feat: 完善模板对比持久化与附件版本处理
This commit is contained in:
wren
@@ -11,12 +11,17 @@ from datetime import date as date_type, datetime
|
||||
import hashlib
|
||||
import mimetypes
|
||||
import re
|
||||
import tempfile
|
||||
import time
|
||||
import unicodedata
|
||||
import uuid
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
from sqlalchemy import text
|
||||
import fitz
|
||||
from leaudit.converters import doc2pdf
|
||||
from sqlalchemy import bindparam, text
|
||||
from docx import Document as DocxDocument
|
||||
|
||||
from fastapi_common.fastapi_common_sqlalchemy.database import GetAsyncSession
|
||||
from fastapi_common.fastapi_common_web.domain.responses import StatusCodeEnum
|
||||
@@ -49,6 +54,7 @@ from fastapi_modules.fastapi_leaudit.domian.vo.reviewPointVo import (
|
||||
ReviewPointsAggregateVO,
|
||||
)
|
||||
from fastapi_modules.fastapi_leaudit.models import LeauditDocument, LeauditDocumentFile
|
||||
from fastapi_modules.fastapi_leaudit.leaudit_bridge.fileSourceResolver import FileSourceResolver
|
||||
from fastapi_modules.fastapi_leaudit.services import IAuditService, IDocumentService, IOssService
|
||||
from fastapi_modules.fastapi_leaudit.services.impl.auditServiceImpl import AuditServiceImpl
|
||||
from fastapi_modules.fastapi_leaudit.services.impl.ossServiceImpl import OssServiceImpl
|
||||
@@ -313,7 +319,12 @@ class DocumentServiceImpl(IDocumentService):
|
||||
documentColumns = await self._loadDocumentColumns(Session)
|
||||
|
||||
currentUser = await self._getCurrentUserContext(CurrentUserId)
|
||||
filters = ["d.is_latest_version = true", "d.deleted_at IS NULL", "f.is_active = true", "f.file_role = 'primary'"]
|
||||
filters = [
|
||||
"d.is_latest_version = true",
|
||||
"d.deleted_at IS NULL",
|
||||
"f.is_active = true",
|
||||
"f.file_role = 'primary'",
|
||||
]
|
||||
params: dict[str, object] = {"limit": page_size, "offset": offset}
|
||||
filters.extend(
|
||||
self._buildDocumentScopeFilters(
|
||||
@@ -516,6 +527,7 @@ class DocumentServiceImpl(IDocumentService):
|
||||
f.file_name,
|
||||
f.file_ext,
|
||||
f.file_size,
|
||||
f.oss_url,
|
||||
ar.status AS run_status,
|
||||
ar.result_status,
|
||||
ar.total_score,
|
||||
@@ -555,6 +567,7 @@ class DocumentServiceImpl(IDocumentService):
|
||||
fileName=row["file_name"],
|
||||
fileExt=row["file_ext"],
|
||||
fileSize=int(row["file_size"]) if row["file_size"] is not None else None,
|
||||
ossUrl=row["oss_url"],
|
||||
processingStatus=row["processing_status"],
|
||||
runStatus=row["run_status"],
|
||||
resultStatus=row["result_status"],
|
||||
@@ -1049,11 +1062,687 @@ class DocumentServiceImpl(IDocumentService):
|
||||
|
||||
await Session.commit()
|
||||
|
||||
async def _load_active_primary_file_row(
|
||||
self,
|
||||
Session,
|
||||
*,
|
||||
DocumentId: int,
|
||||
) -> dict[str, Any]:
|
||||
row = (
|
||||
await Session.execute(
|
||||
text(
|
||||
"""
|
||||
SELECT
|
||||
id,
|
||||
file_name,
|
||||
file_ext,
|
||||
mime_type,
|
||||
file_role,
|
||||
oss_url,
|
||||
local_path
|
||||
FROM leaudit_document_files
|
||||
WHERE document_id = :document_id
|
||||
AND deleted_at IS NULL
|
||||
AND is_active = true
|
||||
AND file_role = 'primary'
|
||||
ORDER BY id DESC
|
||||
LIMIT 1
|
||||
"""
|
||||
),
|
||||
{"document_id": DocumentId},
|
||||
)
|
||||
).mappings().first()
|
||||
if not row:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "当前文档缺少主文件")
|
||||
return dict(row)
|
||||
|
||||
def _normalize_document_source_kind(self, file_name: str, file_ext: str | None, mime_type: str | None) -> str:
|
||||
suffix = (f".{str(file_ext).lstrip('.')}" if file_ext else Path(file_name).suffix).lower()
|
||||
normalizedMime = (mime_type or "").lower()
|
||||
if suffix == ".pdf" or normalizedMime == "application/pdf":
|
||||
return "pdf"
|
||||
if suffix == ".docx" or normalizedMime == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
|
||||
return "docx"
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "当前仅支持 PDF 或 DOCX 主文档追加附件")
|
||||
|
||||
def _normalize_attachment_source_kind(self, file_name: str, file_ext: str | None, mime_type: str | None) -> str:
|
||||
suffix = (f".{str(file_ext).lstrip('.')}" if file_ext else Path(file_name).suffix).lower()
|
||||
normalizedMime = (mime_type or "").lower()
|
||||
if suffix == ".pdf" or normalizedMime == "application/pdf":
|
||||
return "pdf"
|
||||
if suffix == ".docx" or normalizedMime == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
|
||||
return "docx"
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, f"附件 {file_name} 仅支持 PDF 或 DOCX 格式")
|
||||
|
||||
def _validate_attachment_matrix(
|
||||
self,
|
||||
*,
|
||||
MainSourceKind: str,
|
||||
Files: list[tuple[str, bytes, str | None]],
|
||||
) -> None:
|
||||
for fileName, _, contentType in Files:
|
||||
attachmentKind = self._normalize_attachment_source_kind(fileName, Path(fileName).suffix.lstrip(".").lower() or None, contentType)
|
||||
if MainSourceKind == "docx" and attachmentKind != "docx":
|
||||
raise LeauditException(
|
||||
StatusCodeEnum.HTTP_400_BAD_REQUEST,
|
||||
"源文档为 DOCX 时，仅允许追加 DOCX 附件，且合并结果仍为 DOCX",
|
||||
)
|
||||
|
||||
def _merge_docx_paths_for_merge(
|
||||
self,
|
||||
*,
|
||||
DocxPaths: list[str],
|
||||
TempPaths: list[str],
|
||||
) -> str:
|
||||
if not DocxPaths:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "缺少可合并的 DOCX 文件")
|
||||
|
||||
mergedTemp = tempfile.NamedTemporaryFile(suffix=".docx", delete=False)
|
||||
mergedTemp.close()
|
||||
TempPaths.append(mergedTemp.name)
|
||||
|
||||
baseDoc = DocxDocument(DocxPaths[0])
|
||||
for attachmentPath in DocxPaths[1:]:
|
||||
attachmentDoc = DocxDocument(attachmentPath)
|
||||
if baseDoc.paragraphs:
|
||||
baseDoc.add_page_break()
|
||||
for element in attachmentDoc.element.body:
|
||||
baseDoc.element.body.append(deepcopy(element))
|
||||
baseDoc.save(mergedTemp.name)
|
||||
return mergedTemp.name
|
||||
|
||||
async def _cloneActiveFilesToNewDocument(
|
||||
self,
|
||||
Session,
|
||||
*,
|
||||
SourceDocumentId: int,
|
||||
TargetDocumentId: int,
|
||||
CreatedBy: int | None,
|
||||
IncludeAttachments: bool = True,
|
||||
) -> None:
|
||||
"""复制当前文档的主文件与现有附件到新版本文档。"""
|
||||
fileRoles = ["primary", "attachment"] if IncludeAttachments else ["primary"]
|
||||
sourceFiles = (
|
||||
await Session.execute(
|
||||
text(
|
||||
"""
|
||||
SELECT
|
||||
id,
|
||||
file_role,
|
||||
file_name,
|
||||
file_ext,
|
||||
mime_type,
|
||||
file_size,
|
||||
sha256,
|
||||
local_path,
|
||||
oss_url,
|
||||
storage_provider
|
||||
FROM leaudit_document_files
|
||||
WHERE document_id = :document_id
|
||||
AND deleted_at IS NULL
|
||||
AND is_active = true
|
||||
AND file_role = ANY(:file_roles)
|
||||
ORDER BY
|
||||
CASE WHEN file_role = 'primary' THEN 0 ELSE 1 END,
|
||||
id ASC
|
||||
"""
|
||||
).bindparams(bindparam("file_roles", expanding=False)),
|
||||
{"document_id": SourceDocumentId, "file_roles": fileRoles},
|
||||
)
|
||||
).mappings().all()
|
||||
if not sourceFiles:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "源文档缺少可复制的有效文件")
|
||||
|
||||
for row in sourceFiles:
|
||||
clonedFile = LeauditDocumentFile(
|
||||
documentId=TargetDocumentId,
|
||||
fileRole=str(row["file_role"] or "attachment"),
|
||||
fileName=str(row["file_name"] or ""),
|
||||
fileExt=row["file_ext"],
|
||||
mimeType=row["mime_type"],
|
||||
fileSize=int(row["file_size"]) if row["file_size"] is not None else None,
|
||||
sha256=row["sha256"],
|
||||
localPath=row["local_path"],
|
||||
ossUrl=row["oss_url"],
|
||||
storageProvider=row["storage_provider"],
|
||||
isActive=True,
|
||||
createdBy=CreatedBy,
|
||||
)
|
||||
Session.add(clonedFile)
|
||||
|
||||
await Session.flush()
|
||||
|
||||
async def _buildMergedPdfBytesForDocument(
|
||||
self,
|
||||
Session,
|
||||
*,
|
||||
DocumentId: int,
|
||||
) -> tuple[bytes, str]:
|
||||
"""读取当前主文件与附件，生成新的主 PDF 内容。"""
|
||||
primaryFile = (
|
||||
await Session.execute(
|
||||
text(
|
||||
"""
|
||||
SELECT id
|
||||
FROM leaudit_document_files
|
||||
WHERE document_id = :document_id
|
||||
AND deleted_at IS NULL
|
||||
AND is_active = true
|
||||
AND file_role = 'primary'
|
||||
ORDER BY id DESC
|
||||
LIMIT 1
|
||||
"""
|
||||
),
|
||||
{"document_id": DocumentId},
|
||||
)
|
||||
).scalar_one_or_none()
|
||||
if primaryFile is None:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "当前文档缺少主文件，无法生成合并文件")
|
||||
|
||||
attachmentRows = (
|
||||
await Session.execute(
|
||||
text(
|
||||
"""
|
||||
SELECT id
|
||||
FROM leaudit_document_files
|
||||
WHERE document_id = :document_id
|
||||
AND deleted_at IS NULL
|
||||
AND is_active = true
|
||||
AND file_role = 'attachment'
|
||||
ORDER BY id ASC
|
||||
"""
|
||||
),
|
||||
{"document_id": DocumentId},
|
||||
)
|
||||
).scalars().all()
|
||||
if not attachmentRows:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "当前文档没有附件，无法生成合并文件")
|
||||
|
||||
resolver = FileSourceResolver()
|
||||
primaryModel = await Session.get(LeauditDocumentFile, int(primaryFile))
|
||||
if primaryModel is None:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "主文件记录不存在，无法生成合并文件")
|
||||
primaryPayload = await resolver.ResolvePayload(primaryModel)
|
||||
|
||||
attachmentModels: list[LeauditDocumentFile] = []
|
||||
for attachmentId in attachmentRows:
|
||||
attachmentModel = await Session.get(LeauditDocumentFile, int(attachmentId))
|
||||
if attachmentModel is not None:
|
||||
attachmentModels.append(attachmentModel)
|
||||
attachmentPayloads = await resolver.ResolvePayloads(attachmentModels)
|
||||
|
||||
tempPaths: list[str] = []
|
||||
try:
|
||||
mainLocalPath = self._write_temp_file_for_merge(
|
||||
FileName=primaryPayload.fileName,
|
||||
Content=primaryPayload.fileContent,
|
||||
TempPaths=tempPaths,
|
||||
)
|
||||
mainPdfPath = self._convert_source_to_pdf(
|
||||
SourcePath=mainLocalPath,
|
||||
TempPaths=tempPaths,
|
||||
)
|
||||
pdfPaths = [mainPdfPath]
|
||||
|
||||
for attachmentPayload in attachmentPayloads:
|
||||
attachmentLocalPath = self._write_temp_file_for_merge(
|
||||
FileName=attachmentPayload.fileName,
|
||||
Content=attachmentPayload.fileContent,
|
||||
TempPaths=tempPaths,
|
||||
)
|
||||
attachmentPdfPath = self._convert_source_to_pdf(
|
||||
SourcePath=attachmentLocalPath,
|
||||
TempPaths=tempPaths,
|
||||
)
|
||||
pdfPaths.append(attachmentPdfPath)
|
||||
|
||||
mergedPdfPath = self._merge_pdf_paths_for_merge(
|
||||
PdfPaths=pdfPaths,
|
||||
TempPaths=tempPaths,
|
||||
)
|
||||
mergedBytes = Path(mergedPdfPath).read_bytes()
|
||||
mergedName = f"{Path(primaryPayload.fileName).stem}.pdf"
|
||||
return mergedBytes, mergedName
|
||||
except LeauditException:
|
||||
raise
|
||||
except Exception as error:
|
||||
raise LeauditException(
|
||||
StatusCodeEnum.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
f"生成合并PDF失败: {error}",
|
||||
) from error
|
||||
finally:
|
||||
for tempPath in reversed(tempPaths):
|
||||
try:
|
||||
pathObj = Path(tempPath)
|
||||
if pathObj.is_file():
|
||||
pathObj.unlink(missing_ok=True)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
async def _buildMergedDocxBytesForDocument(
|
||||
self,
|
||||
Session,
|
||||
*,
|
||||
DocumentId: int,
|
||||
) -> tuple[bytes, str]:
|
||||
"""读取当前主文件与附件，生成新的主 DOCX 内容。"""
|
||||
primaryFile = await self._load_active_primary_file_row(Session, DocumentId=DocumentId)
|
||||
if self._normalize_document_source_kind(
|
||||
str(primaryFile["file_name"] or ""),
|
||||
primaryFile.get("file_ext"),
|
||||
primaryFile.get("mime_type"),
|
||||
) != "docx":
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "仅 DOCX 主文档支持生成 DOCX 合并结果")
|
||||
|
||||
attachmentRows = (
|
||||
await Session.execute(
|
||||
text(
|
||||
"""
|
||||
SELECT id
|
||||
FROM leaudit_document_files
|
||||
WHERE document_id = :document_id
|
||||
AND deleted_at IS NULL
|
||||
AND is_active = true
|
||||
AND file_role = 'attachment'
|
||||
ORDER BY id ASC
|
||||
"""
|
||||
),
|
||||
{"document_id": DocumentId},
|
||||
)
|
||||
).scalars().all()
|
||||
if not attachmentRows:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "当前文档没有附件，无法生成合并文件")
|
||||
|
||||
resolver = FileSourceResolver()
|
||||
primaryModel = await Session.get(LeauditDocumentFile, int(primaryFile["id"]))
|
||||
if primaryModel is None:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "主文件记录不存在，无法生成合并文件")
|
||||
primaryPayload = await resolver.ResolvePayload(primaryModel)
|
||||
|
||||
attachmentModels: list[LeauditDocumentFile] = []
|
||||
for attachmentId in attachmentRows:
|
||||
attachmentModel = await Session.get(LeauditDocumentFile, int(attachmentId))
|
||||
if attachmentModel is not None:
|
||||
attachmentModels.append(attachmentModel)
|
||||
attachmentPayloads = await resolver.ResolvePayloads(attachmentModels)
|
||||
|
||||
tempPaths: list[str] = []
|
||||
try:
|
||||
docxPaths = [
|
||||
self._write_temp_file_for_merge(
|
||||
FileName=primaryPayload.fileName,
|
||||
Content=primaryPayload.fileContent,
|
||||
TempPaths=tempPaths,
|
||||
)
|
||||
]
|
||||
for attachmentPayload in attachmentPayloads:
|
||||
attachmentKind = self._normalize_attachment_source_kind(
|
||||
attachmentPayload.fileName,
|
||||
Path(attachmentPayload.fileName).suffix.lstrip(".").lower() or None,
|
||||
None,
|
||||
)
|
||||
if attachmentKind != "docx":
|
||||
raise LeauditException(
|
||||
StatusCodeEnum.HTTP_400_BAD_REQUEST,
|
||||
f"DOCX 主文档仅允许追加 DOCX 附件，当前附件 {attachmentPayload.fileName} 不符合要求",
|
||||
)
|
||||
docxPaths.append(
|
||||
self._write_temp_file_for_merge(
|
||||
FileName=attachmentPayload.fileName,
|
||||
Content=attachmentPayload.fileContent,
|
||||
TempPaths=tempPaths,
|
||||
)
|
||||
)
|
||||
|
||||
mergedDocxPath = self._merge_docx_paths_for_merge(
|
||||
DocxPaths=docxPaths,
|
||||
TempPaths=tempPaths,
|
||||
)
|
||||
mergedBytes = Path(mergedDocxPath).read_bytes()
|
||||
mergedName = f"{Path(primaryPayload.fileName).stem}.docx"
|
||||
return mergedBytes, mergedName
|
||||
finally:
|
||||
for tempPath in reversed(tempPaths):
|
||||
try:
|
||||
pathObj = Path(tempPath)
|
||||
if pathObj.is_file():
|
||||
pathObj.unlink(missing_ok=True)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _write_temp_file_for_merge(
|
||||
self,
|
||||
*,
|
||||
FileName: str,
|
||||
Content: bytes,
|
||||
TempPaths: list[str],
|
||||
) -> str:
|
||||
"""为持久化合并流程写入临时文件。"""
|
||||
suffix = Path(FileName).suffix or ".bin"
|
||||
with tempfile.NamedTemporaryFile(suffix=suffix, delete=False) as tempFile:
|
||||
tempFile.write(Content)
|
||||
tempPath = tempFile.name
|
||||
TempPaths.append(tempPath)
|
||||
return tempPath
|
||||
|
||||
def _convert_source_to_pdf(
|
||||
self,
|
||||
*,
|
||||
SourcePath: str,
|
||||
TempPaths: list[str],
|
||||
) -> str:
|
||||
"""将源文件转换为 PDF。"""
|
||||
source = Path(SourcePath)
|
||||
if source.suffix.lower() == ".pdf":
|
||||
return str(source)
|
||||
pdfTemp = tempfile.NamedTemporaryFile(suffix=".pdf", delete=False)
|
||||
pdfTemp.close()
|
||||
TempPaths.append(pdfTemp.name)
|
||||
doc2pdf.convert(source, pdfTemp.name, soffice="auto", pdfa=False, force=True, verify=False)
|
||||
return pdfTemp.name
|
||||
|
||||
def _merge_pdf_paths_for_merge(
|
||||
self,
|
||||
*,
|
||||
PdfPaths: list[str],
|
||||
TempPaths: list[str],
|
||||
) -> str:
|
||||
"""合并多个 PDF 为一个临时 PDF。"""
|
||||
mergedTemp = tempfile.NamedTemporaryFile(suffix=".pdf", delete=False)
|
||||
mergedTemp.close()
|
||||
TempPaths.append(mergedTemp.name)
|
||||
output = fitz.open()
|
||||
try:
|
||||
for pdfPath in PdfPaths:
|
||||
source = fitz.open(pdfPath)
|
||||
try:
|
||||
output.insert_pdf(source)
|
||||
finally:
|
||||
source.close()
|
||||
output.save(mergedTemp.name)
|
||||
finally:
|
||||
output.close()
|
||||
return mergedTemp.name
|
||||
|
||||
async def _persistMergedPdfForDocument(
|
||||
self,
|
||||
Session,
|
||||
*,
|
||||
DocumentId: int,
|
||||
TypeCode: str,
|
||||
Region: str,
|
||||
VersionNo: int,
|
||||
CreatedBy: int | None,
|
||||
FileRole: str = "primary",
|
||||
) -> None:
|
||||
"""为当前文档生成并替换主 PDF 文件。"""
|
||||
mergedBytes, mergedName = await self._buildMergedPdfBytesForDocument(
|
||||
Session,
|
||||
DocumentId=DocumentId,
|
||||
)
|
||||
mergedSha256 = hashlib.sha256(mergedBytes).hexdigest()
|
||||
mergedSize = len(mergedBytes)
|
||||
uploadedAt = datetime.now()
|
||||
versionLabel = f"v{VersionNo}"
|
||||
objectKey = OssPathUtils.BuildBusinessDocKey(
|
||||
Region=Region,
|
||||
TypeCode=TypeCode,
|
||||
DocumentId=DocumentId,
|
||||
Version=versionLabel,
|
||||
FileRole=FileRole,
|
||||
FileName=mergedName,
|
||||
Year=uploadedAt.year,
|
||||
Month=uploadedAt.month,
|
||||
)
|
||||
ossUrl = await self.OssService.UploadBytes(
|
||||
ObjectKey=objectKey,
|
||||
Content=mergedBytes,
|
||||
ContentType="application/pdf",
|
||||
)
|
||||
|
||||
if FileRole == "primary":
|
||||
await Session.execute(
|
||||
text(
|
||||
"""
|
||||
UPDATE leaudit_document_files
|
||||
SET is_active = false
|
||||
WHERE document_id = :document_id
|
||||
AND deleted_at IS NULL
|
||||
AND is_active = true
|
||||
AND file_role IN ('primary', 'merged_pdf', 'merged_docx')
|
||||
"""
|
||||
),
|
||||
{"document_id": DocumentId},
|
||||
)
|
||||
else:
|
||||
await Session.execute(
|
||||
text(
|
||||
"""
|
||||
UPDATE leaudit_document_files
|
||||
SET is_active = false
|
||||
WHERE document_id = :document_id
|
||||
AND deleted_at IS NULL
|
||||
AND is_active = true
|
||||
AND file_role = :file_role
|
||||
"""
|
||||
),
|
||||
{"document_id": DocumentId, "file_role": FileRole},
|
||||
)
|
||||
|
||||
Session.add(
|
||||
LeauditDocumentFile(
|
||||
documentId=DocumentId,
|
||||
fileRole=FileRole,
|
||||
fileName=mergedName,
|
||||
fileExt="pdf",
|
||||
mimeType="application/pdf",
|
||||
fileSize=mergedSize,
|
||||
sha256=mergedSha256,
|
||||
localPath=None,
|
||||
ossUrl=ossUrl,
|
||||
storageProvider="minio",
|
||||
isActive=True,
|
||||
createdBy=CreatedBy,
|
||||
)
|
||||
)
|
||||
await Session.flush()
|
||||
|
||||
async def _persistMergedDocxForDocument(
|
||||
self,
|
||||
Session,
|
||||
*,
|
||||
DocumentId: int,
|
||||
TypeCode: str,
|
||||
Region: str,
|
||||
VersionNo: int,
|
||||
CreatedBy: int | None,
|
||||
) -> None:
|
||||
"""为当前文档生成并替换主 DOCX 文件。"""
|
||||
mergedBytes, mergedName = await self._buildMergedDocxBytesForDocument(
|
||||
Session,
|
||||
DocumentId=DocumentId,
|
||||
)
|
||||
mergedSha256 = hashlib.sha256(mergedBytes).hexdigest()
|
||||
mergedSize = len(mergedBytes)
|
||||
uploadedAt = datetime.now()
|
||||
versionLabel = f"v{VersionNo}"
|
||||
objectKey = OssPathUtils.BuildBusinessDocKey(
|
||||
Region=Region,
|
||||
TypeCode=TypeCode,
|
||||
DocumentId=DocumentId,
|
||||
Version=versionLabel,
|
||||
FileRole="primary",
|
||||
FileName=mergedName,
|
||||
Year=uploadedAt.year,
|
||||
Month=uploadedAt.month,
|
||||
)
|
||||
ossUrl = await self.OssService.UploadBytes(
|
||||
ObjectKey=objectKey,
|
||||
Content=mergedBytes,
|
||||
ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
)
|
||||
|
||||
await Session.execute(
|
||||
text(
|
||||
"""
|
||||
UPDATE leaudit_document_files
|
||||
SET is_active = false
|
||||
WHERE document_id = :document_id
|
||||
AND deleted_at IS NULL
|
||||
AND is_active = true
|
||||
AND file_role IN ('primary', 'merged_pdf', 'merged_docx')
|
||||
"""
|
||||
),
|
||||
{"document_id": DocumentId},
|
||||
)
|
||||
|
||||
Session.add(
|
||||
LeauditDocumentFile(
|
||||
documentId=DocumentId,
|
||||
fileRole="primary",
|
||||
fileName=mergedName,
|
||||
fileExt="docx",
|
||||
mimeType="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
fileSize=mergedSize,
|
||||
sha256=mergedSha256,
|
||||
localPath=None,
|
||||
ossUrl=ossUrl,
|
||||
storageProvider="minio",
|
||||
isActive=True,
|
||||
createdBy=CreatedBy,
|
||||
)
|
||||
)
|
||||
await Session.flush()
|
||||
|
||||
async def _createNextVersionFromExistingDocument(
|
||||
self,
|
||||
Session,
|
||||
*,
|
||||
SourceDocumentId: int,
|
||||
CreatedBy: int,
|
||||
Remark: str | None = None,
|
||||
) -> tuple[LeauditDocument, str, str]:
|
||||
"""基于现有文档创建一个新版本，并复制当前主文件/附件。"""
|
||||
documentColumns = await self._loadDocumentColumns(Session)
|
||||
optionalSelects = [
|
||||
"d.document_number AS document_number" if "document_number" in documentColumns else "NULL::text AS document_number",
|
||||
"d.remark AS remark" if "remark" in documentColumns else "NULL::text AS remark",
|
||||
"d.is_test_document AS is_test_document" if "is_test_document" in documentColumns else "FALSE AS is_test_document",
|
||||
"d.audit_status AS audit_status" if "audit_status" in documentColumns else "NULL::integer AS audit_status",
|
||||
]
|
||||
sourceRow = (
|
||||
await Session.execute(
|
||||
text(
|
||||
"""
|
||||
SELECT
|
||||
d.id,
|
||||
d.biz_document_id,
|
||||
d.type_id,
|
||||
d.group_id,
|
||||
d.region,
|
||||
d.processing_status,
|
||||
d.version_group_key,
|
||||
d.version_no,
|
||||
d.previous_version_id,
|
||||
d.root_version_id,
|
||||
d.is_latest_version,
|
||||
d.normalized_name,
|
||||
d.review_scope,
|
||||
"""
|
||||
+ ",\n ".join(optionalSelects)
|
||||
+ """
|
||||
,
|
||||
dt.code AS type_code
|
||||
FROM leaudit_documents d
|
||||
LEFT JOIN leaudit_document_types dt
|
||||
ON dt.id = d.type_id
|
||||
WHERE d.id = :document_id
|
||||
AND d.deleted_at IS NULL
|
||||
LIMIT 1
|
||||
"""
|
||||
),
|
||||
{"document_id": SourceDocumentId},
|
||||
)
|
||||
).mappings().first()
|
||||
if not sourceRow:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_404_NOT_FOUND, "文档不存在或无权访问")
|
||||
|
||||
resolvedTypeCode = str(sourceRow["type_code"] or "").strip()
|
||||
if not resolvedTypeCode:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "当前文档缺少文档类型编码，无法创建新版本")
|
||||
|
||||
previousDocument = await Session.get(LeauditDocument, SourceDocumentId)
|
||||
if previousDocument is None:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_404_NOT_FOUND, "文档不存在或无权访问")
|
||||
previousDocument.isLatestVersion = False
|
||||
|
||||
documentFields: dict[str, object] = {
|
||||
"bizDocumentId": time.time_ns(),
|
||||
"typeId": int(sourceRow["type_id"]) if sourceRow["type_id"] is not None else None,
|
||||
"groupId": int(sourceRow["group_id"]) if sourceRow["group_id"] is not None else None,
|
||||
"region": str(sourceRow["region"] or "default").strip() or "default",
|
||||
"processingStatus": "waiting",
|
||||
"versionGroupKey": str(sourceRow["version_group_key"] or uuid.uuid4().hex),
|
||||
"versionNo": int(sourceRow["version_no"] or 1) + 1,
|
||||
"previousVersionId": SourceDocumentId,
|
||||
"rootVersionId": int(sourceRow["root_version_id"] or SourceDocumentId),
|
||||
"isLatestVersion": True,
|
||||
"normalizedName": sourceRow["normalized_name"],
|
||||
"reviewScope": str(sourceRow["review_scope"] or "standard"),
|
||||
}
|
||||
|
||||
newDocument = await LeauditDocument.create_new(Session, **documentFields)
|
||||
if newDocument.rootVersionId is None:
|
||||
newDocument.rootVersionId = newDocument.Id
|
||||
|
||||
assignments: list[str] = []
|
||||
params: dict[str, object] = {"id": int(newDocument.Id)}
|
||||
if "document_number" in documentColumns:
|
||||
assignments.append("document_number = :document_number")
|
||||
params["document_number"] = sourceRow["document_number"]
|
||||
if "remark" in documentColumns:
|
||||
assignments.append("remark = :remark")
|
||||
params["remark"] = Remark.strip() if Remark and Remark.strip() else sourceRow["remark"]
|
||||
if "is_test_document" in documentColumns:
|
||||
assignments.append("is_test_document = :is_test_document")
|
||||
params["is_test_document"] = bool(sourceRow["is_test_document"])
|
||||
if "audit_status" in documentColumns:
|
||||
assignments.append("audit_status = :audit_status")
|
||||
params["audit_status"] = int(sourceRow["audit_status"]) if sourceRow["audit_status"] is not None else None
|
||||
if assignments:
|
||||
assignments.append("updated_at = NOW()")
|
||||
await Session.execute(
|
||||
text(f"UPDATE leaudit_documents SET {', '.join(assignments)} WHERE id = :id"),
|
||||
params,
|
||||
)
|
||||
|
||||
await self._cloneActiveFilesToNewDocument(
|
||||
Session,
|
||||
SourceDocumentId=SourceDocumentId,
|
||||
TargetDocumentId=newDocument.Id,
|
||||
CreatedBy=CreatedBy,
|
||||
IncludeAttachments=False,
|
||||
)
|
||||
await Session.flush()
|
||||
return newDocument, resolvedTypeCode, str(sourceRow["region"] or "default").strip() or "default"
|
||||
|
||||
def _normalizeAttachmentMergeMode(self, MergeMode: str | None) -> str:
|
||||
"""标准化附件合并模式。"""
|
||||
normalizedMode = (MergeMode or "new").strip().lower()
|
||||
if normalizedMode not in {"overwrite", "new"}:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "mergeMode 仅支持 overwrite 或 new")
|
||||
return normalizedMode
|
||||
|
||||
async def DeleteDocument(self, CurrentUserId: int, Id: int) -> None:
|
||||
"""软删除文档，并执行数据隔离校验。"""
|
||||
async with GetAsyncSession() as Session:
|
||||
currentUser = await self._getCurrentUserContext(CurrentUserId)
|
||||
filters = ["d.id = :id", "d.deleted_at IS NULL", "f.is_active = true", "f.file_role = 'primary'"]
|
||||
filters = [
|
||||
"d.id = :id",
|
||||
"d.deleted_at IS NULL",
|
||||
"f.is_active = true",
|
||||
"f.file_role = 'primary'",
|
||||
]
|
||||
params: dict[str, object] = {"id": Id}
|
||||
filters.extend(
|
||||
self._buildDocumentScopeFilters(
|
||||
@@ -1141,10 +1830,13 @@ class DocumentServiceImpl(IDocumentService):
|
||||
CurrentUserId: int,
|
||||
Id: int,
|
||||
Files: list[tuple[str, bytes, str | None]],
|
||||
MergeMode: str = "overwrite",
|
||||
Remark: str | None = None,
|
||||
) -> DocumentDetailVO:
|
||||
"""为现有文档追加附件，并执行数据隔离校验。"""
|
||||
if not Files:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "至少上传一个附件文件")
|
||||
normalizedMergeMode = self._normalizeAttachmentMergeMode(MergeMode)
|
||||
|
||||
async with GetAsyncSession() as Session:
|
||||
await self._ensureDocumentGroupColumn(Session)
|
||||
@@ -1182,18 +1874,72 @@ class DocumentServiceImpl(IDocumentService):
|
||||
if not resolvedTypeCode:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_400_BAD_REQUEST, "当前文档缺少文档类型编码，无法追加附件")
|
||||
|
||||
primaryFileRow = await self._load_active_primary_file_row(Session, DocumentId=Id)
|
||||
mainSourceKind = self._normalize_document_source_kind(
|
||||
str(primaryFileRow["file_name"] or ""),
|
||||
primaryFileRow.get("file_ext"),
|
||||
primaryFileRow.get("mime_type"),
|
||||
)
|
||||
self._validate_attachment_matrix(
|
||||
MainSourceKind=mainSourceKind,
|
||||
Files=Files,
|
||||
)
|
||||
|
||||
targetDocumentId = int(documentMeta["document_id"])
|
||||
targetVersionNo = int(documentMeta["version_no"] or 1)
|
||||
normalizedRegion = str(documentMeta["region"] or "default").strip() or "default"
|
||||
|
||||
if normalizedMergeMode == "new":
|
||||
newDocument, resolvedTypeCode, normalizedRegion = await self._createNextVersionFromExistingDocument(
|
||||
Session,
|
||||
SourceDocumentId=Id,
|
||||
CreatedBy=CurrentUserId,
|
||||
Remark=Remark,
|
||||
)
|
||||
targetDocumentId = int(newDocument.Id)
|
||||
targetVersionNo = int(newDocument.versionNo or (int(documentMeta["version_no"] or 1) + 1))
|
||||
|
||||
await self._appendAttachmentFiles(
|
||||
Session=Session,
|
||||
DocumentId=int(documentMeta["document_id"]),
|
||||
DocumentId=targetDocumentId,
|
||||
TypeCode=resolvedTypeCode,
|
||||
Region=normalizedRegion,
|
||||
VersionNo=int(documentMeta["version_no"] or 1),
|
||||
VersionNo=targetVersionNo,
|
||||
Files=Files,
|
||||
CreatedBy=CurrentUserId,
|
||||
)
|
||||
|
||||
refreshed = await self._getDocumentDetail(Session, Id, CurrentUserId, currentUser, documentColumns)
|
||||
if mainSourceKind == "docx":
|
||||
await self._persistMergedDocxForDocument(
|
||||
Session,
|
||||
DocumentId=targetDocumentId,
|
||||
TypeCode=resolvedTypeCode,
|
||||
Region=normalizedRegion,
|
||||
VersionNo=targetVersionNo,
|
||||
CreatedBy=CurrentUserId,
|
||||
)
|
||||
await self._persistMergedPdfForDocument(
|
||||
Session,
|
||||
DocumentId=targetDocumentId,
|
||||
TypeCode=resolvedTypeCode,
|
||||
Region=normalizedRegion,
|
||||
VersionNo=targetVersionNo,
|
||||
CreatedBy=CurrentUserId,
|
||||
FileRole="merged_pdf",
|
||||
)
|
||||
else:
|
||||
await self._persistMergedPdfForDocument(
|
||||
Session,
|
||||
DocumentId=targetDocumentId,
|
||||
TypeCode=resolvedTypeCode,
|
||||
Region=normalizedRegion,
|
||||
VersionNo=targetVersionNo,
|
||||
CreatedBy=CurrentUserId,
|
||||
)
|
||||
|
||||
await Session.commit()
|
||||
|
||||
refreshed = await self._getDocumentDetail(Session, targetDocumentId, CurrentUserId, currentUser, documentColumns)
|
||||
if not refreshed:
|
||||
raise LeauditException(StatusCodeEnum.HTTP_404_NOT_FOUND, "文档不存在或无权访问")
|
||||
return refreshed
|
||||
@@ -1949,7 +2695,12 @@ class DocumentServiceImpl(IDocumentService):
|
||||
) -> DocumentDetailVO | None:
|
||||
"""查询单文档详情，并附带历史版本。"""
|
||||
params: dict[str, object] = {"id": DocumentId}
|
||||
filters = ["d.id = :id", "d.deleted_at IS NULL", "f.is_active = true", "f.file_role = 'primary'"]
|
||||
filters = [
|
||||
"d.id = :id",
|
||||
"d.deleted_at IS NULL",
|
||||
"f.is_active = true",
|
||||
"f.file_role = 'primary'",
|
||||
]
|
||||
if not BypassScopeCheck:
|
||||
filters.extend(
|
||||
self._buildDocumentScopeFilters(
|
||||
@@ -2065,6 +2816,7 @@ class DocumentServiceImpl(IDocumentService):
|
||||
f.id AS file_id,
|
||||
f.file_name,
|
||||
f.file_ext,
|
||||
f.oss_url,
|
||||
ar.status AS run_status,
|
||||
ar.result_status
|
||||
FROM leaudit_documents d
|
||||
@@ -2090,6 +2842,7 @@ class DocumentServiceImpl(IDocumentService):
|
||||
versionNo=int(row["version_no"]),
|
||||
fileName=row["file_name"],
|
||||
fileExt=row["file_ext"],
|
||||
ossUrl=row["oss_url"],
|
||||
processingStatus=row["processing_status"],
|
||||
runStatus=row["run_status"],
|
||||
resultStatus=row["result_status"],
|
||||
@@ -2913,8 +3666,9 @@ class DocumentServiceImpl(IDocumentService):
|
||||
ORDER BY
|
||||
CASE file_role
|
||||
WHEN 'converted_pdf' THEN 0
|
||||
WHEN 'merged_pdf' THEN 1
|
||||
WHEN 'primary' THEN 2
|
||||
WHEN 'primary' THEN 1
|
||||
WHEN 'merged_docx' THEN 2
|
||||
WHEN 'merged_pdf' THEN 3
|
||||
ELSE 9
|
||||
END,
|
||||
id DESC
|
||||
|
||||
Reference in New Issue
Block a user