Files
govoplan-files/src/govoplan_files/backend/routes/uploads.py
T
zemion ff84812f7f
Module Package Release / publish-packages (push) Successful in 12s
Release govoplan-files v0.1.26: speed archive workflows and unify file tools
2026-09-08 01:32:41 +02:00

565 lines
23 KiB
Python

from __future__ import annotations
import hashlib
import hmac
import json
from contextlib import ExitStack, contextmanager
from datetime import UTC, datetime, timedelta
from pathlib import Path
from typing import Literal
from fastapi import APIRouter, Depends, File as FastAPIFile, Form, HTTPException, UploadFile
from sqlalchemy.orm import Session
from govoplan_core.auth import ApiPrincipal, require_scope
from govoplan_core.security.secrets import (
TransientPayloadError,
open_transient_payload,
seal_transient_payload,
)
from govoplan_files.backend.schemas import (
ArchiveEntryResponse,
ArchivePreviewResponse,
ConflictResolutionRequest,
FileUploadResponse,
_conflict_resolutions,
)
from govoplan_files.backend.db.models import FileAsset
from govoplan_core.db.session import get_session
from govoplan_files.backend.runtime import settings
from govoplan_files.backend.archive_work import (
ArchiveProgress, ArchiveWorkExpired, discard_staged_upload, read_progress,
stage_upload, use_staged_upload,
)
from govoplan_files.backend.storage.paths import (
UnsafeFilePathError,
normalize_folder,
)
from govoplan_files.backend.storage.archives import (
archive_format_for_filename,
extract_archive_upload,
extract_zip_upload,
inspect_archive,
)
from govoplan_files.backend.storage.common import FileStorageError
from govoplan_files.backend.storage.connector_policy import (
ConnectorPolicyDenied,
)
from govoplan_files.backend.storage.files import (
create_file_asset,
)
from govoplan_files.backend.route_support import (
_asset_list_response,
_audit_connector_imports,
_cleanup_temp_file,
_connector_policy_error,
_enforce_connector_policy,
_http_error,
_is_admin,
_read_limited_upload,
_source_metadata_from_form,
_spool_limited_upload_to_temp,
)
router = APIRouter(prefix="/files", tags=["files"])
_ARCHIVE_PREVIEW_PURPOSE = "files.archive-preview.v1"
@contextmanager
def _archive_source(file, staged_upload_id, preview_token, principal):
if isinstance(staged_upload_id, str):
if file is not None and hasattr(file, "file"):
raise FileStorageError("Choose either the staged archive or a new upload")
if not isinstance(preview_token, str) or not preview_token:
raise FileStorageError("A valid preview token is required for a staged archive")
payload = open_transient_payload(preview_token, ttl_seconds=settings.file_archive_preview_ttl_seconds)
expected = {"purpose": _ARCHIVE_PREVIEW_PURPOSE, "tenant_id": principal.tenant_id,
"user_id": principal.user.id, "staged_upload_id": staged_upload_id}
if any(payload.get(key) != value for key, value in expected.items()) or not isinstance(payload.get("filename"), str):
raise FileStorageError("Archive preview does not match this staged upload")
with use_staged_upload(settings, staged_upload_id, tenant_id=principal.tenant_id, user_id=principal.user.id) as path:
token_digest = payload.get("archive_sha256")
if not isinstance(token_digest, str) or not hmac.compare_digest(_archive_sha256(path), token_digest):
raise FileStorageError("Archive contents changed after preview; preview it again")
yield path, payload["filename"]
return
if file is None or not hasattr(file, "file"):
raise FileStorageError("Select an archive to upload")
filename = file.filename or "archive"
path = _spool_limited_upload_to_temp(file, max_bytes=settings.file_upload_zip_max_bytes, suffix=_archive_suffix(filename))
try:
yield path, filename
finally:
try:
_cleanup_temp_file(path)
except OSError:
pass
@router.get("/archive-progress/{operation_id}")
async def archive_operation_progress(operation_id: str, principal: ApiPrincipal = Depends(require_scope("files:file:upload"))):
# Small local receipt read stays available even while sync upload workers
# are busy. The request owns the transaction; this is not a job retry API.
try:
return read_progress(settings, operation_id, tenant_id=principal.tenant_id, user_id=principal.user.id)
except ArchiveWorkExpired as exc:
raise HTTPException(status_code=404, detail=str(exc)) from exc
except FileStorageError as exc:
raise _http_error(exc) from exc
@router.delete("/archive-staging/{stage_id}", status_code=204)
def release_staged_archive(stage_id: str, principal: ApiPrincipal = Depends(require_scope("files:file:upload"))):
try:
discard_staged_upload(settings, stage_id, tenant_id=principal.tenant_id, user_id=principal.user.id)
except FileStorageError as exc:
raise _http_error(exc) from exc
def _archive_suffix(filename: str) -> str:
lowered = filename.casefold()
for suffix in (".tar.bz2", ".tar.gz", ".tar.xz", ".tbz2", ".tgz", ".txz", ".tar", ".zip"):
if lowered.endswith(suffix):
return suffix
return ".archive"
def _archive_sha256(path: str) -> str:
digest = hashlib.sha256()
with open(path, "rb") as source:
while chunk := source.read(1024 * 1024):
digest.update(chunk)
return digest.hexdigest()
def _archive_selected_paths(value: str) -> list[str]:
parsed = json.loads(value)
if not isinstance(parsed, list) or not parsed:
raise FileStorageError("Select at least one archive file or folder")
if len(parsed) > settings.file_archive_max_entries:
raise FileStorageError(
"Archive selection exceeds the configured entry limit"
)
selected: list[str] = []
for item in parsed:
if not isinstance(item, str) or not item.strip():
raise FileStorageError("Archive selection contains an invalid path")
if len(item) > 4096:
raise FileStorageError("Archive selection path is too long")
selected.append(item)
return selected
def _validate_archive_preview_token(
token: str,
*,
tenant_id: str,
user_id: str,
owner_type: str,
owner_id: str,
path: str,
campaign_id: str | None,
archive_format: str,
archive_sha256: str,
) -> None:
payload = open_transient_payload(
token,
ttl_seconds=settings.file_archive_preview_ttl_seconds,
)
expected = {
"purpose": _ARCHIVE_PREVIEW_PURPOSE,
"tenant_id": tenant_id,
"user_id": user_id,
"owner_type": owner_type,
"owner_id": owner_id,
"path": path,
"campaign_id": campaign_id or "",
"archive_format": archive_format,
}
if any(payload.get(key) != value for key, value in expected.items()):
raise FileStorageError(
"Archive preview does not match this upload destination"
)
token_digest = payload.get("archive_sha256")
if not isinstance(token_digest, str) or not hmac.compare_digest(
token_digest, archive_sha256
):
raise FileStorageError(
"Archive contents changed after preview; preview it again"
)
@router.post("/archive-preview", response_model=ArchivePreviewResponse)
def preview_archive_upload(
file: UploadFile | None = FastAPIFile(default=None),
owner_type: Literal["user", "group"] = Form(default="user"),
owner_id: str | None = Form(default=None),
path: str = Form(default=""),
campaign_id: str | None = Form(default=None),
password: str | None = Form(default=None),
retain_upload: bool = Form(default=False),
staged_upload_id: str | None = Form(default=None),
preview_token: str | None = Form(default=None),
principal: ApiPrincipal = Depends(require_scope("files:file:upload")),
):
target_owner = owner_id or principal.user.id
sources = ExitStack()
try:
archive_path, filename = sources.enter_context(_archive_source(file, staged_upload_id, preview_token, principal))
archive_format = archive_format_for_filename(filename)
inspection = inspect_archive(
archive_path,
filename=filename,
password=password,
max_entries=settings.file_archive_max_entries,
max_expanded_bytes=settings.file_archive_max_expanded_bytes,
max_expansion_ratio=settings.file_archive_max_expansion_ratio,
)
digest = _archive_sha256(archive_path)
normalized_path = normalize_folder(path)
stage_id = staged_upload_id if isinstance(staged_upload_id, str) else None
if retain_upload is True and stage_id is None:
stage_id = stage_upload(settings, archive_path, tenant_id=principal.tenant_id, user_id=principal.user.id)
preview_token = seal_transient_payload(
{
"purpose": _ARCHIVE_PREVIEW_PURPOSE,
"tenant_id": principal.tenant_id,
"user_id": principal.user.id,
"owner_type": owner_type,
"owner_id": target_owner,
"path": normalized_path,
"campaign_id": campaign_id or "",
"archive_format": archive_format,
"archive_sha256": digest,
**({"staged_upload_id": stage_id, "filename": filename} if stage_id else {}),
}
)
expires_at = datetime.now(UTC) + timedelta(
seconds=settings.file_archive_preview_ttl_seconds
)
if isinstance(staged_upload_id, str):
# Repreviewing (for example with a password) does not renew the
# underlying private stage's lifetime.
expires_at = min(expires_at, datetime.fromtimestamp(
Path(archive_path).stat().st_mtime, UTC
) + timedelta(seconds=settings.file_archive_preview_ttl_seconds))
return ArchivePreviewResponse(
preview_token=preview_token,
staged_upload_id=stage_id,
archive_format=inspection.archive_format,
entries=[
ArchiveEntryResponse(
path=entry.path,
kind=entry.kind,
size_bytes=entry.size_bytes,
compressed_size_bytes=entry.compressed_size_bytes,
encrypted=entry.encrypted,
)
for entry in inspection.entries
],
file_count=inspection.file_count,
directory_count=inspection.directory_count,
expanded_size_bytes=inspection.expanded_size_bytes,
compressed_size_bytes=inspection.compressed_size_bytes,
requires_password=inspection.requires_password,
password_verified=inspection.password_verified,
expires_at=expires_at.isoformat(),
)
except ArchiveWorkExpired as exc:
raise HTTPException(status_code=410, detail=str(exc)) from exc
except (FileStorageError, TransientPayloadError, UnsafeFilePathError, ValueError) as exc:
raise _http_error(exc) from exc
finally:
sources.close()
@router.post("/archive-confirm", response_model=FileUploadResponse)
def confirm_archive_upload(
file: UploadFile | None = FastAPIFile(default=None),
preview_token: str = Form(...),
selected_paths_json: str = Form(...),
owner_type: Literal["user", "group"] = Form(default="user"),
owner_id: str | None = Form(default=None),
path: str = Form(default=""),
campaign_id: str | None = Form(default=None),
password: str | None = Form(default=None),
conflict_strategy: Literal["reject", "overwrite", "rename"] = Form(
default="reject"
),
conflict_resolutions_json: str | None = Form(default=None),
source_provenance_json: str | None = Form(default=None),
source_revision: str | None = Form(default=None),
connector_policy_json: str | None = Form(default=None),
encryption_vault_id: str | None = Form(default=None),
staged_upload_id: str | None = Form(default=None),
operation_id: str | None = Form(default=None),
session: Session = Depends(get_session),
principal: ApiPrincipal = Depends(require_scope("files:file:upload")),
):
target_owner = owner_id or principal.user.id
sources = ExitStack()
progress = None
committed = False
try:
archive_path, filename = sources.enter_context(_archive_source(file, staged_upload_id, preview_token, principal))
raw_resolutions = (
json.loads(conflict_resolutions_json)
if conflict_resolutions_json
else []
)
upload_resolutions = _conflict_resolutions(
[ConflictResolutionRequest(**item) for item in raw_resolutions]
)
selected_paths = _archive_selected_paths(selected_paths_json)
_enforce_connector_policy(
source_provenance_json,
connector_policy_json,
operation="import",
)
metadata = _source_metadata_from_form(
source_provenance_json, source_revision
)
archive_format = archive_format_for_filename(filename)
normalized_path = normalize_folder(path)
digest = _archive_sha256(archive_path)
_validate_archive_preview_token(
preview_token,
tenant_id=principal.tenant_id,
user_id=principal.user.id,
owner_type=owner_type,
owner_id=target_owner,
path=normalized_path,
campaign_id=campaign_id,
archive_format=archive_format,
archive_sha256=digest,
)
progress = ArchiveProgress(settings, operation_id, tenant_id=principal.tenant_id, user_id=principal.user.id)
extracted = extract_archive_upload(
session,
tenant_id=principal.tenant_id,
owner_type=owner_type,
owner_id=target_owner,
user_id=principal.user.id,
archive_data=archive_path,
filename=filename,
folder=normalized_path,
campaign_id=campaign_id,
selected_paths=selected_paths,
password=password,
conflict_strategy=conflict_strategy,
conflict_resolutions=upload_resolutions,
metadata=metadata,
is_admin=_is_admin(principal),
encryption_vault_id=encryption_vault_id,
max_entries=settings.file_archive_max_entries,
max_file_bytes=settings.file_upload_max_bytes,
max_expanded_bytes=settings.file_archive_max_expanded_bytes,
max_expansion_ratio=settings.file_archive_max_expansion_ratio,
progress=progress,
)
uploaded_assets = [item.asset for item in extracted]
_audit_connector_imports(session, principal, uploaded_assets)
progress("finalizing", len(extracted), len(extracted), progress.value["completed_bytes"], progress.value["total_bytes"])
session.flush()
response = FileUploadResponse(files=_asset_list_response(session, uploaded_assets, include_shares=True))
session.commit()
committed = True
progress.finish(True)
return response
except ArchiveWorkExpired as exc:
session.rollback()
raise HTTPException(status_code=410, detail=str(exc)) from exc
except ConnectorPolicyDenied as exc:
session.rollback()
raise _connector_policy_error(exc) from exc
except (
FileStorageError,
TransientPayloadError,
UnsafeFilePathError,
ValueError,
json.JSONDecodeError,
) as exc:
session.rollback()
raise _http_error(exc) from exc
except Exception:
session.rollback()
raise
finally:
if progress and not committed:
progress.finish(False)
try:
sources.close()
except OSError:
pass
if committed and isinstance(staged_upload_id, str):
try:
discard_staged_upload(settings, staged_upload_id, tenant_id=principal.tenant_id, user_id=principal.user.id)
except (OSError, FileStorageError):
pass
@router.post("/upload", response_model=FileUploadResponse)
def upload_files(
files: list[UploadFile] = FastAPIFile(...),
owner_type: Literal["user", "group"] = Form(default="user"),
owner_id: str | None = Form(default=None),
path: str = Form(default=""),
campaign_id: str | None = Form(default=None),
unpack_zip: bool = Form(default=False),
conflict_strategy: Literal["reject", "overwrite", "rename"] = Form(
default="reject"
),
conflict_resolutions_json: str | None = Form(default=None),
source_provenance_json: str | None = Form(default=None),
source_revision: str | None = Form(default=None),
connector_policy_json: str | None = Form(default=None),
encryption_vault_id: str | None = Form(default=None),
session: Session = Depends(get_session),
principal: ApiPrincipal = Depends(require_scope("files:file:upload")),
):
target_owner = owner_id or principal.user.id
uploaded_assets: list[FileAsset] = []
try:
raw_resolutions = (
json.loads(conflict_resolutions_json) if conflict_resolutions_json else []
)
upload_resolutions = _conflict_resolutions(
[ConflictResolutionRequest(**item) for item in raw_resolutions]
)
_enforce_connector_policy(
source_provenance_json, connector_policy_json, operation="import"
)
metadata = _source_metadata_from_form(source_provenance_json, source_revision)
for upload in files:
filename = upload.filename or "file"
content_type = upload.content_type or None
upload_limit = (
settings.file_upload_zip_max_bytes
if unpack_zip and filename.lower().endswith(".zip")
else settings.file_upload_max_bytes
)
if unpack_zip and filename.lower().endswith(".zip"):
zip_path = _spool_limited_upload_to_temp(
upload, max_bytes=upload_limit, suffix=".zip"
)
try:
extracted = extract_zip_upload(
session,
tenant_id=principal.tenant_id,
owner_type=owner_type,
owner_id=target_owner,
user_id=principal.user.id,
zip_data=zip_path,
folder=path,
campaign_id=campaign_id,
conflict_strategy=conflict_strategy,
conflict_resolutions=upload_resolutions,
metadata=metadata,
is_admin=_is_admin(principal),
encryption_vault_id=encryption_vault_id,
max_file_bytes=settings.file_upload_max_bytes,
max_total_bytes=settings.file_upload_zip_max_bytes,
)
finally:
_cleanup_temp_file(zip_path)
uploaded_assets.extend(item.asset for item in extracted)
continue
data = _read_limited_upload(upload, max_bytes=upload_limit)
stored = create_file_asset(
session,
tenant_id=principal.tenant_id,
owner_type=owner_type,
owner_id=target_owner,
user_id=principal.user.id,
filename=filename,
data=data,
folder=path,
content_type=content_type,
campaign_id=campaign_id,
conflict_strategy=conflict_strategy,
conflict_resolutions=upload_resolutions,
metadata=metadata,
is_admin=_is_admin(principal),
encryption_vault_id=encryption_vault_id,
)
uploaded_assets.append(stored.asset)
_audit_connector_imports(session, principal, uploaded_assets)
session.flush()
response = FileUploadResponse(files=_asset_list_response(session, uploaded_assets, include_shares=True))
session.commit()
except ConnectorPolicyDenied as exc:
session.rollback()
raise _connector_policy_error(exc) from exc
except (FileStorageError, UnsafeFilePathError, ValueError) as exc:
session.rollback()
raise _http_error(exc) from exc
return response
@router.post("/upload-zip", response_model=FileUploadResponse)
def upload_zip(
file: UploadFile = FastAPIFile(...),
owner_type: Literal["user", "group"] = Form(default="user"),
owner_id: str | None = Form(default=None),
path: str = Form(default=""),
campaign_id: str | None = Form(default=None),
conflict_strategy: Literal["reject", "overwrite", "rename"] = Form(
default="reject"
),
conflict_resolutions_json: str | None = Form(default=None),
source_provenance_json: str | None = Form(default=None),
source_revision: str | None = Form(default=None),
connector_policy_json: str | None = Form(default=None),
encryption_vault_id: str | None = Form(default=None),
session: Session = Depends(get_session),
principal: ApiPrincipal = Depends(require_scope("files:file:upload")),
):
target_owner = owner_id or principal.user.id
zip_path: str | None = None
try:
raw_resolutions = (
json.loads(conflict_resolutions_json) if conflict_resolutions_json else []
)
upload_resolutions = _conflict_resolutions(
[ConflictResolutionRequest(**item) for item in raw_resolutions]
)
_enforce_connector_policy(
source_provenance_json, connector_policy_json, operation="import"
)
metadata = _source_metadata_from_form(source_provenance_json, source_revision)
zip_path = _spool_limited_upload_to_temp(
file, max_bytes=settings.file_upload_zip_max_bytes, suffix=".zip"
)
extracted = extract_zip_upload(
session,
tenant_id=principal.tenant_id,
owner_type=owner_type,
owner_id=target_owner,
user_id=principal.user.id,
zip_data=zip_path,
folder=path,
campaign_id=campaign_id,
conflict_strategy=conflict_strategy,
conflict_resolutions=upload_resolutions,
metadata=metadata,
is_admin=_is_admin(principal),
encryption_vault_id=encryption_vault_id,
max_file_bytes=settings.file_upload_max_bytes,
max_total_bytes=settings.file_upload_zip_max_bytes,
)
_audit_connector_imports(session, principal, [item.asset for item in extracted])
session.flush()
response = FileUploadResponse(files=_asset_list_response(session, [item.asset for item in extracted], include_shares=True))
session.commit()
except ConnectorPolicyDenied as exc:
session.rollback()
raise _connector_policy_error(exc) from exc
except (FileStorageError, UnsafeFilePathError, ValueError) as exc:
session.rollback()
raise _http_error(exc) from exc
finally:
if zip_path:
_cleanup_temp_file(zip_path)
return response