Refactor processing logic and enhance error handling

- Cleaned up code in processing.py by removing inline semicolons and improving readability.
- Updated upsert_file_relation calls to ensure consistent handling of file relations.
- Enhanced query_file_relations in db_schema.py to support filtering by file existence.
- Improved API error handling in index.ts with user-friendly messages for 401 and 403 errors.
- Added online/offline status tracking in Layout.vue.
- Implemented debounced search functionality across multiple views to optimize performance.
- Introduced loading skeletons in Dashboard.vue for better user experience during data fetching.
- Enhanced file preview cleanup logic in Images.vue, Orders.vue, and Tables.vue to prevent memory leaks.
- Updated global styles to include new loading and notification animations.
This commit is contained in:
2026-05-12 18:37:23 +08:00
parent 81bafaf557
commit e441ac82a8
20 changed files with 455 additions and 76 deletions
+7
View File
@@ -53,6 +53,7 @@ class MemoryListResponse(BaseModel):
total: int
page: int
page_size: int
stats: Optional[Dict] = None
def _get_db():
@@ -96,11 +97,17 @@ async def list_memory(
start = (page - 1) * page_size
page_items = results[start:start + page_size]
# Compute confidence stats from all results (not just current page)
high = sum(1 for r in results if r.get("confidence", 0) > 50)
medium = sum(1 for r in results if 10 <= r.get("confidence", 0) <= 50)
low = sum(1 for r in results if r.get("confidence", 0) < 10)
return MemoryListResponse(
items=[_row_to_item(r) for r in page_items],
total=total,
page=page,
page_size=page_size,
stats={"high": high, "medium": medium, "low": low, "total": total},
)
+16 -9
View File
@@ -265,7 +265,7 @@ async def ocr_batch(
for ext in ['.xlsx', '.xls']:
candidate = _output_dir / f"{out_stem}{ext}"
if candidate.exists():
upsert_file_relation(input_image=f.name, output_excel=candidate.name, status='ocr_done'); _add_result_file(candidate.name)
upsert_file_relation(input_image=f.name, output_excel=candidate.name, status='ocr_done')
_add_result_file(candidate.name)
break
tm.add_log(task.id, f"[OCR] 完成: {f.name}")
@@ -317,7 +317,8 @@ async def process_excel(
result_path = _result_dir / result_name
if result_path.exists():
tm.add_log(task.id, f"[跳过] {f.name} 已处理过 → {result_name}")
upsert_file_relation(output_excel=f.name, result_purchase=result_name, status='done'); _add_result_file(result_name)
upsert_file_relation(output_excel=f.name, result_purchase=result_name, status='done')
_add_result_file(result_name)
continue
tm.update_progress(task.id, int((i / total) * 100), f"正在处理: {f.name}")
@@ -326,7 +327,7 @@ async def process_excel(
svc.process_excel(str(f))
# Find result file
if result_path.exists():
upsert_file_relation(output_excel=f.name, result_purchase=result_name, status='done'); _add_result_file(result_name)
upsert_file_relation(output_excel=f.name, result_purchase=result_name, status='done')
_add_result_file(result_name)
tm.add_log(task.id, f"[Excel] 完成: {f.name}")
# Learn products into memory from purchase order result
@@ -430,7 +431,8 @@ async def full_pipeline(
for ext in ['.xlsx', '.xls']:
candidate = _output_dir / f"{out_stem}{ext}"
if candidate.exists():
upsert_file_relation(input_image=f.name, output_excel=candidate.name, status='ocr_done'); _add_result_file(candidate.name)
upsert_file_relation(input_image=f.name, output_excel=candidate.name, status='ocr_done')
_add_result_file(candidate.name)
break
tm.add_log(task.id, f"[OCR] 完成: {f.name}")
out_file = _output_dir / f"{out_stem}.xlsx"
@@ -456,7 +458,8 @@ async def full_pipeline(
result_path = _result_dir / result_name
if result_path.exists():
tm.add_log(task.id, f"[跳过] {f.name} 已处理过 → {result_name}")
upsert_file_relation(output_excel=f.name, result_purchase=result_name, status='done'); _add_result_file(result_name)
upsert_file_relation(output_excel=f.name, result_purchase=result_name, status='done')
_add_result_file(result_name)
tm.update_progress(task.id, pct, f"跳过: {f.name}")
continue
@@ -464,7 +467,8 @@ async def full_pipeline(
try:
order_svc.process_excel(str(f))
if result_path.exists():
upsert_file_relation(output_excel=f.name, result_purchase=result_name, status='done'); _add_result_file(result_name)
upsert_file_relation(output_excel=f.name, result_purchase=result_name, status='done')
_add_result_file(result_name)
tm.add_log(task.id, f"[Excel] 完成: {f.name}")
if result_path.exists():
_learn_products_from_excel(result_path, tm, task.id, source='ocr')
@@ -515,7 +519,8 @@ async def ocr_single(
for ext in ['.xlsx', '.xls']:
candidate = _output_dir / f"{stem}{ext}"
if candidate.exists():
upsert_file_relation(input_image=body.filename, output_excel=candidate.name, status='ocr_done'); _add_result_file(candidate.name)
upsert_file_relation(input_image=body.filename, output_excel=candidate.name, status='ocr_done')
_add_result_file(candidate.name)
break
tm.add_log(task.id, f"[OCR] 完成: {body.filename}")
result_files = list(getattr(_tlocal, 'result_files', []))
@@ -598,13 +603,15 @@ async def pipeline_single(
if out_xlsx.exists() or out_xls.exists():
out_name = out_xlsx.name if out_xlsx.exists() else out_xls.name
tm.add_log(task.id, f"[跳过] 已OCR过 → {out_name}")
upsert_file_relation(input_image=body.filename, output_excel=out_name, status='ocr_done'); _add_result_file(out_name)
upsert_file_relation(input_image=body.filename, output_excel=out_name, status='ocr_done')
_add_result_file(out_name)
else:
ocr_svc.process_image(str(file_path))
for ext in ['.xlsx', '.xls']:
candidate = _output_dir / f"{stem}{ext}"
if candidate.exists():
upsert_file_relation(input_image=body.filename, output_excel=candidate.name, status='ocr_done'); _add_result_file(candidate.name)
upsert_file_relation(input_image=body.filename, output_excel=candidate.name, status='ocr_done')
_add_result_file(candidate.name)
break
tm.add_log(task.id, f"[OCR] 完成")
+24 -12
View File
@@ -476,16 +476,21 @@ def upsert_file_relation(input_image: str = None, output_excel: str = None,
def query_file_relations(view: str = None, status: str = None,
page: int = 1, page_size: int = 50,
sort_by: str = None, sort_order: str = "desc") -> tuple[list[dict], int]:
sort_by: str = None, sort_order: str = "desc",
exists_only: bool = True) -> tuple[list[dict], int]:
"""Query file relations with optional view filter and pagination.
view='orders': only rows with result_purchase, sorted by result_purchase
view='tables': only rows with output_excel, sorted by output_excel
view='images': only rows with input_image, sorted by input_image
view=None: all rows
exists_only=True: for a given view, only return rows where the primary file
still exists on disk (input_image for images,
output_excel for tables, result_purchase for orders)
Returns (items, total).
"""
project_root = Path(__file__).resolve().parent.parent.parent.parent
conn = sqlite3.connect(_db_path)
conn.row_factory = sqlite3.Row
try:
@@ -516,22 +521,13 @@ def query_file_relations(view: str = None, status: str = None,
sort_col = order_by.split()[0] if order_by else 'id'
sort_dir = 'DESC' if sort_order.lower() == 'desc' else 'ASC'
# Count
row = conn.execute(
f"SELECT COUNT(*) as cnt FROM file_relations{where}", params
).fetchone()
total = row[0] if row else 0
# Page
offset = (page - 1) * page_size
params.extend([page_size, offset])
# Fetch all matching rows (existence filter happens in Python)
rows = conn.execute(
f"SELECT * FROM file_relations{where} ORDER BY {sort_col} {sort_dir} LIMIT ? OFFSET ?",
f"SELECT * FROM file_relations{where} ORDER BY {sort_col} {sort_dir}",
params,
).fetchall()
items = []
project_root = Path(__file__).resolve().parent.parent.parent.parent
for r in rows:
d = dict(r)
# Check file existence
@@ -547,8 +543,24 @@ def query_file_relations(view: str = None, status: str = None,
d['result_exists'] = (project_root / 'data' / 'result' / d['result_purchase']).exists()
else:
d['result_exists'] = False
# Filter: when exists_only is True, only keep rows whose primary file exists
if exists_only:
if view == 'images' and not d['input_exists']:
continue
if view == 'tables' and not d['output_exists']:
continue
if view == 'orders' and not d['result_exists']:
continue
items.append(d)
total = len(items)
# Page (Python-side after existence filtering)
start = (page - 1) * page_size
items = items[start:start + page_size]
return items, total
finally:
conn.close()