doc-forge-remark/backend/routers/export.py

import asyncio
import json
import os
import uuid
from datetime import datetime

from fastapi import APIRouter, Depends, HTTPException
from fastapi.responses import PlainTextResponse, RedirectResponse
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession

from config import settings
from database import get_db
from models.document import Document
from models.generation_log import GenerationLog
from models.paragraph import Paragraph
from models.template import Template
from models.template_block import TemplateBlock
from services.document_export import export_document_bytes, export_document_bytes_from_blocks
from services.minio_client import (
    download_object_bytes,
    get_presigned_url,
    split_bucket_path,
    upload_bytes,
)

router = APIRouter()


@router.get("/{document_id}/docx")
async def export_docx(document_id: int, db: AsyncSession = Depends(get_db)):
    document = await db.get(Document, document_id)
    if document is None:
        raise HTTPException(status_code=404, detail="生成记录不存在")

    template = await db.get(Template, document.template_id)
    if template is None:
        raise HTTPException(status_code=404, detail="模板不存在")

    template_bucket, template_object = split_bucket_path(template.file_path)
    template_bytes = await asyncio.to_thread(download_object_bytes, template_bucket, template_object)

    result = await db.execute(
        select(GenerationLog, Paragraph)
        .join(Paragraph, Paragraph.id == GenerationLog.paragraph_id)
        .where(GenerationLog.document_id == document_id)
        .order_by(Paragraph.sort_index.asc(), Paragraph.id.asc())
    )
    logs = []
    for log, paragraph in result.all():
        logs.append(
            {
                "anchor_title": paragraph.anchor_title or paragraph.title,
                "title": paragraph.title,
                "write_mode": paragraph.write_mode,
                "content": json.loads(log.content) if log.content else {"content": []},
            }
        )

    exported_bytes = await asyncio.to_thread(export_document_bytes, template_bytes, logs)
    object_name = f"{datetime.now().strftime('%Y%m%d')}/{uuid.uuid4().hex}.docx"
    await asyncio.to_thread(
        upload_bytes,
        settings.MINIO_BUCKET_OUTPUTS,
        object_name,
        exported_bytes,
        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
    )

    document.file_path = f"{settings.MINIO_BUCKET_OUTPUTS}/{object_name}"
    await db.commit()
    return RedirectResponse(
        url=get_presigned_url(settings.MINIO_BUCKET_OUTPUTS, object_name),
        status_code=307,
    )


@router.get("/{document_id}/docx-v2")
async def export_docx_v2(document_id: int, db: AsyncSession = Depends(get_db)):
    """基于块结构的 Word 导出。"""
    document = await db.get(Document, document_id)
    if document is None:
        raise HTTPException(status_code=404, detail="生成记录不存在")

    template = await db.get(Template, document.template_id)
    if template is None:
        raise HTTPException(status_code=404, detail="模板不存在")

    template_bucket, template_object = split_bucket_path(template.file_path)
    template_bytes = await asyncio.to_thread(download_object_bytes, template_bucket, template_object)

    # 查询块和生成日志
    blocks_result = await db.execute(
        select(TemplateBlock)
        .where(TemplateBlock.template_id == document.template_id)
        .order_by(TemplateBlock.sort_index.asc(), TemplateBlock.id.asc())
    )
    blocks = blocks_result.scalars().all()

    logs_result = await db.execute(
        select(GenerationLog)
        .where(GenerationLog.document_id == document_id)
    )
    logs = logs_result.scalars().all()

    block_dicts = [
        {
            "id": b.id,
            "sort_index": b.sort_index,
            "anchor_start_index": b.anchor_start_index,
            "anchor_end_index": b.anchor_end_index,
            "edit_mode": b.edit_mode,
            "block_type": b.block_type,
            "title": b.title,
        }
        for b in blocks
    ]

    log_dicts = [
        {
            "id": log.id,
            "block_id": log.block_id,
            "status": log.status,
            "content": json.loads(log.content) if log.content else {"content": []},
        }
        for log in logs
    ]

    exported_bytes = await asyncio.to_thread(
        export_document_bytes_from_blocks, template_bytes, block_dicts, log_dicts
    )

    object_name = f"{datetime.now().strftime('%Y%m%d')}/{uuid.uuid4().hex}.docx"
    await asyncio.to_thread(
        upload_bytes,
        settings.MINIO_BUCKET_OUTPUTS,
        object_name,
        exported_bytes,
        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
    )

    document.file_path = f"{settings.MINIO_BUCKET_OUTPUTS}/{object_name}"
    await db.commit()
    return RedirectResponse(
        url=get_presigned_url(settings.MINIO_BUCKET_OUTPUTS, object_name),
        status_code=307,
    )


@router.get("/{document_id}/pdf")
async def export_pdf(document_id: int):
    return PlainTextResponse(
        f"文档 {document_id} 的 PDF 导出功能正在开发中，当前版本请先使用预览页查看结果。",
        media_type="text/plain; charset=utf-8",
    )