mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-09-29 01:41:38 +00:00
a4efc0f776
* fix(bm25_index): 修正BM25索引计算中的文档长度归一化问题 修复了在计算BM25相似度时对文档长度进行不正确归一化的bug，确保所有查询都能得到准确的相关性评分。 * up * up * up * up * up * up * up * up * up * up * up * up * up * up * up * up * up * refactor(steps): Rename and adjust indexing step logic - Rename `scan_changes.py` and `reindex.py` to `clear_and_scan.py` - Update implementation details of `ScanChangesStep` and `ClearAndScanStep` - Modify the scheduling mechanism in `WatchChangesStep` - Adjust step registration and parameter configuration in config files - Update related tests to align with the new interface changes * up * feat(daily): replace daily CRUD operations with slug provisioning approach * refactor(tests): migrate CRUD step tests from HTTP server to direct LocalFileStore * up * up * up * up --------- Co-authored-by: huangsen <huangsen.huang@alibaba-inc.com>
84 lines
3.1 KiB
Python
84 lines
3.1 KiB
Python
"""``file_download`` — copy a file out of the vault to a local path.
|
|
|
|
Symmetric counterpart to ``file_upload``: source is under the vault,
|
|
target is on the local filesystem.
|
|
|
|
``src_path`` is a path relative to the vault (the file to copy out).
|
|
Returns ``error="not found"`` when the file isn't on disk.
|
|
|
|
``dst_path`` (filesystem target) is an absolute path on the host
|
|
filesystem. **Optional** — when empty, the file lands in a
|
|
session-scoped temp dir (lazy, auto-cleaned on process exit; each
|
|
call gets its own subdirectory so concurrent agents don't trample
|
|
each other) and the realized path is returned in ``dst_path``.
|
|
``overwrite`` defaults to False — callers must opt in to clobber an
|
|
existing destination.
|
|
"""
|
|
|
|
import mimetypes
|
|
import shutil
|
|
import tempfile
|
|
from pathlib import Path
|
|
|
|
from ..base_step import BaseStep
|
|
|
|
from ...components import R
|
|
|
|
|
|
_TEMP_ROOT: Path | None = None
|
|
|
|
|
|
def _get_temp_root() -> Path:
|
|
"""Lazy session-scoped temp dir. Auto-cleaned on process exit."""
|
|
global _TEMP_ROOT
|
|
if _TEMP_ROOT is None:
|
|
_TEMP_ROOT = Path(tempfile.mkdtemp(prefix="reme-files-"))
|
|
return _TEMP_ROOT
|
|
|
|
|
|
@R.register("download_step")
|
|
class DownloadStep(BaseStep):
|
|
"""Copy ``src_path`` (under the vault) to ``dst_path`` (or a temp file if omitted)."""
|
|
|
|
async def execute(self):
|
|
assert self.context is not None
|
|
src_path: str = self.context.get("src_path", "") or ""
|
|
dst_path: str = self.context.get("dst_path", "") or ""
|
|
overwrite: bool = bool(self.context.get("overwrite", False))
|
|
assert src_path, "src_path is required"
|
|
payload = await self._download(src_path, dst_path, overwrite)
|
|
if "error" in payload:
|
|
self.context.response.success = False
|
|
self.context.response.answer = f"Error: {payload['error']}"
|
|
else:
|
|
self.context.response.success = True
|
|
self.context.response.answer = f"Downloaded {src_path} → {payload['dst_path']} ({payload['size']} bytes)"
|
|
self.context.response.metadata.update(payload)
|
|
|
|
async def _download(self, src_path: str, dst_path: str, overwrite: bool) -> dict:
|
|
if not src_path:
|
|
return {"src_path": src_path, "error": "not found"}
|
|
src_abs = (Path(self.file_store.vault_path or ".") / src_path).resolve()
|
|
if not src_abs.is_file():
|
|
return {"src_path": src_path, "error": "not found"}
|
|
|
|
if dst_path:
|
|
dst_abs = Path(dst_path)
|
|
if dst_abs.exists() and not overwrite:
|
|
return {
|
|
"src_path": src_path,
|
|
"dst_path": dst_path,
|
|
"error": "destination exists; pass overwrite=True",
|
|
}
|
|
dst_abs.parent.mkdir(parents=True, exist_ok=True)
|
|
else:
|
|
dst_dir = Path(tempfile.mkdtemp(prefix="dl-", dir=_get_temp_root()))
|
|
dst_abs = dst_dir / src_abs.name
|
|
|
|
shutil.copy2(src_abs, dst_abs)
|
|
return {
|
|
"src_path": src_path,
|
|
"dst_path": str(dst_abs),
|
|
"size": dst_abs.stat().st_size,
|
|
"mime": mimetypes.guess_type(dst_abs.name)[0] or "application/octet-stream",
|
|
}
|