feat: 平台治理与对象存储增强,审批中心与运行日志整合
- 新增 storage/policy.py 落盘策略:按大小/类型决定文件存 MinIO 或内联数据库 - 数据处理源文件与生成结果写入 MinIO 并登记 storage_objects,支持失败回滚 - 算力节点训练产物按版本归档到 MinIO,登记 model_artifacts - 数据转换任务输入输出对象化,支持从 MinIO 读写 - 新增审批中心(申请/我的/策略)、组织与权限、运行日志整合页面 - schema 与 docker 配置、前端路由侧边栏、治理文档同步更新 Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -1,4 +1,4 @@
|
||||
"""数据处理原始源文件的受控本地对象存储。"""
|
||||
"""数据处理源文件的受控暂存与分层对象存储。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -13,6 +13,9 @@ from pathlib import Path, PurePosixPath
|
||||
from typing import Iterable, Iterator
|
||||
from urllib.parse import quote, unquote, urlsplit
|
||||
|
||||
from app.core.config import get_settings
|
||||
from app.modules.storage.minio_store import get_object_storage
|
||||
|
||||
|
||||
class DataProcessStorageError(ValueError):
|
||||
"""本地对象引用或文件系统状态不安全。"""
|
||||
@@ -68,7 +71,7 @@ def _safe_basename(value: str) -> str:
|
||||
|
||||
|
||||
class LocalDataProcessStorage:
|
||||
"""只允许访问配置根目录下的版本化原始文件。"""
|
||||
"""Stage locally, but publish and read authoritative source files from MinIO."""
|
||||
|
||||
def __init__(self, root: str | os.PathLike[str] | Path | None = None) -> None:
|
||||
configured = Path(root) if root is not None else _configured_storage_root()
|
||||
@@ -132,10 +135,7 @@ class LocalDataProcessStorage:
|
||||
f"v{version}",
|
||||
basename,
|
||||
)
|
||||
reference = (
|
||||
"local://data-process/"
|
||||
f"{task_id}/{source_file_id}/v{version}/{quote(basename, safe='')}"
|
||||
)
|
||||
reference = self._reference(task_id, source_file_id, version, basename)
|
||||
staged = StagedSourceObject(reference, temporary_path, relative_path)
|
||||
self._issued_staged_objects[temporary_path] = staged
|
||||
return staged
|
||||
@@ -168,6 +168,18 @@ class LocalDataProcessStorage:
|
||||
expected_task_id=expected_source_task_id,
|
||||
expected_source_file_id=expected_source_file_id,
|
||||
)
|
||||
if self._is_minio_reference(source_reference):
|
||||
content = self.read(source_reference)
|
||||
if content is None:
|
||||
raise DataProcessStorageError("original source object is not available")
|
||||
return self.stage_bytes(
|
||||
batch_id=batch_id,
|
||||
task_id=task_id,
|
||||
source_file_id=source_file_id,
|
||||
version=version,
|
||||
name=basename,
|
||||
content=content,
|
||||
)
|
||||
descriptor, source_info = self._open_read_descriptor(source_relative)
|
||||
os.close(descriptor)
|
||||
|
||||
@@ -193,10 +205,7 @@ class LocalDataProcessStorage:
|
||||
f"v{version}",
|
||||
basename,
|
||||
)
|
||||
reference = (
|
||||
"local://data-process/"
|
||||
f"{task_id}/{source_file_id}/v{version}/{quote(basename, safe='')}"
|
||||
)
|
||||
reference = self._reference(task_id, source_file_id, version, basename)
|
||||
staged = StagedSourceObject(reference, temporary_path, relative_path)
|
||||
self._issued_staged_objects[temporary_path] = staged
|
||||
return staged
|
||||
@@ -212,14 +221,22 @@ class LocalDataProcessStorage:
|
||||
raise DataProcessStorageError("duplicate staged source object")
|
||||
seen_temporary_paths.add(item._temporary_path)
|
||||
for item in staged:
|
||||
final_path = self._path_for_relative(item._relative_path)
|
||||
self._ensure_directory(final_path.parent)
|
||||
if final_path.exists() or final_path.is_symlink():
|
||||
raise DataProcessStorageError("source storage object already exists")
|
||||
os.link(item._temporary_path, final_path, follow_symlinks=False)
|
||||
if self._is_minio_reference(item.reference):
|
||||
content = item._temporary_path.read_bytes()
|
||||
get_object_storage().put_bytes(
|
||||
self.object_key(item.reference),
|
||||
content,
|
||||
"application/octet-stream",
|
||||
)
|
||||
elif not item.reference.startswith("db://data-process/"):
|
||||
final_path = self._path_for_relative(item._relative_path)
|
||||
self._ensure_directory(final_path.parent)
|
||||
if final_path.exists() or final_path.is_symlink():
|
||||
raise DataProcessStorageError("source storage object already exists")
|
||||
os.link(item._temporary_path, final_path, follow_symlinks=False)
|
||||
self._fsync_directory(final_path.parent)
|
||||
published.append(item)
|
||||
item._temporary_path.unlink()
|
||||
self._fsync_directory(final_path.parent)
|
||||
except Exception:
|
||||
for item in reversed(published):
|
||||
try:
|
||||
@@ -258,7 +275,13 @@ class LocalDataProcessStorage:
|
||||
raise first_error
|
||||
|
||||
def read(self, reference: str) -> bytes | None:
|
||||
"""读取 local 引用;旧 ``db://`` 对象返回 ``None`` 由数据库正文兜底。"""
|
||||
"""Read a MinIO object or legacy local reference."""
|
||||
|
||||
if self._is_minio_reference(reference):
|
||||
try:
|
||||
return get_object_storage().get_bytes(self.object_key(reference))
|
||||
except Exception as exc: # noqa: BLE001 - normalize object-not-found for callers
|
||||
raise DataProcessStorageError("source storage object does not exist") from exc
|
||||
|
||||
relative_path = self._relative_from_reference(reference)
|
||||
if relative_path is None:
|
||||
@@ -276,6 +299,11 @@ class LocalDataProcessStorage:
|
||||
) -> int | None:
|
||||
"""返回受控 local 对象大小;旧 ``db://`` 对象没有原始文件。"""
|
||||
|
||||
if self._is_minio_reference(reference):
|
||||
try:
|
||||
return int(get_object_storage().stat(self.object_key(reference)).get("byte_size") or 0)
|
||||
except Exception as exc: # noqa: BLE001
|
||||
raise DataProcessStorageError("source storage object does not exist") from exc
|
||||
relative_path = self._relative_from_reference(reference)
|
||||
if relative_path is None:
|
||||
return None
|
||||
@@ -301,6 +329,15 @@ class LocalDataProcessStorage:
|
||||
) -> Iterator[bytes]:
|
||||
"""按范围流式读取原始文件,避免 PDF 预览把大文件整体载入内存。"""
|
||||
|
||||
if self._is_minio_reference(reference):
|
||||
content = self.read(reference) or b""
|
||||
if start < 0 or expected_size != len(content) or start > expected_size:
|
||||
raise DataProcessStorageError("source object size does not match metadata")
|
||||
remaining = expected_size - start if length is None else length
|
||||
if remaining < 0 or start + remaining > expected_size:
|
||||
raise DataProcessStorageError("invalid source byte range")
|
||||
yield content[start : start + remaining]
|
||||
return
|
||||
relative_path = self._relative_from_reference(reference)
|
||||
if relative_path is None:
|
||||
raise DataProcessStorageError("original source object is not available")
|
||||
@@ -337,6 +374,12 @@ class LocalDataProcessStorage:
|
||||
) -> bool:
|
||||
"""校验 local 引用归属;旧 ``db://`` 引用无需文件系统处理。"""
|
||||
|
||||
if self._is_minio_reference(reference):
|
||||
self._assert_minio_owner(reference, expected_task_id, expected_source_file_id)
|
||||
return True
|
||||
if str(reference or "").startswith("db://data-process/"):
|
||||
self._assert_database_owner(reference, expected_task_id, expected_source_file_id)
|
||||
return True
|
||||
relative_path = self._relative_from_reference(reference)
|
||||
if relative_path is None:
|
||||
return False
|
||||
@@ -382,6 +425,19 @@ class LocalDataProcessStorage:
|
||||
) -> bool:
|
||||
"""删除受控 local 对象;旧 ``db://`` 引用保持不变。"""
|
||||
|
||||
if self._is_minio_reference(reference):
|
||||
if (expected_task_id is None) != (expected_source_file_id is None):
|
||||
raise DataProcessStorageError("both expected storage owner fields are required")
|
||||
if expected_task_id is not None and expected_source_file_id is not None:
|
||||
self._assert_minio_owner(reference, expected_task_id, expected_source_file_id)
|
||||
get_object_storage().delete(self.object_key(reference))
|
||||
return True
|
||||
if str(reference or "").startswith("db://data-process/"):
|
||||
if (expected_task_id is None) != (expected_source_file_id is None):
|
||||
raise DataProcessStorageError("both expected storage owner fields are required")
|
||||
if expected_task_id is not None and expected_source_file_id is not None:
|
||||
self._assert_database_owner(reference, expected_task_id, expected_source_file_id)
|
||||
return False
|
||||
relative_path = self._relative_from_reference(reference)
|
||||
if relative_path is None:
|
||||
return False
|
||||
@@ -426,7 +482,7 @@ class LocalDataProcessStorage:
|
||||
if reference.startswith("db://"):
|
||||
return None
|
||||
parsed = urlsplit(reference)
|
||||
if parsed.scheme != "local" or parsed.netloc != "data-process":
|
||||
if parsed.scheme not in {"local", "minio"} or parsed.netloc != "data-process":
|
||||
raise DataProcessStorageError("unsupported source storage reference")
|
||||
if parsed.query or parsed.fragment or "\\" in parsed.path:
|
||||
raise DataProcessStorageError("unsafe source storage reference")
|
||||
@@ -460,6 +516,39 @@ class LocalDataProcessStorage:
|
||||
basename = _safe_basename(decoded[3])
|
||||
return PurePosixPath(task_id, source_file_id, f"v{version}", basename)
|
||||
|
||||
@staticmethod
|
||||
def _is_minio_reference(reference: str) -> bool:
|
||||
return str(reference or "").startswith("minio://data-process/")
|
||||
|
||||
@staticmethod
|
||||
def _reference(task_id: str, source_file_id: str, version: int, basename: str) -> str:
|
||||
scheme = "minio" if get_settings().minio_enabled else "local"
|
||||
return f"{scheme}://data-process/{task_id}/{source_file_id}/v{version}/{quote(basename, safe='')}"
|
||||
|
||||
@staticmethod
|
||||
def object_key(reference: str) -> str:
|
||||
parsed = urlsplit(reference)
|
||||
if parsed.scheme != "minio" or parsed.netloc != "data-process":
|
||||
raise DataProcessStorageError("reference is not a MinIO source object")
|
||||
return "data-process/" + parsed.path.lstrip("/")
|
||||
|
||||
def _assert_minio_owner(self, reference: str, task_id: str, source_file_id: str) -> None:
|
||||
relative = self._relative_from_reference(reference)
|
||||
if relative is None:
|
||||
raise DataProcessStorageError("invalid MinIO source reference")
|
||||
self._assert_expected_owner(relative, expected_task_id=task_id, expected_source_file_id=source_file_id)
|
||||
|
||||
@staticmethod
|
||||
def _assert_database_owner(reference: str, task_id: str, source_file_id: str) -> None:
|
||||
parsed = urlsplit(reference)
|
||||
parts = parsed.path.lstrip("/").split("/")
|
||||
if parsed.netloc != "data-process" or len(parts) != 3:
|
||||
raise DataProcessStorageError("invalid database source reference")
|
||||
expected_task_id = _safe_component(task_id, "expected task id")
|
||||
expected_source_file_id = _safe_component(source_file_id, "expected source file id")
|
||||
if tuple(parts[:2]) != (expected_task_id, expected_source_file_id) or parts[2] != "v1":
|
||||
raise DataProcessStorageError("source storage object owner mismatch")
|
||||
|
||||
def _path_for_relative(self, relative_path: PurePosixPath) -> Path:
|
||||
if relative_path.is_absolute() or any(
|
||||
part in {"", ".", ".."} for part in relative_path.parts
|
||||
@@ -479,9 +568,22 @@ class LocalDataProcessStorage:
|
||||
raise DataProcessStorageError("invalid staged source object")
|
||||
if self._issued_staged_objects.get(item._temporary_path) is not item:
|
||||
raise DataProcessStorageError("staged source object was not issued by this storage")
|
||||
expected_relative = self._relative_from_reference(item.reference)
|
||||
if expected_relative is None or expected_relative != item._relative_path:
|
||||
raise DataProcessStorageError("staged source object reference mismatch")
|
||||
if item.reference.startswith("db://data-process/"):
|
||||
parsed = urlsplit(item.reference)
|
||||
parts = parsed.path.lstrip("/").split("/")
|
||||
expected = item._relative_path.parts[:3]
|
||||
if (
|
||||
parsed.netloc != "data-process"
|
||||
or parsed.query
|
||||
or parsed.fragment
|
||||
or len(parts) != 3
|
||||
or tuple(parts) != expected
|
||||
):
|
||||
raise DataProcessStorageError("staged source object reference mismatch")
|
||||
else:
|
||||
expected_relative = self._relative_from_reference(item.reference)
|
||||
if expected_relative is None or expected_relative != item._relative_path:
|
||||
raise DataProcessStorageError("staged source object reference mismatch")
|
||||
staging_root = self._root / ".staging"
|
||||
try:
|
||||
relative_temporary = item._temporary_path.relative_to(staging_root)
|
||||
|
||||
@@ -247,14 +247,19 @@ def _source_storage_descriptor(
|
||||
or f"db://data-process/{task_id}/{file_id}/v1"
|
||||
)
|
||||
expected_local_prefix = f"local://data-process/{task_id}/{file_id}/v1/"
|
||||
expected_minio_prefix = f"minio://data-process/{task_id}/{file_id}/v1/"
|
||||
expected_database_reference = f"db://data-process/{task_id}/{file_id}/v1"
|
||||
if storage_object_id.startswith(expected_local_prefix) and len(storage_object_id) > len(
|
||||
expected_local_prefix
|
||||
):
|
||||
storage_backend = "local"
|
||||
elif storage_object_id.startswith(expected_minio_prefix) and len(storage_object_id) > len(
|
||||
expected_minio_prefix
|
||||
):
|
||||
storage_backend = "minio"
|
||||
elif storage_object_id == expected_database_reference:
|
||||
storage_backend = "database"
|
||||
elif storage_object_id.startswith(("local://data-process/", "db://data-process/")):
|
||||
elif storage_object_id.startswith(("local://data-process/", "minio://data-process/", "db://data-process/")):
|
||||
raise DataProcessStoreError("source storage object owner mismatch")
|
||||
else:
|
||||
raise DataProcessStoreError("unsupported source storage object reference")
|
||||
|
||||
@@ -11,6 +11,7 @@ import psycopg
|
||||
|
||||
from app.core.config import get_settings
|
||||
from app.modules.storage.minio_store import get_object_storage
|
||||
from app.modules.storage.policy import should_store_in_minio
|
||||
|
||||
from .base import (
|
||||
StoreBase,
|
||||
@@ -168,7 +169,11 @@ class DatasetsMixin:
|
||||
split_name: assignments.count(split_name) for split_name in split_order
|
||||
}
|
||||
split_specs: list[dict[str, Any]] = []
|
||||
use_minio = bool(get_settings().minio_enabled)
|
||||
# Explicit local is retained for old callers/tests that request the
|
||||
# legacy backend; all normal platform requests default to MinIO.
|
||||
allow_minio = bool(get_settings().minio_enabled) and str(
|
||||
payload.get("storage_type") or "minio"
|
||||
).lower() != "local"
|
||||
for split_name in split_order:
|
||||
split_records = [
|
||||
(source_row, record)
|
||||
@@ -193,12 +198,15 @@ class DatasetsMixin:
|
||||
"storage_object_id": (
|
||||
f"db://data-process/{task_id}/{file_id}/v1"
|
||||
),
|
||||
"store_in_minio": allow_minio and should_store_in_minio(
|
||||
len(raw), content_type="application/jsonl", file_format="jsonl"
|
||||
),
|
||||
}
|
||||
)
|
||||
source_result_ids = [row["id"] for row in rows]
|
||||
common_metadata = {
|
||||
"source": "data_process",
|
||||
"storage_backend": "minio" if use_minio else "database",
|
||||
"storage_backend": "minio" if any(spec["store_in_minio"] for spec in split_specs) else "database",
|
||||
"source_task_id": task_id,
|
||||
"output_type": _task_output_type(task),
|
||||
"reasoning_detail": _task_reasoning_detail(task),
|
||||
@@ -273,7 +281,7 @@ class DatasetsMixin:
|
||||
split_name = str(spec["split"])
|
||||
dataset_id = dataset_ids[split_name]
|
||||
storage_object_id = str(spec["storage_object_id"])
|
||||
if use_minio:
|
||||
if spec["store_in_minio"]:
|
||||
file_name = f"{base_dataset_name}.{split_name}.jsonl"
|
||||
object_key = f"datasets/{dataset_id}/versions/{spec['version_id']}/{file_name}"
|
||||
uploaded = get_object_storage().put_bytes(
|
||||
@@ -356,7 +364,7 @@ class DatasetsMixin:
|
||||
(
|
||||
dataset_name,
|
||||
dataset_types[split_name],
|
||||
"minio" if use_minio else (payload.get("storage_type") or "local"),
|
||||
"minio" if spec["store_in_minio"] else "database",
|
||||
f"{len(spec['raw'])} B",
|
||||
len(spec["raw"]),
|
||||
len(spec["records"]),
|
||||
@@ -386,7 +394,7 @@ class DatasetsMixin:
|
||||
dataset_id,
|
||||
dataset_name,
|
||||
dataset_types[split_name],
|
||||
"minio" if use_minio else (payload.get("storage_type") or "local"),
|
||||
"minio" if spec["store_in_minio"] else "database",
|
||||
task_id,
|
||||
task_id,
|
||||
f"{len(spec['raw'])} B",
|
||||
@@ -405,7 +413,11 @@ class DatasetsMixin:
|
||||
),
|
||||
).fetchone()
|
||||
|
||||
file_metadata = {**dataset_metadata, "file_split": split_name}
|
||||
file_metadata = {
|
||||
**dataset_metadata,
|
||||
"file_split": split_name,
|
||||
"storage_backend": "minio" if spec["store_in_minio"] else "database",
|
||||
}
|
||||
version = {
|
||||
"id": spec["version_id"],
|
||||
"version_no": 1,
|
||||
|
||||
@@ -137,7 +137,7 @@ class SourceFilesMixin:
|
||||
payload["record_count"],
|
||||
payload["file_format"],
|
||||
payload["checksum_sha256"],
|
||||
payload["content"],
|
||||
"" if str(storage_object_id or "").startswith("minio://") else payload["content"],
|
||||
str(payload["content"])[:2000],
|
||||
json_dumps(metadata_payload),
|
||||
task.get("tenant_id"),
|
||||
@@ -223,7 +223,17 @@ class SourceFilesMixin:
|
||||
).fetchone()
|
||||
if not row:
|
||||
raise NotFoundError("source file not found")
|
||||
return _decode_row(row) or {}
|
||||
decoded = _decode_row(row) or {}
|
||||
# New source files keep only a preview in PostgreSQL. Load the
|
||||
# authoritative body from MinIO on demand for existing processing code.
|
||||
reference = str(decoded.get("storage_object_id") or "")
|
||||
if include_content and not decoded.get("content") and reference.startswith("minio://"):
|
||||
from app.modules.data_process.storage import get_data_process_storage
|
||||
|
||||
decoded["content"] = (get_data_process_storage().read(reference) or b"").decode(
|
||||
"utf-8", errors="replace"
|
||||
)
|
||||
return decoded
|
||||
|
||||
def source_content_window(
|
||||
self, task_id: str, file_id: str, offset: int, limit: int
|
||||
|
||||
Reference in New Issue
Block a user