Files
ragflow/rag/utils/azure_spn_conn.py

124 lines
4.4 KiB
Python
Raw Normal View History

#
# Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import logging
import os
import time
from common.decorator import singleton
from azure.identity import ClientSecretCredential, AzureAuthorityHosts
from azure.storage.filedatalake import FileSystemClient
from common import settings
_CLOUD_AUTHORITY_MAP = {
"public": AzureAuthorityHosts.AZURE_PUBLIC_CLOUD,
"china": AzureAuthorityHosts.AZURE_CHINA,
"government": AzureAuthorityHosts.AZURE_GOVERNMENT,
"germany": AzureAuthorityHosts.AZURE_GERMANY,
}
@singleton
class RAGFlowAzureSpnBlob:
def __init__(self):
self.conn = None
self.account_url = os.getenv('ACCOUNT_URL', settings.AZURE["account_url"])
self.client_id = os.getenv('CLIENT_ID', settings.AZURE["client_id"])
self.secret = os.getenv('SECRET', settings.AZURE["secret"])
self.tenant_id = os.getenv('TENANT_ID', settings.AZURE["tenant_id"])
self.container_name = os.getenv('CONTAINER_NAME', settings.AZURE["container_name"])
self.cloud = os.getenv('AZURE_CLOUD', settings.AZURE.get("cloud", "public")).lower()
self.__open__()
def __open__(self):
try:
if self.conn:
self.__close__()
except Exception:
pass
try:
authority = _CLOUD_AUTHORITY_MAP.get(self.cloud, AzureAuthorityHosts.AZURE_PUBLIC_CLOUD)
credentials = ClientSecretCredential(tenant_id=self.tenant_id, client_id=self.client_id,
client_secret=self.secret, authority=authority)
self.conn = FileSystemClient(account_url=self.account_url, file_system_name=self.container_name,
credential=credentials)
except Exception:
logging.exception("Fail to connect %s" % self.account_url)
def __close__(self):
del self.conn
self.conn = None
def health(self):
_bucket, fnm, binary = "txtxtxtxt1", "txtxtxtxt1", b"_t@@@1"
f = self.conn.create_file(f"{_bucket}/{fnm}")
f.append_data(binary, offset=0, length=len(binary))
return f.flush_data(len(binary))
def put(self, bucket, fnm, binary, tenant_id=None):
fix: prepend bucket prefix to Azure SPN and SAS storage paths (#14185) ## Summary Fixes #14159 — files from different datasets can overwrite each other in Azure Blob storage. ## Problem Both `azure_spn_conn.py` and `azure_sas_conn.py` ignore the `bucket` parameter in all storage operations (`put`, `get`, `rm`, `obj_exist`, `get_presigned_url`). Files are stored flat using only the filename, so two datasets containing a file with the same name will overwrite each other. The MinIO and S3 implementations correctly use the bucket (typically the knowledge base ID) as a path prefix to create logical folder isolation: - MinIO: uses `use_prefix_path` decorator → `{orig_bucket}/{fnm}` - S3: uses `use_prefix_path` decorator → `{prefix_path}/{bucket}/{fnm}` ## Fix Prepend `{bucket}/` to the file path in all 5 operations across both Azure connector files: | File | Methods fixed | |------|---------------| | `azure_spn_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | | `azure_sas_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | This matches the existing convention where `bucket` is the knowledge base ID used as a directory prefix. ## ⚠️ Migration Note Existing Azure SPN/SAS deployments have files stored without the bucket prefix. After this fix, new files will be stored under `{bucket}/{filename}` while existing files remain at `{filename}`. A one-time migration script or manual file move may be needed for existing deployments. New deployments are unaffected. ## Testing - Verified the fix is consistent across all 5 methods in both files - The `health()` method is intentionally left unchanged as it uses a hardcoded test filename without bucket semantics Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-07 20:48:32 +08:00
blob = f"{bucket}/{fnm}"
for _ in range(3):
try:
fix: prepend bucket prefix to Azure SPN and SAS storage paths (#14185) ## Summary Fixes #14159 — files from different datasets can overwrite each other in Azure Blob storage. ## Problem Both `azure_spn_conn.py` and `azure_sas_conn.py` ignore the `bucket` parameter in all storage operations (`put`, `get`, `rm`, `obj_exist`, `get_presigned_url`). Files are stored flat using only the filename, so two datasets containing a file with the same name will overwrite each other. The MinIO and S3 implementations correctly use the bucket (typically the knowledge base ID) as a path prefix to create logical folder isolation: - MinIO: uses `use_prefix_path` decorator → `{orig_bucket}/{fnm}` - S3: uses `use_prefix_path` decorator → `{prefix_path}/{bucket}/{fnm}` ## Fix Prepend `{bucket}/` to the file path in all 5 operations across both Azure connector files: | File | Methods fixed | |------|---------------| | `azure_spn_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | | `azure_sas_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | This matches the existing convention where `bucket` is the knowledge base ID used as a directory prefix. ## ⚠️ Migration Note Existing Azure SPN/SAS deployments have files stored without the bucket prefix. After this fix, new files will be stored under `{bucket}/{filename}` while existing files remain at `{filename}`. A one-time migration script or manual file move may be needed for existing deployments. New deployments are unaffected. ## Testing - Verified the fix is consistent across all 5 methods in both files - The `health()` method is intentionally left unchanged as it uses a hardcoded test filename without bucket semantics Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-07 20:48:32 +08:00
f = self.conn.create_file(f"{blob}")
f.append_data(binary, offset=0, length=len(binary))
return f.flush_data(len(binary))
except Exception:
fix: prepend bucket prefix to Azure SPN and SAS storage paths (#14185) ## Summary Fixes #14159 — files from different datasets can overwrite each other in Azure Blob storage. ## Problem Both `azure_spn_conn.py` and `azure_sas_conn.py` ignore the `bucket` parameter in all storage operations (`put`, `get`, `rm`, `obj_exist`, `get_presigned_url`). Files are stored flat using only the filename, so two datasets containing a file with the same name will overwrite each other. The MinIO and S3 implementations correctly use the bucket (typically the knowledge base ID) as a path prefix to create logical folder isolation: - MinIO: uses `use_prefix_path` decorator → `{orig_bucket}/{fnm}` - S3: uses `use_prefix_path` decorator → `{prefix_path}/{bucket}/{fnm}` ## Fix Prepend `{bucket}/` to the file path in all 5 operations across both Azure connector files: | File | Methods fixed | |------|---------------| | `azure_spn_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | | `azure_sas_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | This matches the existing convention where `bucket` is the knowledge base ID used as a directory prefix. ## ⚠️ Migration Note Existing Azure SPN/SAS deployments have files stored without the bucket prefix. After this fix, new files will be stored under `{bucket}/{filename}` while existing files remain at `{filename}`. A one-time migration script or manual file move may be needed for existing deployments. New deployments are unaffected. ## Testing - Verified the fix is consistent across all 5 methods in both files - The `health()` method is intentionally left unchanged as it uses a hardcoded test filename without bucket semantics Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-07 20:48:32 +08:00
logging.exception(f"Fail put {blob}")
self.__open__()
time.sleep(1)
return None
return None
def rm(self, bucket, fnm):
blob = f"{bucket}/{fnm}"
try:
self.conn.delete_file(f"{blob}")
except Exception:
logging.exception(f"Fail rm {blob}")
def get(self, bucket, fnm):
fix: prepend bucket prefix to Azure SPN and SAS storage paths (#14185) ## Summary Fixes #14159 — files from different datasets can overwrite each other in Azure Blob storage. ## Problem Both `azure_spn_conn.py` and `azure_sas_conn.py` ignore the `bucket` parameter in all storage operations (`put`, `get`, `rm`, `obj_exist`, `get_presigned_url`). Files are stored flat using only the filename, so two datasets containing a file with the same name will overwrite each other. The MinIO and S3 implementations correctly use the bucket (typically the knowledge base ID) as a path prefix to create logical folder isolation: - MinIO: uses `use_prefix_path` decorator → `{orig_bucket}/{fnm}` - S3: uses `use_prefix_path` decorator → `{prefix_path}/{bucket}/{fnm}` ## Fix Prepend `{bucket}/` to the file path in all 5 operations across both Azure connector files: | File | Methods fixed | |------|---------------| | `azure_spn_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | | `azure_sas_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | This matches the existing convention where `bucket` is the knowledge base ID used as a directory prefix. ## ⚠️ Migration Note Existing Azure SPN/SAS deployments have files stored without the bucket prefix. After this fix, new files will be stored under `{bucket}/{filename}` while existing files remain at `{filename}`. A one-time migration script or manual file move may be needed for existing deployments. New deployments are unaffected. ## Testing - Verified the fix is consistent across all 5 methods in both files - The `health()` method is intentionally left unchanged as it uses a hardcoded test filename without bucket semantics Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-07 20:48:32 +08:00
blob = f"{bucket}/{fnm}"
for _ in range(1):
try:
fix: prepend bucket prefix to Azure SPN and SAS storage paths (#14185) ## Summary Fixes #14159 — files from different datasets can overwrite each other in Azure Blob storage. ## Problem Both `azure_spn_conn.py` and `azure_sas_conn.py` ignore the `bucket` parameter in all storage operations (`put`, `get`, `rm`, `obj_exist`, `get_presigned_url`). Files are stored flat using only the filename, so two datasets containing a file with the same name will overwrite each other. The MinIO and S3 implementations correctly use the bucket (typically the knowledge base ID) as a path prefix to create logical folder isolation: - MinIO: uses `use_prefix_path` decorator → `{orig_bucket}/{fnm}` - S3: uses `use_prefix_path` decorator → `{prefix_path}/{bucket}/{fnm}` ## Fix Prepend `{bucket}/` to the file path in all 5 operations across both Azure connector files: | File | Methods fixed | |------|---------------| | `azure_spn_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | | `azure_sas_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | This matches the existing convention where `bucket` is the knowledge base ID used as a directory prefix. ## ⚠️ Migration Note Existing Azure SPN/SAS deployments have files stored without the bucket prefix. After this fix, new files will be stored under `{bucket}/{filename}` while existing files remain at `{filename}`. A one-time migration script or manual file move may be needed for existing deployments. New deployments are unaffected. ## Testing - Verified the fix is consistent across all 5 methods in both files - The `health()` method is intentionally left unchanged as it uses a hardcoded test filename without bucket semantics Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-07 20:48:32 +08:00
client = self.conn.get_file_client(f"{blob}")
r = client.download_file()
return r.read()
except Exception:
fix: prepend bucket prefix to Azure SPN and SAS storage paths (#14185) ## Summary Fixes #14159 — files from different datasets can overwrite each other in Azure Blob storage. ## Problem Both `azure_spn_conn.py` and `azure_sas_conn.py` ignore the `bucket` parameter in all storage operations (`put`, `get`, `rm`, `obj_exist`, `get_presigned_url`). Files are stored flat using only the filename, so two datasets containing a file with the same name will overwrite each other. The MinIO and S3 implementations correctly use the bucket (typically the knowledge base ID) as a path prefix to create logical folder isolation: - MinIO: uses `use_prefix_path` decorator → `{orig_bucket}/{fnm}` - S3: uses `use_prefix_path` decorator → `{prefix_path}/{bucket}/{fnm}` ## Fix Prepend `{bucket}/` to the file path in all 5 operations across both Azure connector files: | File | Methods fixed | |------|---------------| | `azure_spn_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | | `azure_sas_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | This matches the existing convention where `bucket` is the knowledge base ID used as a directory prefix. ## ⚠️ Migration Note Existing Azure SPN/SAS deployments have files stored without the bucket prefix. After this fix, new files will be stored under `{bucket}/{filename}` while existing files remain at `{filename}`. A one-time migration script or manual file move may be needed for existing deployments. New deployments are unaffected. ## Testing - Verified the fix is consistent across all 5 methods in both files - The `health()` method is intentionally left unchanged as it uses a hardcoded test filename without bucket semantics Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-07 20:48:32 +08:00
logging.exception(f"fail get {blob}")
self.__open__()
time.sleep(1)
return None
def obj_exist(self, bucket, fnm):
blob = f"{bucket}/{fnm}"
try:
client = self.conn.get_blob_client(f"{blob}")
return client.exists()
except Exception:
logging.exception(f"Fail put {blob}")
return False
def get_presigned_url(self, bucket, fnm, expires):
fix: prepend bucket prefix to Azure SPN and SAS storage paths (#14185) ## Summary Fixes #14159 — files from different datasets can overwrite each other in Azure Blob storage. ## Problem Both `azure_spn_conn.py` and `azure_sas_conn.py` ignore the `bucket` parameter in all storage operations (`put`, `get`, `rm`, `obj_exist`, `get_presigned_url`). Files are stored flat using only the filename, so two datasets containing a file with the same name will overwrite each other. The MinIO and S3 implementations correctly use the bucket (typically the knowledge base ID) as a path prefix to create logical folder isolation: - MinIO: uses `use_prefix_path` decorator → `{orig_bucket}/{fnm}` - S3: uses `use_prefix_path` decorator → `{prefix_path}/{bucket}/{fnm}` ## Fix Prepend `{bucket}/` to the file path in all 5 operations across both Azure connector files: | File | Methods fixed | |------|---------------| | `azure_spn_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | | `azure_sas_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | This matches the existing convention where `bucket` is the knowledge base ID used as a directory prefix. ## ⚠️ Migration Note Existing Azure SPN/SAS deployments have files stored without the bucket prefix. After this fix, new files will be stored under `{bucket}/{filename}` while existing files remain at `{filename}`. A one-time migration script or manual file move may be needed for existing deployments. New deployments are unaffected. ## Testing - Verified the fix is consistent across all 5 methods in both files - The `health()` method is intentionally left unchanged as it uses a hardcoded test filename without bucket semantics Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-07 20:48:32 +08:00
f_path = f"{bucket}/{fnm}"
for _ in range(10):
try:
fix: prepend bucket prefix to Azure SPN and SAS storage paths (#14185) ## Summary Fixes #14159 — files from different datasets can overwrite each other in Azure Blob storage. ## Problem Both `azure_spn_conn.py` and `azure_sas_conn.py` ignore the `bucket` parameter in all storage operations (`put`, `get`, `rm`, `obj_exist`, `get_presigned_url`). Files are stored flat using only the filename, so two datasets containing a file with the same name will overwrite each other. The MinIO and S3 implementations correctly use the bucket (typically the knowledge base ID) as a path prefix to create logical folder isolation: - MinIO: uses `use_prefix_path` decorator → `{orig_bucket}/{fnm}` - S3: uses `use_prefix_path` decorator → `{prefix_path}/{bucket}/{fnm}` ## Fix Prepend `{bucket}/` to the file path in all 5 operations across both Azure connector files: | File | Methods fixed | |------|---------------| | `azure_spn_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | | `azure_sas_conn.py` | `put`, `get`, `rm`, `obj_exist`, `get_presigned_url` | This matches the existing convention where `bucket` is the knowledge base ID used as a directory prefix. ## ⚠️ Migration Note Existing Azure SPN/SAS deployments have files stored without the bucket prefix. After this fix, new files will be stored under `{bucket}/{filename}` while existing files remain at `{filename}`. A one-time migration script or manual file move may be needed for existing deployments. New deployments are unaffected. ## Testing - Verified the fix is consistent across all 5 methods in both files - The `health()` method is intentionally left unchanged as it uses a hardcoded test filename without bucket semantics Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-07 20:48:32 +08:00
return self.conn.get_presigned_url("GET", bucket, f_path, expires)
except Exception:
logging.exception(f"fail get {bucket}/{fnm}")
self.__open__()
time.sleep(1)
return None