X-Financial/server/tests/test_receipt_folder_service.py

from __future__ import annotations

import base64

from app.api.deps import CurrentUserContext
from app.core.config import get_settings
from app.schemas.ocr import OcrRecognizeBatchRead, OcrRecognizeDocumentRead, OcrRecognizeFieldRead
from app.services.document_preview import DocumentPreviewAssets
from app.services.receipt_folder import ReceiptFolderService


def test_receipt_folder_train_ticket_uses_invoice_date_and_enriches_fields(monkeypatch, tmp_path) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )
        service = ReceiptFolderService()
        receipt = service.save_receipt(
            filename="2月23_上海-武汉.pdf",
            content=b"%PDF-1.4 fake",
            media_type="application/pdf",
            current_user=current_user,
            document=OcrRecognizeDocumentRead(
                filename="2月23_上海-武汉.pdf",
                media_type="application/pdf",
                text=(
                    "电子发票（铁路电子客票）\n"
                    "发票号码:26319166100006175398\n"
                    "电子客票号:E1234567890123\n"
                    "开票日期:2026-02-18\n"
                    "上海虹桥站\n"
                    "武汉站\n"
                    "G456\n"
                    "二等座\n"
                    "06车01B号\n"
                    "2026-02-20 08:30开\n"
                    "票价:￥354.00\n"
                    "1101011990****1234\n"
                    "张三"
                ),
                summary="铁路电子客票，上海虹桥至武汉，票价 354 元。",
                document_type="train_ticket",
                document_type_label="火车/高铁票",
                scene_code="travel",
                scene_label="差旅票据",
            ),
        )

        assert receipt.document_date == "2026-02-18"
        assert receipt.merchant_name == "中国铁路"
        assert receipt.amount == "354.00元"

        detail = service.get_receipt(receipt.id, current_user)
        fields = {field.label: field.value for field in detail.fields}
        assert fields["开票日期"] == "2026-02-18"
        assert fields["乘车人"] == "张三"
        assert fields["出发地点"] == "上海虹桥"
        assert fields["到达地点"] == "武汉"
        assert fields["车次"] == "G456"
        assert fields["电子客票号"] == "E1234567890123"
        assert fields["身份证号"] == "1101011990****1234"
        assert fields["席别"] == "二等座"
        assert fields["车厢"] == "06车"
        assert fields["座位号"] == "01B"
        assert fields["列车出发时间"] == "2026-02-20 08:30"
    finally:
        get_settings.cache_clear()


def test_receipt_folder_pdf_save_eagerly_renders_image_preview(monkeypatch, tmp_path) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )

        def fake_render_pdf_first_page(*, pdf_path, preview_path, timeout_seconds):
            preview_path.write_bytes(b"rendered-preview")
            return preview_path

        monkeypatch.setattr(DocumentPreviewAssets, "render_pdf_first_page", fake_render_pdf_first_page)

        service = ReceiptFolderService()
        receipt = service.save_receipt(
            filename="2月20_武汉-上海.pdf",
            content=b"%PDF-1.4 fake",
            media_type="application/pdf",
            current_user=current_user,
            document=OcrRecognizeDocumentRead(
                filename="2月20_武汉-上海.pdf",
                media_type="application/pdf",
                text="铁路电子客票 武汉 上海虹桥 354.00",
                summary="铁路电子客票，武汉至上海虹桥。",
            ),
        )

        receipt_dir = next(service.root.glob("pytest/*"))
        preview_path = receipt_dir / "preview.png"
        meta = service._read_meta(receipt_dir)

        assert receipt.preview_kind == "image"
        assert preview_path.read_bytes() == b"rendered-preview"
        assert meta["preview_file_name"] == "preview.png"
        assert meta["preview_media_type"] == "image/png"
        assert meta["preview_rendered_with"] == DocumentPreviewAssets.PDF_RENDERER_ID

        resolved_path, media_type, file_name = service.resolve_preview(receipt.id, current_user)
        assert resolved_path == preview_path
        assert media_type == "image/png"
        assert file_name == "preview.png"
    finally:
        get_settings.cache_clear()


def test_receipt_folder_persist_enriches_pdf_ocr_document_with_image_preview(monkeypatch, tmp_path) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )

        def fake_render_pdf_first_page(*, pdf_path, preview_path, timeout_seconds):
            preview_path.write_bytes(b"rendered-preview")
            return preview_path

        monkeypatch.setattr(DocumentPreviewAssets, "render_pdf_first_page", fake_render_pdf_first_page)

        service = ReceiptFolderService()
        result = service.persist_ocr_batch(
            files=[("2月23_上海-武汉.pdf", b"%PDF-1.4 fake", "application/pdf")],
            result=OcrRecognizeBatchRead(
                total_file_count=1,
                success_count=1,
                documents=[
                    OcrRecognizeDocumentRead(
                        filename="2月23_上海-武汉.pdf",
                        media_type="application/pdf",
                        text="铁路电子客票 上海虹桥 武汉 G456 354.00",
                        summary="铁路电子客票，上海虹桥至武汉。",
                        document_type="train_ticket",
                        document_type_label="火车/高铁票",
                        scene_code="travel",
                        scene_label="差旅票据",
                    ),
                ],
            ),
            current_user=current_user,
        )

        document = result.documents[0]
        assert document.receipt_id
        assert document.receipt_preview_url.endswith(f"/receipt-folder/{document.receipt_id}/preview")
        assert document.preview_kind == "image"
    finally:
        get_settings.cache_clear()


def test_receipt_folder_pdf_preview_regenerates_stale_cached_image(monkeypatch, tmp_path) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )
        stale_preview = b"stale-preview"
        preview_data_url = f"data:image/png;base64,{base64.b64encode(stale_preview).decode('ascii')}"
        service = ReceiptFolderService()
        receipt = service.save_receipt(
            filename="2月20_武汉-上海.pdf",
            content=b"%PDF-1.4 fake",
            media_type="application/pdf",
            current_user=current_user,
            document=OcrRecognizeDocumentRead(
                filename="2月20_武汉-上海.pdf",
                media_type="application/pdf",
                preview_kind="image",
                preview_data_url=preview_data_url,
            ),
        )

        receipt_dir = next(service.root.glob("pytest/*"))
        preview_path = receipt_dir / "preview.png"
        assert preview_path.read_bytes() == stale_preview
        stale_meta = service._read_meta(receipt_dir)
        stale_meta.pop("preview_rendered_with", None)
        service._write_meta(receipt_dir, stale_meta)

        def fake_render_pdf_first_page(*, pdf_path, preview_path, timeout_seconds):
            preview_path.write_bytes(b"refreshed-preview")
            return preview_path

        monkeypatch.setattr(DocumentPreviewAssets, "render_pdf_first_page", fake_render_pdf_first_page)

        resolved_path, media_type, file_name = service.resolve_preview(receipt.id, current_user)

        assert resolved_path == preview_path
        assert media_type == "image/png"
        assert file_name == "preview.png"
        assert preview_path.read_bytes() == b"refreshed-preview"
        meta = service._read_meta(receipt_dir)
        assert meta["preview_rendered_with"] == DocumentPreviewAssets.PDF_RENDERER_ID
    finally:
        get_settings.cache_clear()


def test_receipt_folder_pdf_preview_falls_back_to_source_when_render_fonts_missing(
    monkeypatch,
    tmp_path,
) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )
        stale_preview = b"broken-preview"
        preview_data_url = f"data:image/png;base64,{base64.b64encode(stale_preview).decode('ascii')}"
        service = ReceiptFolderService()
        receipt = service.save_receipt(
            filename="2月20_武汉-上海.pdf",
            content=b"%PDF-1.7 fake",
            media_type="application/pdf",
            current_user=current_user,
            document=OcrRecognizeDocumentRead(
                filename="2月20_武汉-上海.pdf",
                media_type="application/pdf",
                preview_kind="image",
                preview_data_url=preview_data_url,
            ),
        )

        receipt_dir = next(service.root.glob("pytest/*"))
        meta = service._read_meta(receipt_dir)
        meta["preview_rendered_with"] = "pdftoppm-png-r160-poppler-data"
        service._write_meta(receipt_dir, meta)

        def fake_render_pdf_first_page(*, pdf_path, preview_path, timeout_seconds):
            raise RuntimeError("Missing language pack for 'Adobe-GB1' mapping")

        monkeypatch.setattr(DocumentPreviewAssets, "render_pdf_first_page", fake_render_pdf_first_page)

        resolved_path, media_type, file_name = service.resolve_preview(receipt.id, current_user)

        assert resolved_path == receipt_dir / "2月20_武汉-上海.pdf"
        assert media_type == "application/pdf"
        assert file_name == "2月20_武汉-上海.pdf"
        refreshed_meta = service._read_meta(receipt_dir)
        assert refreshed_meta["preview_kind"] == "pdf"
        assert refreshed_meta["preview_file_name"] == "2月20_武汉-上海.pdf"
        assert refreshed_meta["preview_media_type"] == "application/pdf"
        assert refreshed_meta["preview_rendered_with"] == ""
    finally:
        get_settings.cache_clear()


def test_receipt_folder_train_ticket_extracts_passenger_from_id_line_and_purchase_name(
    monkeypatch,
    tmp_path,
) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )
        service = ReceiptFolderService()
        receipt = service.save_receipt(
            filename="2月20_武汉-上海.pdf",
            content=b"%PDF-1.4 fake",
            media_type="application/pdf",
            current_user=current_user,
            document=OcrRecognizeDocumentRead(
                filename="2月20_武汉-上海.pdf",
                media_type="application/pdf",
                text=(
                    "电子发票（铁路电子客票）\n"
                    "发票号码:26429165800002785705 湖北\n"
                    "开票日期:2026年05月18日\n"
                    "武汉站 G458 上海虹桥站\n"
                    "Wuhan Shanghaihongqiao\n"
                    "2026年02月20日 07:55开 06车01B号 二等座\n"
                    "票价:￥354.00\n"
                    "4201061987****1615 曹笑竹\n"
                    "电子客票号:6580061086021391007342026\n"
                    "购买方名称:曹笑竹 统一社会信用代码:\n"
                    "买票请到12306 发货请到95306\n"
                    "中国铁路祝您旅途愉快"
                ),
                summary="电子发票（铁路电子客票）；发票监；统一 制",
                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="merchant_name", label="商户", value="电子发票（铁路"),
                    OcrRecognizeFieldRead(key="amount", label="金额", value="354元"),
                    OcrRecognizeFieldRead(key="date", label="列车出发时间", value="2026-02-20 07:55"),
                    OcrRecognizeFieldRead(key="trip_no", label="车次", value="G458"),
                    OcrRecognizeFieldRead(key="route", label="行程", value="武汉-上海"),
                ],
            ),
        )

        assert receipt.merchant_name == "中国铁路"

        detail = service.get_receipt(receipt.id, current_user)
        fields = {field.label: field.value for field in detail.fields}
        assert fields["商户"] == "中国铁路"
        assert fields["乘车人"] == "曹笑竹"
        assert fields["出发地点"] == "武汉"
        assert fields["到达地点"] == "上海虹桥"
        assert fields["身份证号"] == "4201061987****1615"
        assert fields["电子客票号"] == "6580061086021391007342026"
        assert fields["开票日期"] == "2026-05-18"
        assert fields["列车出发时间"] == "2026-02-20 07:55"
        assert fields["车厢"] == "06车"
        assert fields["座位号"] == "01B"
    finally:
        get_settings.cache_clear()


def test_receipt_folder_train_ticket_repairs_invalid_generated_fields_from_ocr_text(
    monkeypatch,
    tmp_path,
) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )
        service = ReceiptFolderService()
        receipt = service.save_receipt(
            filename="2月21日_上海-深圳.png",
            content=b"fake image",
            media_type="image/png",
            current_user=current_user,
            document=OcrRecognizeDocumentRead(
                filename="2月21日_上海-深圳.png",
                media_type="image/png",
                text=(
                    "行程单示意\n"
                    "出票渠道：示例平台\n"
                    "非官方车票\n"
                    "不可报销\n"
                    "仅供演示\n"
                    "创建日期：2026年02月15日\n"
                    "订单号：DEMO202602210001\n"
                    "单据编号：DEMO-IT-000001\n"
                    "上海虹桥\n"
                    "G999\n"
                    "深圳北\n"
                    "站\n"
                    "站\n"
                    "Shanghaihongqiao\n"
                    "Shenzhenbei\n"
                    "2026年02月21日\n"
                    "08:30出发\n"
                    "全程约7小时30分\n"
                    "15:00到达\n"
                    "DEMO\n"
                    "乘客：示例旅客\n"
                    "车厢：05车\n"
                    "席别：二等座\n"
                    "-\n"
                    "扫码无效\n"
                    "证件号：310101199001010000\n"
                    "座位：08A\n"
                    "票价：￥438.00\n"
                    "仅为演示"
                ),
                summary="行程单示意；出票渠道：示例平台；非官方车票",
                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="amount", label="金额", value="438元"),
                    OcrRecognizeFieldRead(key="date", label="列车出发时间", value="2026-02-21 08:30"),
                    OcrRecognizeFieldRead(key="invoice_number", label="票据号码", value="DEMO202602210001"),
                    OcrRecognizeFieldRead(key="trip_no", label="车次", value="G999"),
                    OcrRecognizeFieldRead(key="route", label="行程", value="上海-深圳"),
                    OcrRecognizeFieldRead(key="departure_station", label="出发地点", value="二等座"),
                    OcrRecognizeFieldRead(key="arrival_station", label="到达地点", value="扫码无效"),
                    OcrRecognizeFieldRead(key="passenger_name", label="乘车人", value="席别二等座"),
                ],
            ),
        )

        detail = service.get_receipt(receipt.id, current_user)
        fields = {field.label: field.value for field in detail.fields}
        assert fields["出发地点"] == "上海虹桥"
        assert fields["到达地点"] == "深圳北"
        assert fields["乘车人"] == "示例旅客"
        assert fields["身份证号"] == "310101199001010000"
        assert fields["席别"] == "二等座"
        assert fields["车厢"] == "05车"
        assert fields["座位号"] == "08A"
        assert fields["票价"] == "438.00元"
    finally:
        get_settings.cache_clear()


def test_receipt_folder_delete_removes_duplicate_marker(monkeypatch, tmp_path) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )
        service = ReceiptFolderService()
        content = b"%PDF-1.4 same receipt"

        receipt = service.save_receipt(
            filename="same-receipt.pdf",
            content=content,
            media_type="application/pdf",
            current_user=current_user,
            document=OcrRecognizeDocumentRead(
                filename="same-receipt.pdf",
                media_type="application/pdf",
                text="same receipt amount 354",
                document_type="other",
                document_type_label="其他单据",
                scene_code="other",
                scene_label="其他票据",
            ),
        )
        receipt_dir = service.root / "pytest" / receipt.id

        assert receipt_dir.exists()
        duplicate = service.find_duplicate_receipt(
            filename="same-receipt.pdf",
            content=content,
            current_user=current_user,
        )
        assert duplicate is not None
        assert duplicate.id == receipt.id

        service.delete_receipt(receipt_id=receipt.id, current_user=current_user)

        assert not receipt_dir.exists()
        assert (
            service.find_duplicate_receipt(
                filename="same-receipt.pdf",
                content=content,
                current_user=current_user,
            )
            is None
        )
    finally:
        get_settings.cache_clear()


def test_receipt_folder_duplicate_uses_newer_ocr_when_existing_meta_is_weaker(monkeypatch, tmp_path) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )
        service = ReceiptFolderService()
        content = b"%PDF-1.7 same train ticket"
        stale_receipt = service.save_receipt(
            filename="2月20_武汉-上海.pdf",
            content=content,
            media_type="application/pdf",
            current_user=current_user,
            document=OcrRecognizeDocumentRead(
                filename="2月20_武汉-上海.pdf",
                media_type="application/pdf",
                document_type="other",
                document_type_label="其他单据",
                scene_code="other",
                scene_label="其他票据",
                warnings=["PDF 转图片失败：Missing language pack for Adobe-GB1"],
            ),
        )

        result = service.persist_ocr_batch(
            files=[("2月20_武汉-上海.pdf", content, "application/pdf")],
            result=OcrRecognizeBatchRead(
                total_file_count=1,
                success_count=1,
                documents=[
                    OcrRecognizeDocumentRead(
                        filename="2月20_武汉-上海.pdf",
                        media_type="application/pdf",
                        text="G458 Wuhan Shanghaihongqiao 2026 02 20 07:55 票价: 354.00 12306",
                        summary="Wuhan Shanghaihongqiao G458 354.00",
                        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="amount", label="金额", value="354元"),
                            OcrRecognizeFieldRead(key="trip_no", label="车次/航班", value="G458"),
                            OcrRecognizeFieldRead(key="route", label="行程", value="武汉-上海"),
                        ],
                    ),
                ],
            ),
            current_user=current_user,
        )

        document = result.documents[0]
        assert document.receipt_id == stale_receipt.id
        assert document.document_type == "train_ticket"
        assert document.document_type_label == "火车/高铁票"
        assert any(field.label == "金额" and field.value == "354元" for field in document.document_fields)
        assert any("重复上传" in warning for warning in document.warnings)

        repaired = service.get_receipt(stale_receipt.id, current_user)
        assert repaired.document_type == "train_ticket"
        assert repaired.document_type_label == "火车/高铁票"
        assert {field.label: field.value for field in repaired.fields}["金额"] == "354元"
    finally:
        get_settings.cache_clear()


def test_receipt_folder_recovers_train_ticket_detail_from_other_english_ocr(monkeypatch, tmp_path) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )
        service = ReceiptFolderService()
        receipt = service.save_receipt(
            filename="2月20_武汉-上海.pdf",
            content=b"%PDF-1.4 fake",
            media_type="application/pdf",
            current_user=current_user,
            document=OcrRecognizeDocumentRead(
                filename="2月20_武汉-上海.pdf",
                media_type="application/pdf",
                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"
                ),
                summary="Wuhan Shanghaihongqiao G458 354.00",
                document_type="other",
                document_type_label="其他单据",
                scene_code="other",
                scene_label="其他票据",
            ),
        )

        assert receipt.document_type == "train_ticket"
        assert receipt.document_type_label == "火车/高铁票"
        assert receipt.scene_code == "travel"
        assert receipt.amount == "354.00元"
        assert receipt.document_date == "2026-02-20"
        assert receipt.merchant_name == "中国铁路"

        detail = service.get_receipt(receipt.id, current_user)
        fields = {field.label: field.value for field in detail.fields}
        assert fields["行程"] == "武汉-上海"
        assert fields["车次"] == "G458"
        assert fields["列车出发时间"] == "2026-02-20 07:55"
        assert fields["票价"] == "354.00元"
        assert fields["身份证号"] == "4201061987****1615"
        assert fields["车厢"] == "06车"
        assert fields["座位号"] == "01B"
        assert "乘车人" not in fields
    finally:
        get_settings.cache_clear()


def test_receipt_folder_unlink_receipts_for_claim_marks_linked_receipts_unlinked(monkeypatch, tmp_path) -> None:
    monkeypatch.setenv("STORAGE_ROOT_DIR", str(tmp_path / "storage"))
    get_settings.cache_clear()
    try:
        current_user = CurrentUserContext(
            username="pytest",
            name="Py Test",
            role_codes=[],
            is_admin=False,
        )
        service = ReceiptFolderService()
        receipt = service.save_receipt(
            filename="linked-receipt.pdf",
            content=b"%PDF-1.4 linked",
            media_type="application/pdf",
            current_user=current_user,
            linked_claim_id="claim-1",
            linked_claim_no="RE-001",
            linked_item_id="item-1",
            document=OcrRecognizeDocumentRead(
                filename="linked-receipt.pdf",
                media_type="application/pdf",
                text="invoice number 123 amount 100",
                document_type="vat_invoice",
                document_type_label="invoice",
                scene_code="other",
                scene_label="receipt",
            ),
        )

        linked_detail = service.get_receipt(receipt.id, current_user)
        assert linked_detail.status == "linked"
        assert linked_detail.linked_claim_id == "claim-1"
        assert linked_detail.linked_claim_no == "RE-001"

        assert service.unlink_receipts_for_claim("claim-1") == 1

        unlinked_detail = service.get_receipt(receipt.id, current_user)
        assert unlinked_detail.status == "unlinked"
        assert unlinked_detail.linked_claim_id == ""
        assert unlinked_detail.linked_claim_no == ""
        assert unlinked_detail.linked_at is None
    finally:
        get_settings.cache_clear()