feat(server): 票据文件夹资产缓存与文档预览统一生成

- 新增 document_preview 模块,DocumentPreviewAssets 统一处理 data URL 解码、pdftoppm PNG 预览生成(poppler-data 编码)、renderer_id 标识
- receipt_folder 服务复用预览生成,缓存票据资产并提供清理;删除票据时保留已关联报销单的附件副本
- document_intelligence 新增票据预览/资产缓存接入与字段提取增强;ocr 抽取复用预览工具,附件分析/文档/操作/展示四个子模块同步适配
- receipt_folder 端点补充资产缓存头,补/扩 document_intelligence、ocr_endpoints、ocr_service、receipt_folder_service、reimbursement_endpoints 测试,新增 attachment_analysis 回归测试
This commit is contained in:
caoxiaozhu
2026-06-23 09:42:00 +08:00
parent bc743adef3
commit 84a8998e59
15 changed files with 1076 additions and 79 deletions

View File

@@ -84,6 +84,35 @@ def test_document_intelligence_prefers_train_ticket_for_railway_e_ticket_invoice
assert any(field.label == "金额" and field.value == "354元" for field in insight.fields)
def test_document_intelligence_recovers_train_ticket_from_english_station_ocr_text() -> None:
insight = build_document_insight(
filename="2月20_武汉-上海.pdf",
summary=":26429165800002785705:2026 05 18Wuhan Shanghaihongqiao G458",
text=(
":26429165800002785705\n"
":2026 05 18\n"
"G458\n"
"Wuhan\n"
"Shanghaihongqiao\n"
"2026 02 20 07:55\n"
"06 01B\n"
": 354.00\n"
"4201061987****1615\n"
":6580061086021391007342026\n"
"12306 95306"
),
)
assert insight.document_type == "train_ticket"
assert insight.document_type_label == "火车/高铁票"
assert insight.scene_code == "travel"
fields = {field.label: field.value for field in insight.fields}
assert fields["金额"] == "354元"
assert fields["列车出发时间"] == "2026-02-20 07:55"
assert fields["车次/航班"] == "G458"
assert fields["行程"] == "武汉-上海"
def test_document_intelligence_labels_train_ticket_date_as_train_departure_time() -> None:
insight = build_document_insight(
filename="铁路电子客票.pdf",