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
2026-06-23 09:42:00 +08:00
parent bc743adef3
commit 84a8998e59
15 changed files with 1076 additions and 79 deletions
--- a/server/tests/test_ocr_endpoints.py
+++ b/server/tests/test_ocr_endpoints.py
@@ -176,3 +176,73 @@ def test_ocr_recognize_endpoint_returns_structured_payload(monkeypatch, tmp_path
        assert deleted_response.status_code == 404
    finally:
        get_settings.cache_clear()
+
+
+def test_ocr_recognize_endpoint_returns_receipt_enriched_train_fields(monkeypatch, tmp_path) -> None:
+    def fake_recognize(
+        self,
+        files: list[tuple[str, bytes, str | None]],
+    ) -> OcrRecognizeBatchRead:
+        return OcrRecognizeBatchRead(
+            engine="paddleocr_mobile",
+            model="PP-OCRv5_mobile",
+            total_file_count=1,
+            success_count=1,
+            documents=[
+                OcrRecognizeDocumentRead(
+                    filename="2月20_武汉-上海.png",
+                    media_type="image/png",
+                    text=(
+                        ":26429165800002785705\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"
+                    ),
+                    summary="Wuhan Shanghaihongqiao G458 354.00",
+                    avg_score=0.92,
+                    line_count=0,
+                    page_count=1,
+                    document_type="train_ticket",
+                    document_type_label="火车/高铁票",
+                    scene_code="travel",
+                    scene_label="差旅票据",
+                    document_fields=[
+                        OcrRecognizeFieldRead(key="date", label="列车出发时间", value="2026-02-20 07:55"),
+                        OcrRecognizeFieldRead(key="trip_no", label="车次/航班", value="G458"),
+                        OcrRecognizeFieldRead(key="route", label="行程", value="武汉-上海"),
+                        OcrRecognizeFieldRead(key="amount", label="金额", value="354元"),
+                    ],
+                )
+            ],
+        )
+
+    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
+    get_settings.cache_clear()
+    monkeypatch.setattr(OcrService, "recognize_files", fake_recognize)
+    try:
+        client = build_client()
+        response = client.post(
+            "/api/v1/ocr/recognize",
+            headers={"x-auth-username": "pytest", "x-auth-name": "Py Test"},
+            files=[("files", ("2月20_武汉-上海.png", b"fake-image", "image/png"))],
+        )
+    finally:
+        get_settings.cache_clear()
+
+    assert response.status_code == 200
+    document = response.json()["documents"][0]
+    fields = {
+        item["label"]: item["value"]
+        for item in document["document_fields"]
+    }
+    assert document["receipt_id"]
+    assert fields["身份证号"] == "4201061987****1615"
+    assert fields["车厢"] == "06车"
+    assert fields["座位号"] == "01B"
+    assert fields["票价"] == "354.00元"