From 0d6dc4b3428fc817410aca58926304174c8c97ed Mon Sep 17 00:00:00 2001
From: aerospaceboy <790286734@qq.com>
Date: Wed, 14 Oct 2026 14:48:16 +0800
Subject: [PATCH 01/17] fix: expose per-file cover identities in import scans
---
backend/tests/test_import_and_model_errors.py | 22 +++++++++++++++++++
backend/wisegrade/storage.py | 9 ++++++--
2 files changed, 29 insertions(+), 2 deletions(-)
diff --git a/backend/tests/test_import_and_model_errors.py b/backend/tests/test_import_and_model_errors.py
index d0b1e1a..1e63df6 100644
--- a/backend/tests/test_import_and_model_errors.py
+++ b/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):
diff --git a/backend/wisegrade/storage.py b/backend/wisegrade/storage.py
index 2fc9611..ed92641 100644
--- a/backend/wisegrade/storage.py
+++ b/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)
From 1776b1b50cc0e5cc01f8d65142c5e03b65bada2b Mon Sep 17 00:00:00 2001
From: aerospaceboy <790286734@qq.com>
Date: Wed, 14 Oct 2026 14:57:02 +0800
Subject: [PATCH 02/17] fix: explain import blockers and recompute selected
identities
---
frontend/src/App.tsx | 79 ++++++++++++++++++++++++----
frontend/src/importReview.ts | 66 +++++++++++++++++++++++
frontend/tests/import.spec.ts | 98 +++++++++++++++++++++++++++++++++++
3 files changed, 233 insertions(+), 10 deletions(-)
create mode 100644 frontend/src/importReview.ts
create mode 100644 frontend/tests/import.spec.ts
diff --git a/frontend/src/App.tsx b/frontend/src/App.tsx
index 0bc2a96..aa99e50 100644
--- a/frontend/src/App.tsx
+++ b/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 editFile = (projectIndex: number, fileIndex: number, key: string, value: any) => { const next = structuredClone(scanData); next.projects[projectIndex].files[fileIndex][key] = value; setScanData(next); };
+ const errors = importErrors(scanData?.projects, versionId);
+ 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,
- name: p.name, topic: p.topic, direction: p.direction || '',
+ const projects = scanData.projects.map((p: any) => ({ relative_dir: p.relative_dir, student_no: p.student_no.trim(),
+ 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 <>挂载目录扫描与导入确认浏览 /data/inbox 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。{path}{dirs.map(dir => )}
+ const projectIndex = (project: any) => scanData.projects.findIndex((item: any) => item.relative_dir === project.relative_dir);
+ const identityInput = (project: any, key: string, label: string) => editProject(projectIndex(project), key, event.target.value)} />;
+ return <>挂载目录扫描与导入确认
+ 浏览 /data/inbox 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”。
+ {path}
+
+ {dirs.map(dir => )}
{imported && imported.projectIds.length > 0 &&
} />}
- {scanData && <>{!scanData.projects.length && } editProject(scanData.projects.findIndex((x: any) => x.relative_dir === p.relative_dir), 'student_no', e.target.value)} /> }, { title: '姓名', render: (_, p, index) => editProject(scanData.projects.findIndex((x: any) => x.relative_dir === p.relative_dir), 'name', e.target.value)} /> }, { title: '选题', render: (_, p, index) => editProject(scanData.projects.findIndex((x: any) => x.relative_dir === p.relative_dir), 'topic', e.target.value)} /> }, { title: '选题方向', render: (_, p) => editProject(scanData.projects.findIndex((x: any) => x.relative_dir === p.relative_dir), 'direction', e.target.value)} /> }, { title: '待处理', render: (_, p) => {p.status !== 'recognized' && 身份信息需确认}{p.missing.map((c: string) => 缺{categories[c]})}{p.warnings?.map((w: string) => {w})} }]}
- expandable={{ defaultExpandAllRows: true, expandedRowRender: (p: any) => { const pi = scanData.projects.findIndex((item: any) => item.relative_dir === p.relative_dir); return size="small" rowKey="relative_path" pagination={false} dataSource={p.files} columns={[{ title: '文件', dataIndex: 'relative_path' }, { title: '类型', render: (_, f, fi) =>