pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2026-01-31 23:55:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: close file handles when loading JSON mapping in doc store connectors (#12904)

Browse Source 
**What problem does this PR solve?**

When loading JSON mapping/schema files, the code used
json.load(open(path)) without closing the file. The file handle stayed
open until garbage collection, which can leak file descriptors under
load (e.g. repeated reconnects or migrations).

**Type of change**
[x] Bug Fix (non-breaking change which fixes an issue)
**Change**
Replaced json.load(open(...)) with a context manager so the file is
closed after loading:
with open(fp_mapping, "r") as f:    ... = json.load(f)

**Files updated**
rag/utils/opensearch_conn.py – mapping load (1 place)
common/doc_store/es_conn_base.py – mapping load + doc_meta_mapping load
(2 places)
common/doc_store/infinity_conn_base.py – schema loads in _migrate_db,
doc metadata table creation, and SQL field mapping (4 places)
Behavior is unchanged; only resource handling is fixed.

Co-authored-by: Gittensor Miner <miner@gittensor.io>
This commit is contained in:
Phives
2026-01-30 01:07:51 -05:00
committed by GitHub
parent 212d6f3660
commit 87305cb08c
3 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
common/doc_store/es_conn_base.py
View File

@ -48,7 +48,8 @@ class ESConnectionBase(DocStoreConnection):
msg = f"Elasticsearch mapping file not found at {fp_mapping}" msg = f"Elasticsearch mapping file not found at {fp_mapping}"
self.logger.error(msg) self.logger.error(msg)
raise Exception(msg) raise Exception(msg)
self.mapping = json.load(open(fp_mapping, "r")) with open(fp_mapping, "r") as f:
self.mapping = json.load(f)
self.logger.info(f"Elasticsearch {settings.ES['hosts']} is healthy.") self.logger.info(f"Elasticsearch {settings.ES['hosts']} is healthy.")
def _connect(self): def _connect(self):
@ -150,7 +151,8 @@ class ESConnectionBase(DocStoreConnection):
self.logger.error(f"Document metadata mapping file not found at {fp_mapping}") self.logger.error(f"Document metadata mapping file not found at {fp_mapping}")
return False return False
doc_meta_mapping = json.load(open(fp_mapping, "r")) with open(fp_mapping, "r") as f:
doc_meta_mapping = json.load(f)
return IndicesClient(self.es).create(index=index_name, return IndicesClient(self.es).create(index=index_name,
settings=doc_meta_mapping["settings"], settings=doc_meta_mapping["settings"],
mappings=doc_meta_mapping["mappings"]) mappings=doc_meta_mapping["mappings"])

9
common/doc_store/infinity_conn_base.py
View File

@ -73,7 +73,8 @@ class InfinityConnectionBase(DocStoreConnection):
fp_mapping = os.path.join(get_project_base_directory(), "conf", self.mapping_file_name) fp_mapping = os.path.join(get_project_base_directory(), "conf", self.mapping_file_name)
if not os.path.exists(fp_mapping): if not os.path.exists(fp_mapping):
raise Exception(f"Mapping file not found at {fp_mapping}") raise Exception(f"Mapping file not found at {fp_mapping}")
schema = json.load(open(fp_mapping)) with open(fp_mapping) as f:
schema = json.load(f)
table_names = inf_db.list_tables().table_names table_names = inf_db.list_tables().table_names
for table_name in table_names: for table_name in table_names:
inf_table = inf_db.get_table(table_name) inf_table = inf_db.get_table(table_name)
@ -300,7 +301,8 @@ class InfinityConnectionBase(DocStoreConnection):
if not os.path.exists(fp_mapping): if not os.path.exists(fp_mapping):
self.logger.error(f"Document metadata mapping file not found at {fp_mapping}") self.logger.error(f"Document metadata mapping file not found at {fp_mapping}")
return False return False
schema = json.load(open(fp_mapping)) with open(fp_mapping) as f:
schema = json.load(f)
inf_db.create_table( inf_db.create_table(
table_name, table_name,
schema, schema,
@ -547,7 +549,8 @@ class InfinityConnectionBase(DocStoreConnection):
reverse_mapping = {} reverse_mapping = {}
fp_mapping = os.path.join(get_project_base_directory(), "conf", self.mapping_file_name) fp_mapping = os.path.join(get_project_base_directory(), "conf", self.mapping_file_name)
if os.path.exists(fp_mapping): if os.path.exists(fp_mapping):
schema = json.load(open(fp_mapping)) with open(fp_mapping) as f:
schema = json.load(f)
for field_name, field_info in schema.items(): for field_name, field_info in schema.items():
if "comment" in field_info: if "comment" in field_info:
# Parse comma-separated aliases from comment # Parse comma-separated aliases from comment

3
rag/utils/opensearch_conn.py
View File

@ -72,7 +72,8 @@ class OSConnection(DocStoreConnection):
msg = f"OpenSearch mapping file not found at {fp_mapping}" msg = f"OpenSearch mapping file not found at {fp_mapping}"
logger.error(msg) logger.error(msg)
raise Exception(msg) raise Exception(msg)
self.mapping = json.load(open(fp_mapping, "r")) with open(fp_mapping, "r") as f:
self.mapping = json.load(f)
logger.info(f"OpenSearch {settings.OS['hosts']} is healthy.") logger.info(f"OpenSearch {settings.OS['hosts']} is healthy.")
""" """