diff options
Diffstat (limited to 'packages/meshbay-node/src/meshbay_node/uploads.py')
| -rw-r--r-- | packages/meshbay-node/src/meshbay_node/uploads.py | 33 |
1 files changed, 32 insertions, 1 deletions
diff --git a/packages/meshbay-node/src/meshbay_node/uploads.py b/packages/meshbay-node/src/meshbay_node/uploads.py index dd31e1e..c485e39 100644 --- a/packages/meshbay-node/src/meshbay_node/uploads.py +++ b/packages/meshbay-node/src/meshbay_node/uploads.py @@ -24,6 +24,8 @@ build first. from __future__ import annotations +import re +import secrets import time from collections.abc import Iterable from dataclasses import dataclass, field @@ -34,6 +36,26 @@ from pathlib import Path # recognise one, and a second spelling of it would be a bug nobody could see. PART_SUFFIX = ".part" + +def part_name(stored_name: str) -> str: + """The `.part` one upload writes: its final name, a tag of its own, `.part`. + + Its own, because the final name alone is shared: two uploads that settled + on one name — two groups hosting one folder, each with its own lock — + would write one file, the second truncating the first. + """ + return f"{stored_name}.{secrets.token_hex(4)}{PART_SUFFIX}" + + +# What `part_name` writes, and the only thing the reaper deletes. A `.part` +# without the node's tag is somebody else's — a browser's download in progress in +# a shared folder, a copy the operator is making — and is never touched. +_OWN_PART = re.compile(r"\.[0-9a-f]{8}" + re.escape(PART_SUFFIX) + r"$") + + +def is_own_part(path: Path) -> bool: + return bool(_OWN_PART.search(path.name)) + # How long a `.part` with no upload behind it is kept before it is deleted. # # Generous on purpose. The cost of waiting is disk; the cost of being wrong is @@ -107,6 +129,15 @@ class PartialUploads: def drop(self, user_id: str, rel_dir: str, filename: str) -> Partial | None: return self._by_key.pop((user_id, rel_dir, filename), None) + def reserved_names(self, rel_dir: str) -> set[str]: + """The final names uploads in flight into `rel_dir` will take. + + None of them exists on disk yet, so a name check that looked only at + the directory would hand the same name to a second upload. + """ + return {state.stored_name for (_u, d, _f), state in self._by_key.items() + if d == rel_dir} + def __len__(self) -> int: return len(self._by_key) @@ -145,7 +176,7 @@ def orphaned_parts(candidates: Iterable[tuple[Path, float]], """ doomed: list[Path] = [] for path, mtime in candidates: - if path.suffix != PART_SUFFIX: + if not is_own_part(path): continue if path in live: continue |