126 lines
4.8 KiB
Python
126 lines
4.8 KiB
Python
"""Office 文档转 PDF(host-side LibreOffice)。
|
||
|
||
Docker 沙盒内不安装 LibreOffice；本工具运行在 backend host，把用户工作区内已有的
|
||
DOCX/PPTX/XLSX/ODF 文件交给 host `soffice --headless` 转成 PDF。新写的 Markdown
|
||
报告不走这里，统一由沙盒平台渲染器 `rendering/render.py --format pdf` 直出。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import shutil
|
||
import subprocess
|
||
import tempfile
|
||
from pathlib import Path
|
||
from typing import Optional
|
||
from uuid import uuid4
|
||
|
||
from tools.base import FileOutOfBounds, Tool
|
||
from web.pptx_render import SofficeNotFoundError, find_soffice
|
||
|
||
|
||
_ALLOWED_SUFFIXES = {
|
||
".doc", ".docx", ".ppt", ".pptx", ".xls", ".xlsx", ".odt", ".odp", ".ods",
|
||
}
|
||
_DEFAULT_TIMEOUT = 120
|
||
|
||
|
||
def soffice_available() -> bool:
|
||
"""Host 装有 LibreOffice 时才向 agent 注册工具。"""
|
||
try:
|
||
find_soffice()
|
||
except SofficeNotFoundError:
|
||
return False
|
||
return True
|
||
|
||
|
||
class OfficeToPdfTool(Tool):
|
||
name = "office_to_pdf"
|
||
description = (
|
||
"Convert an existing Office document in the current user's workspace to PDF using "
|
||
"LibreOffice on the backend host. Supports DOC/DOCX, PPT/PPTX, XLS/XLSX and ODF. "
|
||
"Use this only when an Office file already exists; for a new Markdown report, call "
|
||
"the platform rendering/render.py command with --format pdf directly."
|
||
)
|
||
parameters = {
|
||
"type": "object",
|
||
"properties": {
|
||
"source": {
|
||
"type": "string",
|
||
"description": "Existing Office file path, relative to task_dir or under /workspace.",
|
||
},
|
||
"output": {
|
||
"type": "string",
|
||
"description": (
|
||
"Optional output .pdf path in the user's workspace. "
|
||
"Defaults to the source path with a .pdf suffix."
|
||
),
|
||
},
|
||
},
|
||
"required": ["source"],
|
||
}
|
||
|
||
def execute(self, source: str, output: Optional[str] = None) -> str:
|
||
try:
|
||
src = self._resolve_user_file(source)
|
||
except FileOutOfBounds:
|
||
return f"[Error] source path out of user workspace: {source}"
|
||
if not src.is_file():
|
||
return f"[Error] source file not found: {source}"
|
||
if src.suffix.lower() not in _ALLOWED_SUFFIXES:
|
||
allowed = ", ".join(sorted(_ALLOWED_SUFFIXES))
|
||
return f"[Error] unsupported Office format {src.suffix!r}; allowed: {allowed}"
|
||
|
||
raw_out = output.strip() if isinstance(output, str) and output.strip() else ""
|
||
try:
|
||
out = self._resolve_user_file(raw_out) if raw_out else src.with_suffix(".pdf")
|
||
except FileOutOfBounds:
|
||
return f"[Error] output path out of user workspace: {output}"
|
||
if out.suffix.lower() != ".pdf":
|
||
return f"[Error] output must end with .pdf: {output}"
|
||
|
||
try:
|
||
soffice = find_soffice()
|
||
except SofficeNotFoundError as e:
|
||
return f"[Error] LibreOffice unavailable on backend host: {e}"
|
||
|
||
out.parent.mkdir(parents=True, exist_ok=True)
|
||
try:
|
||
with tempfile.TemporaryDirectory(prefix="office-pdf-") as tmp:
|
||
tmp_dir = Path(tmp)
|
||
profile_uri = (tmp_dir / "profile").resolve().as_uri()
|
||
cmd = [
|
||
soffice,
|
||
"--headless",
|
||
"--norestore",
|
||
"--nolockcheck",
|
||
"--nodefault",
|
||
f"-env:UserInstallation={profile_uri}",
|
||
"--convert-to",
|
||
"pdf",
|
||
"--outdir",
|
||
str(tmp_dir),
|
||
str(src),
|
||
]
|
||
proc = subprocess.run(
|
||
cmd,
|
||
capture_output=True,
|
||
timeout=_DEFAULT_TIMEOUT,
|
||
check=False,
|
||
)
|
||
converted = tmp_dir / f"{src.stem}.pdf"
|
||
if proc.returncode != 0 or not converted.is_file() or converted.stat().st_size == 0:
|
||
detail = (proc.stderr or proc.stdout or b"").decode("utf-8", "replace")[-500:]
|
||
return f"[Error] LibreOffice conversion failed (rc={proc.returncode}): {detail}"
|
||
|
||
staged = out.with_name(f".{out.name}.{uuid4().hex}.tmp")
|
||
try:
|
||
shutil.copyfile(converted, staged)
|
||
staged.replace(out)
|
||
finally:
|
||
staged.unlink(missing_ok=True)
|
||
except subprocess.TimeoutExpired:
|
||
return f"[Error] LibreOffice conversion timed out after {_DEFAULT_TIMEOUT}s: {source}"
|
||
except OSError as e:
|
||
return f"[Error] failed to publish PDF: {type(e).__name__}: {e}"
|
||
|
||
return f"[OK] PDF created: {self._display(out)} ({out.stat().st_size} bytes)"
|