。人工填写的信息会保留；点击“使用所选资料的封面信息”可重新采用识别值。</Paragraph>
+    </>}
   </>;
 }
 

frontend/src/importReview.ts

@@ -0,0 +1,66 @@
+const fields = ['student_no', 'name', 'topic'] as const;
+type IdentityField = typeof fields[number];
+const labels = { student_no: '学号', name: '姓名', topic: '选题' };
+const categories: Record<string, string> = { stage1: '阶段报告1', stage2: '阶段报告2', stage3: '阶段报告3',
+  final_report: '最终报告', presentation: '汇报PPT/PDF' };
+const text = (value: unknown) => String(value ?? '').trim();
+const fileName = (file: any) => text(file.relative_path).split('/').pop() || '文件';
+
+export function reviewImport(project: any) {
+  const selected = (project.files || []).filter((file: any) => file.status !== 'ignored');
+  const metadata = (project.files || []).some((file: any) => file.detected_identity != null);
+  const identity: Record<IdentityField, string> = { student_no: '', name: '', topic: '' };
+  const warnings: string[] = [];
+  for (const field of fields) {
+    const sources = new Map<string, string[]>();
+    for (const file of selected) {
+      const value = text(file.detected_identity?.[field]);
+      if (value) sources.set(value, [...(sources.get(value) || []), fileName(file)]);
+    }
+    const folderValue = text(project.folder_identity?.[field]);
+    const values = [...sources.keys()];
+    identity[field] = folderValue || (values.length === 1 ? values[0] : '');
+    if (values.length > 1) {
+      warnings.push(`${labels[field]}冲突：${values.map(value => `${value}（${sources.get(value)!.join('、')}）`).join('；')}`);
+    } else if (folderValue && values.length === 1 && folderValue !== values[0]) {
+      warnings.push(`${labels[field]}与目录不一致：封面为${values[0]}（${sources.get(values[0])!.join('、')}），目录为${folderValue}`);
+    }
+  }
+  if (!metadata) warnings.push(...(project.warnings || []));
+
+  const errors: string[] = [];
+  if (!/^[0-9]{5,20}$/.test(text(project.student_no))) errors.push('学号必须为5–20位数字');
+  if (!text(project.name)) errors.push('请填写姓名');
+  if (!text(project.topic)) errors.push('请填写选题');
+  if (!selected.length) errors.push('至少选择1份资料');
+  const counts = new Map<string, number>();
+  for (const file of selected) {
+    if (!categories[file.category]) errors.push(`${fileName(file)}：请选择材料类型`);
+    else counts.set(file.category, (counts.get(file.category) || 0) + 1);
+    if (file.error) errors.push(`${fileName(file)}：无法读取，请修复文件或设为忽略`);
+  }
+  for (const [category, count] of counts) {
+    if (count > 1) errors.push(`${categories[category]}选了${count}份，请只保留1份，其余设为忽略`);
+  }
+  const missing = Object.keys(categories).filter(category => !selected.some((file: any) => file.category === category));
+  return { selected, metadata, identity, warnings, errors, missing };
+}
+
+export function fillImportIdentity(project: any, force = false) {
+  const review = reviewImport(project);
+  if (!review.metadata) return project;
+  for (const field of fields) {
+    if (force || !project.identity_edits?.[field]) project[field] = review.identity[field];
+  }
+  if (force) project.identity_edits = {};
+  return project;
+}
+
+export function importErrors(projects: any[] | undefined, versionId: number | undefined) {
+  const errors = versionId ? [] : ['请选择已发布课程版本'];
+  if (!projects?.length) return [...errors, '当前目录没有PDF、DOCX或PPTX资料，请重新扫描资料目录'];
+  for (const project of projects) {
+    errors.push(...reviewImport(project).errors.map(error => `${project.relative_dir}：${error}`));
+  }
+  return errors;
+}

frontend/tests/import.spec.ts

@@ -0,0 +1,98 @@
+import { expect, test, type Page } from '@playwright/test';
+
+const identity = { student_no: '9000000001', name: '学生甲', topic: '机器人项目' };
+const mixed = () => ({ relative_dir: 'test/student', student_no: '', name: '', topic: '',
+  status: 'needs_confirmation', folder_identity: {}, detected_identity: {}, missing: [],
+  warnings: ['不同材料封面的学号不一致，请核对后填写'], files: [
+    { relative_path: 'test/student/最终报告.pdf', category: 'final_report', status: 'recognized',
+      sha256: 'a'.repeat(64), detected_identity: identity },
+    { relative_path: 'test/student/汇报PPT.pdf', category: 'presentation', status: 'needs_confirmation',
+      sha256: 'b'.repeat(64), detected_identity: { student_no: '9000000002', name: '学生乙', topic: '另一项目' } },
+  ] });
+
+async function setup(page: Page, project: any) {
+  const imports: any[] = [];
+  await page.route('**/api/**', async route => {
+    const request = route.request();
+    const path = new URL(request.url()).pathname.replace(/^\/api/, '');
+    let data: any = [];
+    if (path === '/courses') data = [{ id: 1, name: '课程甲' }];
+    if (path === '/courses/1/versions') data = [{ id: 1, published: true, version: 1, title: '初始版本' }];
+    if (path === '/import/scan') data = { projects: [project] };
+    if (path === '/import/confirm') { imports.push(request.postDataJSON()); data = { project_ids: [12] }; }
+    await route.fulfill({ json: data });
+  });
+  await page.goto('/?page=import');
+  await page.getByRole('button', { name: '扫描此目录', exact: true }).click();
+  await choose(page, '导入课程', '课程甲');
+  await choose(page, '导入课程版本', /初始版本/);
+  return imports;
+}
+
+async function choose(page: Page, label: string, option: string | RegExp) {
+  await page.keyboard.press('Escape');
+  await expect(page.locator('.ant-select-dropdown:visible')).toHaveCount(0);
+  const input = page.getByRole('combobox', { name: label, exact: true });
+  await input.focus(); await input.press('ArrowDown');
+  const listId = await input.getAttribute('aria-controls');
+  const dropdown = page.locator('.ant-select-dropdown').filter({ has: page.locator(`[id="${listId}"]`) });
+  await expect(dropdown).toBeVisible();
+  await dropdown.getByText(option, { exact: typeof option === 'string' }).click();
+}
+
+test('invalid student number explains why confirm is disabled and recovers after editing', async ({ page }) => {
+  const project = { ...mixed(), student_no: '1', name: '1', topic: '1' };
+  delete (project as any).folder_identity;
+  for (const file of project.files) delete (file as any).detected_identity;
+  await setup(page, project);
+  await expect(page.getByText(/学号必须为5–20位数字/)).toBeVisible();
+  await expect(page.getByRole('button', { name: '确认导入', exact: true })).toBeDisabled();
+  await page.getByRole('textbox', { name: '学号 test/student', exact: true }).fill('9000000001');
+  await expect(page.getByRole('button', { name: '确认导入', exact: true })).toBeEnabled();
+});
+
+test('ignoring a foreign PPT recalculates identity and submits the intended project', async ({ page }) => {
+  const imports = await setup(page, mixed());
+  await expect(page.getByText('学生乙（9000000002）', { exact: true })).toBeVisible();
+  await expect(page.getByText(/学号冲突：/)).toBeVisible();
+  await choose(page, '处理 test/student/汇报PPT.pdf', '忽略');
+  await expect(page.getByRole('textbox', { name: '学号 test/student', exact: true })).toHaveValue(identity.student_no);
+  await expect(page.getByRole('textbox', { name: '姓名 test/student', exact: true })).toHaveValue(identity.name);
+  await expect(page.getByText(/学号冲突：/)).toHaveCount(0);
+  await expect(page.getByRole('button', { name: '确认导入', exact: true })).toBeEnabled();
+  await page.getByRole('button', { name: '确认导入', exact: true }).click();
+  await expect.poll(() => imports.length).toBe(1);
+  expect(imports[0].projects[0].student_no).toBe(identity.student_no);
+  expect(imports[0].projects[0].files[1].status).toBe('ignored');
+});
+
+test('file selection preserves manual corrections until the user chooses cover values', async ({ page }) => {
+  await setup(page, mixed());
+  const name = page.getByRole('textbox', { name: '姓名 test/student', exact: true });
+  await name.fill('人工修正姓名');
+  await choose(page, '处理 test/student/汇报PPT.pdf', '忽略');
+  await expect(name).toHaveValue('人工修正姓名');
+  await page.getByRole('button', { name: '使用所选资料的封面信息', exact: true }).click();
+  await expect(name).toHaveValue(identity.name);
+});
+
+test('ignoring all files gives an explicit selected-material error', async ({ page }) => {
+  await setup(page, mixed());
+  await choose(page, '处理 test/student/汇报PPT.pdf', '忽略');
+  await choose(page, '处理 test/student/最终报告.pdf', '忽略');
+  await expect(page.getByText(/至少选择1份资料/)).toBeVisible();
+  await expect(page.getByRole('button', { name: '确认导入', exact: true })).toBeDisabled();
+});
+
+test('unknown and duplicate material types explain the block before sending a request', async ({ page }) => {
+  const project = mixed();
+  project.files[1].category = 'unknown';
+  project.files[1].detected_identity = identity;
+  await setup(page, project);
+  await expect(page.getByText(/请选择材料类型/)).toBeVisible();
+  await expect(page.getByRole('button', { name: '确认导入', exact: true })).toBeDisabled();
+  await choose(page, '材料类型 test/student/汇报PPT.pdf', '最终报告');
+  await expect(page.getByText(/最终报告选了2份/)).toBeVisible();
+  await choose(page, '处理 test/student/汇报PPT.pdf', '忽略');
+  await expect(page.getByRole('button', { name: '确认导入', exact: true })).toBeEnabled();
+});