feat(plugin): add document export, doc‑block, and TTS/ASR support
Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
This commit is contained in:
126
backend/main.py
126
backend/main.py
@@ -3,13 +3,16 @@ import base64
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
import uuid
|
||||
from typing import Optional
|
||||
|
||||
from fastapi import FastAPI, HTTPException, Request, Security
|
||||
from fastapi import FastAPI, HTTPException, Request, Security, File, UploadFile
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from fastapi.responses import JSONResponse, StreamingResponse
|
||||
from fastapi.responses import JSONResponse, StreamingResponse, Response
|
||||
from fastapi.security import APIKeyHeader
|
||||
from pydantic import BaseModel
|
||||
|
||||
@@ -81,6 +84,32 @@ class ConvertRequest(BaseModel):
|
||||
filename: str = "document.pdf"
|
||||
|
||||
|
||||
ALLOWED_CONVERT_EXTENSIONS = {".txt", ".docx", ".pptx", ".pdf"}
|
||||
IMAGE_MARKDOWN_RE = re.compile(r"!\[[^\]]*]\([^)]+\)")
|
||||
IMAGE_HTML_RE = re.compile(r"<img\b[^>]*>", re.IGNORECASE)
|
||||
|
||||
|
||||
def _convert_docx_to_pdf(input_path: str, output_path: str) -> None:
|
||||
node_executable = shutil.which("node")
|
||||
if not node_executable:
|
||||
raise RuntimeError("未找到 Node.js，无法转换 DOCX 为 PDF")
|
||||
|
||||
bridge_path = os.path.join(os.path.dirname(__file__), "docx2pdf_bridge.cjs")
|
||||
if not os.path.exists(bridge_path):
|
||||
raise RuntimeError("缺少 DOCX 转 PDF 桥接脚本")
|
||||
|
||||
result = subprocess.run(
|
||||
[node_executable, bridge_path, input_path, output_path],
|
||||
cwd=os.path.dirname(os.path.dirname(__file__)),
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
|
||||
if result.returncode != 0:
|
||||
error_text = (result.stderr or result.stdout or "DOCX 转 PDF 失败").strip()
|
||||
raise RuntimeError(error_text)
|
||||
|
||||
|
||||
def _preview(text: str, limit: int = 80) -> str:
|
||||
value = (text or "").replace("\n", "\\n")
|
||||
if len(value) <= limit:
|
||||
@@ -88,6 +117,14 @@ def _preview(text: str, limit: int = 80) -> str:
|
||||
return value[:limit] + "..."
|
||||
|
||||
|
||||
def _sanitize_converted_markdown(text: str) -> str:
|
||||
value = (text or "").replace("\r\n", "\n").replace("\r", "\n")
|
||||
value = IMAGE_MARKDOWN_RE.sub("", value)
|
||||
value = IMAGE_HTML_RE.sub("", value)
|
||||
value = re.sub(r"\n{3,}", "\n\n", value)
|
||||
return value.strip()
|
||||
|
||||
|
||||
def _sse_payload(payload: dict) -> str:
|
||||
return f"data: {json.dumps(payload)}\n\n"
|
||||
|
||||
@@ -253,9 +290,9 @@ async def ocr_image(request: OCRRequest, api_key: str = Security(get_api_key)):
|
||||
|
||||
@app.post("/v1/convert")
|
||||
async def convert_to_markdown(request: ConvertRequest, api_key: str = Security(get_api_key)):
|
||||
"""鐏忓棙鏋冩禒鎯版祮閹诡澀璐烳arkdown閺嶇厧绱?""
|
||||
"""Convert file to markdown"""
|
||||
request_id = str(uuid.uuid4())[:8]
|
||||
|
||||
|
||||
try:
|
||||
logger.info(
|
||||
"[%s] /v1/convert filename=%s file_base64_chars=%d",
|
||||
@@ -263,53 +300,106 @@ async def convert_to_markdown(request: ConvertRequest, api_key: str = Security(g
|
||||
request.filename,
|
||||
len(request.file or ""),
|
||||
)
|
||||
|
||||
# 鐟欙絿鐖淏ase64閺傚洣娆㈤崘鍛啇
|
||||
|
||||
# Decode base64
|
||||
file_bytes = base64.b64decode(request.file)
|
||||
logger.info("[%s] /v1/convert decoded file_bytes=%d", request_id, len(file_bytes))
|
||||
|
||||
# 閼惧嘲褰囬弬鍥︽閹碘晛鐫嶉崥?
|
||||
|
||||
# Get file extension
|
||||
ext = os.path.splitext(request.filename)[1].lower()
|
||||
|
||||
# 閸掓稑缂撴稉瀛樻閺傚洣娆?
|
||||
|
||||
if ext not in ALLOWED_CONVERT_EXTENSIONS:
|
||||
raise ValueError("仅支持 txt、docx、pptx、pdf 格式")
|
||||
|
||||
if ext == ".txt":
|
||||
markdown_text = _sanitize_converted_markdown(file_bytes.decode("utf-8", errors="ignore"))
|
||||
return {
|
||||
"markdown": markdown_text,
|
||||
"filename": request.filename
|
||||
}
|
||||
|
||||
# Create temporary file
|
||||
with tempfile.NamedTemporaryFile(delete=False, suffix=ext) as tmp:
|
||||
tmp.write(file_bytes)
|
||||
tmp_path = tmp.name
|
||||
|
||||
|
||||
try:
|
||||
# 娴ｈ法鏁arkItDown鏉烆剚宕叉稉绡梐rkdown
|
||||
# Convert using MarkItDown
|
||||
md = markitdown.MarkItDown()
|
||||
result = md.convert(tmp_path)
|
||||
markdown_text = result.text_content
|
||||
|
||||
markdown_text = _sanitize_converted_markdown(result.text_content)
|
||||
|
||||
logger.info(
|
||||
"[%s] /v1/convert success text_chars=%d text_preview='%s'",
|
||||
request_id,
|
||||
len(markdown_text or ""),
|
||||
_preview(markdown_text, 120),
|
||||
)
|
||||
|
||||
|
||||
return {
|
||||
"markdown": markdown_text,
|
||||
"filename": request.filename
|
||||
}
|
||||
finally:
|
||||
# 濞撳懐鎮婃稉瀛樻閺傚洣娆?
|
||||
# Clean up temporary file
|
||||
if os.path.exists(tmp_path):
|
||||
os.unlink(tmp_path)
|
||||
|
||||
|
||||
except Exception as e:
|
||||
logger.exception("[%s] /v1/convert failed: %s", request_id, e)
|
||||
return JSONResponse(content={"error": str(e)}, status_code=500)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@app.post("/v1/export/pdf")
|
||||
async def export_pdf(file: UploadFile = File(...), api_key: str = Security(get_api_key)):
|
||||
request_id = str(uuid.uuid4())[:8]
|
||||
original_name = file.filename or "document.docx"
|
||||
base_name = os.path.splitext(original_name)[0] or "document"
|
||||
|
||||
try:
|
||||
file_bytes = await file.read()
|
||||
logger.info(
|
||||
"[%s] /v1/export/pdf filename=%s file_bytes=%d",
|
||||
request_id,
|
||||
original_name,
|
||||
len(file_bytes),
|
||||
)
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
input_path = os.path.join(temp_dir, f"{base_name}.docx")
|
||||
output_path = os.path.join(temp_dir, f"{base_name}.pdf")
|
||||
|
||||
with open(input_path, "wb") as tmp_file:
|
||||
tmp_file.write(file_bytes)
|
||||
|
||||
await asyncio.to_thread(_convert_docx_to_pdf, input_path, output_path)
|
||||
|
||||
if not os.path.exists(output_path):
|
||||
raise RuntimeError("PDF 转换后未生成输出文件")
|
||||
|
||||
with open(output_path, "rb") as pdf_file:
|
||||
pdf_bytes = pdf_file.read()
|
||||
|
||||
logger.info("[%s] /v1/export/pdf success pdf_bytes=%d", request_id, len(pdf_bytes))
|
||||
headers = {
|
||||
"Content-Disposition": f'attachment; filename="{base_name}.pdf"',
|
||||
}
|
||||
return Response(content=pdf_bytes, media_type="application/pdf", headers=headers)
|
||||
except Exception as e:
|
||||
logger.exception("[%s] /v1/export/pdf failed: %s", request_id, e)
|
||||
return JSONResponse(content={"error": str(e)}, status_code=500)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import uvicorn
|
||||
|
||||
uvicorn.run(app, host="0.0.0.0", port=8001)
|
||||
|
||||
|
||||
# TTS and STT routes
|
||||
# TTS and ASR routes
|
||||
from tts_asr import register_tts_asr_routes
|
||||
register_tts_asr_routes(app)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user