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

510 lines
19 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import asyncio
import json
import os
import tempfile
import uuid
from datetime import datetime
from io import BytesIO
from fastapi import APIRouter, Depends, File, HTTPException, Query, UploadFile
from sqlalchemy import delete, func, 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 schemas.schemas import Response, TemplateSave
from services.minio_client import minio_client
from services.template_parser import parse_template
from services.word_to_html import docx_to_full_html, docx_to_html_blocks
router = APIRouter()
def _build_object_path(filename: str) -> tuple[str, str]:
ext = os.path.splitext(filename)[1].lower()
date_prefix = datetime.now().strftime("%Y%m%d")
object_name = f"{date_prefix}/{uuid.uuid4().hex}{ext}"
return ext, object_name
def _serialize_paragraph(paragraph: Paragraph) -> dict:
return {
"id": paragraph.id,
"template_id": paragraph.template_id,
"sort_index": paragraph.sort_index,
"anchor_title": paragraph.anchor_title,
"title": paragraph.title,
"content": paragraph.content,
"style_json": paragraph.style_json,
"is_table": paragraph.is_table,
"table_json": paragraph.table_json,
"edit_mode": paragraph.edit_mode,
"write_mode": paragraph.write_mode,
"model_id": paragraph.model_id,
"need_prompt": paragraph.need_prompt,
"prompt_text": paragraph.prompt_text,
"need_file": paragraph.need_file,
"file_note": paragraph.file_note,
"output_format": paragraph.output_format,
}
def _serialize_template(template: Template) -> dict:
return {
"id": template.id,
"name": template.name,
"description": template.description,
"file_path": template.file_path,
"paragraph_count": template.paragraph_count,
"status": template.status,
"created_at": template.created_at,
"updated_at": template.updated_at,
}
def _serialize_block(block: TemplateBlock) -> dict:
return {
"id": block.id,
"template_id": block.template_id,
"sort_index": block.sort_index,
"block_type": block.block_type,
"anchor_ref": block.anchor_ref,
"anchor_start_index": block.anchor_start_index,
"anchor_end_index": block.anchor_end_index,
"html_snippet": block.html_snippet,
"title": block.title,
"content_json": block.content_json,
"style_json": block.style_json,
"edit_mode": block.edit_mode,
"placeholder_key": block.placeholder_key,
"variable_key": block.variable_key,
"default_value": block.default_value,
"model_id": block.model_id,
"need_prompt": block.need_prompt,
"prompt_text": block.prompt_text,
"need_file": block.need_file,
"file_note": block.file_note,
"output_format": block.output_format,
}
@router.get("")
async def list_templates(
page: int = Query(1, ge=1),
page_size: int = Query(20, ge=1, le=100),
keyword: str = Query("", alias="q"),
db: AsyncSession = Depends(get_db),
):
filters = []
if keyword:
filters.append(Template.name.like(f"%{keyword}%"))
total_stmt = select(func.count(Template.id))
list_stmt = select(Template).order_by(Template.id.desc())
if filters:
total_stmt = total_stmt.where(*filters)
list_stmt = list_stmt.where(*filters)
total = (await db.execute(total_stmt)).scalar_one()
result = await db.execute(list_stmt.offset((page - 1) * page_size).limit(page_size))
items = [_serialize_template(item) for item in result.scalars().all()]
return Response(
data={"items": items, "total": total, "page": page, "page_size": page_size}
)
@router.get("/{template_id}")
async def get_template(template_id: int, db: AsyncSession = Depends(get_db)):
template = await db.get(Template, template_id)
if template is None:
raise HTTPException(status_code=404, detail="模板不存在")
result = await db.execute(
select(Paragraph)
.where(Paragraph.template_id == template_id)
.order_by(Paragraph.sort_index.asc(), Paragraph.id.asc())
)
paragraphs = [_serialize_paragraph(item) for item in result.scalars().all()]
payload = _serialize_template(template)
payload["paragraphs"] = paragraphs
return Response(data=payload)
@router.get("/{template_id}/preview")
async def get_template_preview(template_id: int, db: AsyncSession = Depends(get_db)):
"""返回模板的 HTML 预览文档及块列表。"""
template = await db.get(Template, template_id)
if template is None:
raise HTTPException(status_code=404, detail="模板不存在")
# 优先从缓存读取 HTML否则重新生成
result = await db.execute(
select(TemplateBlock)
.where(TemplateBlock.template_id == template_id)
.order_by(TemplateBlock.sort_index.asc(), TemplateBlock.id.asc())
)
blocks = result.scalars().all()
if not blocks:
# 从 MinIO 下载模板文件,重新生成 HTML 和块
file_path = template.file_path or ""
if "/" in file_path:
bucket, object_name = file_path.split("/", 1)
content = await asyncio.to_thread(minio_client.get_object, bucket, object_name)
try:
file_bytes = content.read()
finally:
content.close()
content.release_conn()
with tempfile.NamedTemporaryFile(delete=False, suffix=".docx") as temp_file:
temp_file.write(file_bytes)
temp_path = temp_file.name
try:
rendered_blocks = await asyncio.to_thread(docx_to_html_blocks, temp_path)
html_content = await asyncio.to_thread(docx_to_full_html, temp_path)
finally:
if os.path.exists(temp_path):
os.remove(temp_path)
block_rows: list[TemplateBlock] = []
for rb in rendered_blocks:
anchor_title = ""
if rb.block_type == "heading":
anchor_title = rb.text_content
block_row = TemplateBlock(
template_id=template_id,
sort_index=rb.block_index + 1,
block_type=rb.block_type,
anchor_ref=anchor_title,
anchor_start_index=rb.block_index,
anchor_end_index=rb.block_index,
html_snippet=rb.html,
title=rb.text_content[:200] if rb.text_content else "",
content_json=json.dumps({"text": rb.text_content}, ensure_ascii=False),
style_json=rb.style_json,
edit_mode="manual",
)
db.add(block_row)
block_rows.append(block_row)
await db.commit()
for br in block_rows:
await db.refresh(br)
blocks = block_rows
block_list = [_serialize_block(b) for b in blocks]
# 检查是否有缓存的 HTML 快照
html_snapshot = ""
for b in blocks:
if b.html_snippet:
html_snapshot += b.html_snippet + "\n"
if not html_snapshot:
# 重新生成 HTML
file_path = template.file_path or ""
if "/" in file_path:
bucket, object_name = file_path.split("/", 1)
content = await asyncio.to_thread(minio_client.get_object, bucket, object_name)
try:
file_bytes = content.read()
finally:
content.close()
content.release_conn()
with tempfile.NamedTemporaryFile(delete=False, suffix=".docx") as temp_file:
temp_file.write(file_bytes)
temp_path = temp_file.name
try:
html_snapshot = await asyncio.to_thread(docx_to_full_html, temp_path)
finally:
if os.path.exists(temp_path):
os.remove(temp_path)
return Response(data={
"template": _serialize_template(template),
"blocks": block_list,
"html": html_snapshot,
"block_count": len(block_list),
})
@router.post("/upload")
async def upload_template(file: UploadFile = File(...), db: AsyncSession = Depends(get_db)):
if not file.filename:
raise HTTPException(status_code=400, detail="文件名不能为空")
ext, object_name = _build_object_path(file.filename)
if ext != ".docx":
raise HTTPException(status_code=400, detail="模板仅支持 .docx 格式")
content = await file.read()
if not content:
raise HTTPException(status_code=400, detail="上传文件不能为空")
if len(content) > settings.MAX_UPLOAD_SIZE:
raise HTTPException(status_code=400, detail="文件大小超过限制")
with tempfile.NamedTemporaryFile(delete=False, suffix=ext) as temp_file:
temp_file.write(content)
temp_path = temp_file.name
try:
parsed_items = await asyncio.to_thread(parse_template, temp_path)
rendered_blocks = await asyncio.to_thread(docx_to_html_blocks, temp_path)
html_snapshot = await asyncio.to_thread(docx_to_full_html, temp_path)
finally:
if os.path.exists(temp_path):
os.remove(temp_path)
await asyncio.to_thread(
minio_client.put_object,
settings.MINIO_BUCKET_TEMPLATES,
object_name,
BytesIO(content),
len(content),
file.content_type or "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
)
template = Template(
name=os.path.splitext(file.filename)[0],
description="",
file_path=f"{settings.MINIO_BUCKET_TEMPLATES}/{object_name}",
paragraph_count=len(parsed_items),
status="draft",
)
db.add(template)
await db.flush()
paragraph_rows: list[Paragraph] = []
for item in parsed_items:
paragraph = Paragraph(
template_id=template.id,
sort_index=item.sort_index,
anchor_title=item.anchor_title,
title=item.title,
content=item.content,
style_json=item.style_json,
is_table=item.is_table,
table_json=item.table_json,
edit_mode="manual",
write_mode=item.write_mode,
)
db.add(paragraph)
paragraph_rows.append(paragraph)
# 同步生成新版块结构
block_rows: list[TemplateBlock] = []
for rb in rendered_blocks:
anchor_title = rb.text_content if rb.block_type == "heading" else ""
block_row = TemplateBlock(
template_id=template.id,
sort_index=rb.block_index + 1,
block_type=rb.block_type,
anchor_ref=anchor_title,
anchor_start_index=rb.block_index,
anchor_end_index=rb.block_index,
html_snippet=rb.html,
title=rb.text_content[:200] if rb.text_content else "",
content_json=json.dumps({"text": rb.text_content}, ensure_ascii=False),
style_json=rb.style_json,
edit_mode="manual",
)
db.add(block_row)
block_rows.append(block_row)
await db.commit()
await db.refresh(template)
for paragraph in paragraph_rows:
await db.refresh(paragraph)
for br in block_rows:
await db.refresh(br)
payload = _serialize_template(template)
payload["paragraphs"] = [_serialize_paragraph(item) for item in paragraph_rows]
payload["blocks"] = [_serialize_block(b) for b in block_rows]
payload["html"] = html_snapshot
return Response(data=payload)
@router.put("/{template_id}/paragraphs")
async def save_template_paragraphs(
template_id: int,
body: TemplateSave,
db: AsyncSession = Depends(get_db),
):
template = await db.get(Template, template_id)
if template is None:
raise HTTPException(status_code=404, detail="模板不存在")
result = await db.execute(
select(Paragraph)
.where(Paragraph.template_id == template_id)
.order_by(Paragraph.sort_index.asc(), Paragraph.id.asc())
)
existing_paragraphs = result.scalars().all()
paragraph_map = {item.id: item for item in existing_paragraphs}
incoming_ids = {config.id for config in body.paragraphs if config.id}
print(f"[SAVE] template_id={template_id}, incoming_ids={incoming_ids}, existing_ids={[p.id for p in existing_paragraphs]}")
for paragraph in existing_paragraphs:
if paragraph.id not in incoming_ids:
print(f"[SAVE] Deleting paragraph id={paragraph.id} title={paragraph.title}")
await db.execute(
delete(GenerationLog).where(GenerationLog.paragraph_id == paragraph.id)
)
await db.delete(paragraph)
for index, config in enumerate(body.paragraphs, start=1):
paragraph = paragraph_map.get(config.id) if config.id else None
if paragraph is None:
paragraph = Paragraph(template_id=template_id)
db.add(paragraph)
paragraph.sort_index = index
paragraph.anchor_title = config.anchor_title or config.title or paragraph.anchor_title
paragraph.title = config.title
paragraph.content = config.content
paragraph.edit_mode = config.edit_mode
paragraph.write_mode = config.write_mode
paragraph.model_id = config.model_id
paragraph.need_prompt = config.need_prompt
paragraph.prompt_text = config.prompt_text
paragraph.need_file = config.need_file
paragraph.file_note = config.file_note
paragraph.output_format = config.output_format
await db.commit()
template.paragraph_count = len(body.paragraphs)
await db.commit()
return Response(data={"template_id": template_id, "saved": len(body.paragraphs)})
@router.put("/{template_id}/blocks")
async def save_template_blocks(
template_id: int,
body: dict,
db: AsyncSession = Depends(get_db),
):
"""保存模板的块配置(可视化编辑器使用)。"""
template = await db.get(Template, template_id)
if template is None:
raise HTTPException(status_code=404, detail="模板不存在")
block_data = body.get("blocks", [])
if not block_data:
raise HTTPException(status_code=400, detail="块数据不能为空")
result = await db.execute(
select(TemplateBlock)
.where(TemplateBlock.template_id == template_id)
)
existing_blocks = result.scalars().all()
block_map = {b.id: b for b in existing_blocks}
incoming_ids = {b.get("id") for b in block_data if b.get("id")}
# 删除被移除的块
for block in existing_blocks:
if block.id not in incoming_ids:
await db.delete(block)
# 新增 / 更新块
for index, config in enumerate(block_data, start=1):
block = block_map.get(config.get("id")) if config.get("id") else None
if block is None:
block = TemplateBlock(template_id=template_id)
db.add(block)
block.sort_index = index
block.block_type = config.get("block_type", block.block_type)
block.anchor_ref = config.get("anchor_ref", block.anchor_ref)
block.anchor_start_index = config.get("anchor_start_index", block.anchor_start_index)
block.anchor_end_index = config.get("anchor_end_index", block.anchor_end_index)
block.title = config.get("title", block.title)
block.content_json = config.get("content_json", block.content_json)
block.style_json = config.get("style_json", block.style_json)
block.edit_mode = config.get("edit_mode", block.edit_mode)
block.model_id = config.get("model_id", block.model_id)
block.need_prompt = config.get("need_prompt", block.need_prompt)
block.prompt_text = config.get("prompt_text", block.prompt_text)
block.need_file = config.get("need_file", block.need_file)
block.file_note = config.get("file_note", block.file_note)
block.output_format = config.get("output_format", block.output_format)
await db.commit()
# 更新每个块的 html_snippet 加入对应的 CSS class
try:
result = await db.execute(
select(TemplateBlock)
.where(TemplateBlock.template_id == template_id)
.order_by(TemplateBlock.sort_index.asc(), TemplateBlock.id.asc())
)
updated_blocks = result.scalars().all()
for b in updated_blocks:
if b.html_snippet and b.edit_mode == "ai":
b.html_snippet = b.html_snippet.replace(
'data-block-index=',
'class="block-ai" data-block-index=',
1,
)
elif b.html_snippet and b.edit_mode == "manual":
b.html_snippet = b.html_snippet.replace(
'data-block-index=',
'class="block-fixed" data-block-index=',
1,
)
await db.commit()
except Exception:
pass
return Response(data={"template_id": template_id, "saved": len(block_data)})
@router.delete("/{template_id}")
async def delete_template(template_id: int, db: AsyncSession = Depends(get_db)):
template = await db.get(Template, template_id)
if template is None:
raise HTTPException(status_code=404, detail="模板不存在")
result = await db.execute(select(Paragraph).where(Paragraph.template_id == template_id))
paragraphs_to_delete = result.scalars().all()
paragraph_ids = [p.id for p in paragraphs_to_delete]
blocks_result = await db.execute(select(TemplateBlock).where(TemplateBlock.template_id == template_id))
blocks_to_delete = blocks_result.scalars().all()
doc_result = await db.execute(select(Document).where(Document.template_id == template_id))
documents_to_delete = doc_result.scalars().all()
if paragraph_ids:
await db.execute(
delete(GenerationLog).where(GenerationLog.paragraph_id.in_(paragraph_ids))
)
for document in documents_to_delete:
await db.execute(
delete(GenerationLog).where(GenerationLog.document_id == document.id)
)
await db.delete(document)
for paragraph in paragraphs_to_delete:
await db.delete(paragraph)
for block in blocks_to_delete:
await db.delete(block)
file_path = template.file_path or ""
if "/" in file_path:
bucket, object_name = file_path.split("/", 1)
try:
await asyncio.to_thread(minio_client.remove_object, bucket, object_name)
except Exception:
pass
await db.delete(template)
await db.commit()
return Response(data={"id": template_id})