zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-08-04 06:40:29 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

Browse Source
This commit is contained in:
Wang Qi
2026-07-03 12:53:39 +08:00
committed by GitHub
parent 19fcb4a981
commit 6a4b9be426
588 changed files with 11123 additions and 15412 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
test/unit_test/api/db/joint_services/test_tenant_model_service_max_tokens.py
View File

@@ -65,9 +65,7 @@ def test_max_tokens_falls_back_to_factory_when_model_extra_empty(monkeypatch):
],
)
config = tms.get_model_config_from_provider_instance(
"tenant-1", "chat", "gpt-test@default@OpenAI"
)
config = tms.get_model_config_from_provider_instance("tenant-1", "chat", "gpt-test@default@OpenAI")
assert config["max_tokens"] == 128000
@@ -115,8 +113,6 @@ def test_max_tokens_prefers_model_extra_over_factory(monkeypatch):
],
)
config = tms.get_model_config_from_provider_instance(
"tenant-1", "chat", "gpt-test@default@OpenAI"
)
config = tms.get_model_config_from_provider_instance("tenant-1", "chat", "gpt-test@default@OpenAI")
assert config["max_tokens"] == 32000

1
test/unit_test/api/db/services/test_dataset_access_permissions.py
View File

@@ -30,6 +30,7 @@ warnings.filterwarnings(
def _install_cv2_stub_if_unavailable():
try:
import cv2 # noqa: F401
return
except Exception:
pass

129
test/unit_test/api/db/services/test_dialog_service_final_answer.py
View File

@@ -48,6 +48,7 @@ warnings.filterwarnings(
def _install_cv2_stub_if_unavailable():
try:
import cv2 # noqa: F401
return
except Exception:
pass
@@ -197,6 +198,7 @@ class _FakeLangfuseClient:
def _collect(async_gen):
async def _run():
return [ev async for ev in async_gen]
return asyncio.run(_run())
@@ -204,6 +206,7 @@ def _collect(async_gen):
# Tests for async_ask (production code path)
# ---------------------------------------------------------------------------
@pytest.mark.p2
def test_async_ask_final_event_carries_decorated_answer(monkeypatch):
"""
@@ -218,23 +221,21 @@ def test_async_ask_final_event_carries_decorated_answer(monkeypatch):
chat_mdl = _StreamingChatModel(llm_answer)
retriever = _StubRetriever()
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB])
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB]
)
monkeypatch.setattr(
dialog_service, "get_model_config_from_provider_instance",
dialog_service,
"get_model_config_from_provider_instance",
lambda _tid, _type, _name: _LLM_CONFIG,
)
monkeypatch.setattr(dialog_service, "LLMBundle", lambda _tid, _cfg: chat_mdl)
monkeypatch.setattr(dialog_service.settings, "retriever", retriever, raising=False)
monkeypatch.setattr(dialog_service.settings, "kg_retriever", retriever, raising=False)
monkeypatch.setattr(
dialog_service.DocMetadataService, "get_flatted_meta_by_kbs", lambda _ids: {}
)
monkeypatch.setattr(dialog_service.DocMetadataService, "get_flatted_meta_by_kbs", lambda _ids: {})
monkeypatch.setattr(dialog_service, "label_question", lambda _q, _kbs: "")
# kb_prompt calls DocumentService.get_by_ids which needs a live DB; stub it out.
monkeypatch.setattr(
dialog_service, "kb_prompt",
dialog_service,
"kb_prompt",
lambda _kbinfos, _max_tokens, **_kw: ["RAGFlow is a RAG engine."],
)
@@ -249,9 +250,7 @@ def test_async_ask_final_event_carries_decorated_answer(monkeypatch):
assert events, "async_ask must yield at least one event"
final_events = [e for e in events if e.get("final") is True]
assert len(final_events) == 1, (
f"Expected exactly one final event, got {len(final_events)}: {final_events}"
)
assert len(final_events) == 1, f"Expected exactly one final event, got {len(final_events)}: {final_events}"
final = final_events[0]
assert "answer" in final
@@ -267,22 +266,20 @@ def test_async_ask_delta_events_carry_incremental_text_only(monkeypatch):
chat_mdl = _StreamingChatModel("Incremental text for delta test.")
retriever = _StubRetriever()
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB])
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB]
)
monkeypatch.setattr(
dialog_service, "get_model_config_from_provider_instance",
dialog_service,
"get_model_config_from_provider_instance",
lambda _tid, _type, _name: _LLM_CONFIG,
)
monkeypatch.setattr(dialog_service, "LLMBundle", lambda _tid, _cfg: chat_mdl)
monkeypatch.setattr(dialog_service.settings, "retriever", retriever, raising=False)
monkeypatch.setattr(dialog_service.settings, "kg_retriever", retriever, raising=False)
monkeypatch.setattr(
dialog_service.DocMetadataService, "get_flatted_meta_by_kbs", lambda _ids: {}
)
monkeypatch.setattr(dialog_service.DocMetadataService, "get_flatted_meta_by_kbs", lambda _ids: {})
monkeypatch.setattr(dialog_service, "label_question", lambda _q, _kbs: "")
monkeypatch.setattr(
dialog_service, "kb_prompt",
dialog_service,
"kb_prompt",
lambda _kbinfos, _max_tokens, **_kw: ["RAGFlow is a RAG engine."],
)
@@ -295,15 +292,13 @@ def test_async_ask_delta_events_carry_incremental_text_only(monkeypatch):
)
delta_events = [e for e in events if not e.get("final")]
final_events = [e for e in events if e.get("final") is True]
final_events = [e for e in events if e.get("final") is True]
assert len(final_events) == 1, f"Expected exactly one final event, got {len(final_events)}"
for ev in delta_events:
assert ev["reference"] == {}, f"Delta event must have empty reference, got: {ev['reference']}"
assert "chunks" in final_events[0]["reference"], (
"Final event reference must contain chunk data from decorate_answer()"
)
assert "chunks" in final_events[0]["reference"], "Final event reference must contain chunk data from decorate_answer()"
@pytest.mark.p2
@@ -311,9 +306,7 @@ def test_async_ask_empty_kb_ids_yields_error_final_event(monkeypatch):
"""
When kb_ids is empty, async_ask() must not crash with IndexError on kbs[0].
"""
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: []
)
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [])
events = _collect(
dialog_service.async_ask(
@@ -357,6 +350,7 @@ def test_async_ask_stale_kb_ids_yields_error_final_event(monkeypatch):
# Tests for async_chat (production code path)
# ---------------------------------------------------------------------------
def _make_dialog(chat_mdl_stub):
"""Build a minimal dialog SimpleNamespace for async_chat()."""
return SimpleNamespace(
@@ -405,33 +399,30 @@ def test_async_chat_final_event_carries_decorated_answer(monkeypatch):
retriever = _StubRetriever()
# Stub out the heavy service/model calls
monkeypatch.setattr(dialog_service, "get_model_type_by_name", lambda _tid, _llm_id: ["chat"])
monkeypatch.setattr(
dialog_service, "get_model_type_by_name",
lambda _tid, _llm_id: ["chat"]
)
monkeypatch.setattr(
dialog_service, "get_model_config_from_provider_instance",
dialog_service,
"get_model_config_from_provider_instance",
lambda _tid, _type, _llm_id: _LLM_CONFIG,
)
monkeypatch.setattr(
dialog_service.TenantLangfuseService, "filter_by_tenant",
dialog_service.TenantLangfuseService,
"filter_by_tenant",
lambda tenant_id: None,
)
# get_models returns (kbs, embd_mdl, rerank_mdl, chat_mdl, tts_mdl)
monkeypatch.setattr(
dialog_service, "get_models",
dialog_service,
"get_models",
lambda _dialog, **_kwargs: ([_KB], chat_mdl, None, chat_mdl, None),
)
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_field_map", lambda _kb_ids: {}
)
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB]
)
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_field_map", lambda _kb_ids: {})
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB])
monkeypatch.setattr(dialog_service.settings, "retriever", retriever, raising=False)
monkeypatch.setattr(dialog_service, "label_question", lambda _q, _kbs: "")
monkeypatch.setattr(
dialog_service, "kb_prompt",
dialog_service,
"kb_prompt",
lambda _kbinfos, _max_tokens, **_kw: ["RAGFlow is a RAG engine."],
)
@@ -441,9 +432,7 @@ def test_async_chat_final_event_carries_decorated_answer(monkeypatch):
events = _collect(dialog_service.async_chat(dialog, messages, stream=True, quote=True))
final_events = [e for e in events if e.get("final") is True]
assert len(final_events) == 1, (
f"Expected exactly one final event, got {len(final_events)}: {final_events}"
)
assert len(final_events) == 1, f"Expected exactly one final event, got {len(final_events)}: {final_events}"
final = final_events[0]
assert "answer" in final
@@ -462,16 +451,15 @@ def test_async_chat_langfuse_uses_start_observation(monkeypatch):
chat_mdl = _StreamingChatModel(llm_answer)
retriever = _StubRetriever()
monkeypatch.setattr(dialog_service, "get_model_type_by_name", lambda _tid, _llm_id: ["chat"])
monkeypatch.setattr(
dialog_service, "get_model_type_by_name",
lambda _tid, _llm_id: ["chat"]
)
monkeypatch.setattr(
dialog_service, "get_model_config_from_provider_instance",
dialog_service,
"get_model_config_from_provider_instance",
lambda _tid, _type, _llm_id: _LLM_CONFIG,
)
monkeypatch.setattr(
dialog_service.TenantLangfuseService, "filter_by_tenant",
dialog_service.TenantLangfuseService,
"filter_by_tenant",
lambda tenant_id: SimpleNamespace(
public_key="public",
secret_key="secret",
@@ -486,12 +474,8 @@ def test_async_chat_langfuse_uses_start_observation(monkeypatch):
"get_models",
lambda _dialog, **_kwargs: ([_KB], chat_mdl, None, chat_mdl, None),
)
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_field_map", lambda _kb_ids: {}
)
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB]
)
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_field_map", lambda _kb_ids: {})
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB])
monkeypatch.setattr(dialog_service.settings, "retriever", retriever, raising=False)
monkeypatch.setattr(dialog_service, "label_question", lambda _q, _kbs: "")
monkeypatch.setattr(
@@ -530,17 +514,15 @@ def test_async_chat_langfuse_observation_includes_session_id(monkeypatch):
chat_mdl = _StreamingChatModel("Session traces should be grouped.")
retriever = _StubRetriever()
monkeypatch.setattr(
dialog_service, "get_model_type_by_name",
lambda _tid, _llm_id: ["chat"]
)
monkeypatch.setattr(dialog_service, "get_model_type_by_name", lambda _tid, _llm_id: ["chat"])
monkeypatch.setattr(
dialog_service,
"get_model_config_from_provider_instance",
lambda _tid, _type, _llm_id: _LLM_CONFIG,
)
monkeypatch.setattr(
dialog_service.TenantLangfuseService, "filter_by_tenant",
dialog_service.TenantLangfuseService,
"filter_by_tenant",
lambda tenant_id: SimpleNamespace(
public_key="public",
secret_key="secret",
@@ -554,12 +536,8 @@ def test_async_chat_langfuse_observation_includes_session_id(monkeypatch):
"get_models",
lambda _dialog, **_kwargs: ([_KB], chat_mdl, None, chat_mdl, None),
)
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_field_map", lambda _kb_ids: {}
)
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB]
)
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_field_map", lambda _kb_ids: {})
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB])
monkeypatch.setattr(dialog_service.settings, "retriever", retriever, raising=False)
monkeypatch.setattr(dialog_service, "label_question", lambda _q, _kbs: "")
monkeypatch.setattr(
@@ -635,16 +613,15 @@ def test_async_chat_continues_when_langfuse_observation_start_fails(monkeypatch)
chat_mdl = _StreamingChatModel(llm_answer)
retriever = _StubRetriever()
monkeypatch.setattr(dialog_service, "get_model_type_by_name", lambda _tid, _llm_id: ["chat"])
monkeypatch.setattr(
dialog_service, "get_model_type_by_name",
lambda _tid, _llm_id: ["chat"]
)
monkeypatch.setattr(
dialog_service, "get_model_config_from_provider_instance",
dialog_service,
"get_model_config_from_provider_instance",
lambda _tid, _type, _llm_id: _LLM_CONFIG,
)
monkeypatch.setattr(
dialog_service.TenantLangfuseService, "filter_by_tenant",
dialog_service.TenantLangfuseService,
"filter_by_tenant",
lambda tenant_id: SimpleNamespace(
public_key="public",
secret_key="secret",
@@ -659,12 +636,8 @@ def test_async_chat_continues_when_langfuse_observation_start_fails(monkeypatch)
"get_models",
lambda _dialog, **_kwargs: ([_KB], chat_mdl, None, chat_mdl, None),
)
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_field_map", lambda _kb_ids: {}
)
monkeypatch.setattr(
dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB]
)
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_field_map", lambda _kb_ids: {})
monkeypatch.setattr(dialog_service.KnowledgebaseService, "get_by_ids", lambda _ids: [_KB])
monkeypatch.setattr(dialog_service.settings, "retriever", retriever, raising=False)
monkeypatch.setattr(dialog_service, "label_question", lambda _q, _kbs: "")
monkeypatch.setattr(

5
test/unit_test/api/db/services/test_dialog_service_use_sql_source_columns.py
View File

@@ -316,10 +316,7 @@ def test_async_chat_uses_all_docs_when_no_doc_ids_selected(monkeypatch):
)
monkeypatch.setattr(dialog_service.settings, "retriever", retriever, raising=False)
monkeypatch.setattr(
dialog_service, "get_model_type_by_name",
lambda _tid, _llm_id: ["chat"]
)
monkeypatch.setattr(dialog_service, "get_model_type_by_name", lambda _tid, _llm_id: ["chat"])
monkeypatch.setattr(
dialog_service,
"get_model_config_from_provider_instance",

25
test/unit_test/api/db/services/test_document_service_get_parsing_status.py
View File

@@ -31,6 +31,7 @@ warnings.filterwarnings(
def _install_cv2_stub_if_unavailable():
try:
import cv2 # noqa: F401
return
except Exception:
pass
@@ -70,6 +71,7 @@ from common.constants import TaskStatus # noqa: E402
# Helpers to access the original function bypassing @DB.connection_context()
# ---------------------------------------------------------------------------
def _unwrapped_get_parsing_status():
"""Return the original (un-decorated) get_parsing_status_by_kb_ids function.
@@ -84,6 +86,7 @@ def _unwrapped_get_parsing_status():
# Fake ORM helpers – mimic the minimal peewee query chain used by the function
# ---------------------------------------------------------------------------
class _FieldStub:
"""Minimal stand-in for a peewee model field used in select/where/group_by."""
@@ -130,6 +133,7 @@ def _make_fake_model(rows):
# Pytest fixture – patch DocumentService.model per test
# ---------------------------------------------------------------------------
@pytest.fixture()
def call_with_rows(monkeypatch):
"""Return a helper that runs get_parsing_status_by_kb_ids with fake DB rows."""
@@ -146,14 +150,11 @@ def call_with_rows(monkeypatch):
# Tests
# ---------------------------------------------------------------------------
_ALL_STATUS_FIELDS = frozenset(
["unstart_count", "running_count", "cancel_count", "done_count", "fail_count"]
)
_ALL_STATUS_FIELDS = frozenset(["unstart_count", "running_count", "cancel_count", "done_count", "fail_count"])
@pytest.mark.p2
class TestGetParsingStatusByKbIds:
# ------------------------------------------------------------------
# Edge-case: empty input list – must short-circuit before any DB call
# ------------------------------------------------------------------
@@ -224,16 +225,13 @@ class TestGetParsingStatusByKbIds:
def test_unknown_run_value_ignored(self, call_with_rows):
rows = [
{"kb_id": "kb-1", "run": "9", "cnt": 99}, # "9" is not a TaskStatus
{"kb_id": "kb-1", "run": "9", "cnt": 99}, # "9" is not a TaskStatus
{"kb_id": "kb-1", "run": TaskStatus.DONE.value, "cnt": 4},
]
result = call_with_rows(rows=rows, kb_ids=["kb-1"])
assert result["kb-1"]["done_count"] == 4
assert all(
result["kb-1"][f] == 0
for f in _ALL_STATUS_FIELDS - {"done_count"}
)
assert all(result["kb-1"][f] == 0 for f in _ALL_STATUS_FIELDS - {"done_count"})
# ------------------------------------------------------------------
# A row whose kb_id was NOT requested must not appear in the output
@@ -298,9 +296,7 @@ class TestGetParsingStatusByKbIds:
rows = [
{"kb_id": "kb-with-data", "run": TaskStatus.DONE.value, "cnt": 1},
]
result = call_with_rows(
rows=rows, kb_ids=["kb-with-data", "kb-empty-1", "kb-empty-2"]
)
result = call_with_rows(rows=rows, kb_ids=["kb-with-data", "kb-empty-1", "kb-empty-2"])
assert set(result.keys()) == {"kb-with-data", "kb-empty-1", "kb-empty-2"}
assert result["kb-empty-1"] == {f: 0 for f in _ALL_STATUS_FIELDS}
@@ -320,7 +316,4 @@ class TestGetParsingStatusByKbIds:
assert result["kb-1"]["done_count"] == 2
# SCHEDULE is not a tracked bucket
assert "schedule_count" not in result["kb-1"]
assert all(
result["kb-1"][f] == 0
for f in _ALL_STATUS_FIELDS - {"done_count"}
)
assert all(result["kb-1"][f] == 0 for f in _ALL_STATUS_FIELDS - {"done_count"})

7
test/unit_test/api/db/services/test_file_service_upload_document.py
View File

@@ -127,6 +127,7 @@ def test_upload_document_skips_cross_kb_document_id_collision(monkeypatch):
# Helpers shared by TestValidateUrlForCrawl
# ---------------------------------------------------------------------------
def _addrinfo(ip_str: str) -> list:
"""Build a minimal getaddrinfo-style result for a single address string."""
family = socket.AF_INET6 if ":" in ip_str else socket.AF_INET
@@ -137,6 +138,7 @@ def _addrinfo(ip_str: str) -> list:
# _validate_url_for_crawl SSRF-guard tests
# ---------------------------------------------------------------------------
@pytest.mark.p2
class TestValidateUrlForCrawl:
"""Focused regression suite for the SSRF guard on the URL-crawl path.
@@ -268,10 +270,7 @@ class TestValidateUrlForCrawl:
monkeypatch.setattr(
socket,
"getaddrinfo",
lambda h, p: (
_addrinfo("93.184.216.34")
+ _addrinfo("2606:2800:220:1:248:1893:25c8:1946")
),
lambda h, p: _addrinfo("93.184.216.34") + _addrinfo("2606:2800:220:1:248:1893:25c8:1946"),
)
hostname, resolved_ip = FileService._validate_url_for_crawl("https://example.com/")
assert hostname == "example.com"

45
test/unit_test/api/db/test_oceanbase_peewee.py
View File

@@ -20,22 +20,23 @@ class TestOceanBaseDatabase:
def test_oceanbase_in_pooled_database_enum(self):
"""Test that OCEANBASE is in PooledDatabase enum."""
assert hasattr(PooledDatabase, 'OCEANBASE')
assert hasattr(PooledDatabase, "OCEANBASE")
assert PooledDatabase.OCEANBASE.value == RetryingPooledOceanBaseDatabase
def test_oceanbase_in_database_lock_enum(self):
"""Test that OCEANBASE is in DatabaseLock enum."""
assert hasattr(DatabaseLock, 'OCEANBASE')
assert hasattr(DatabaseLock, "OCEANBASE")
def test_oceanbase_in_text_field_type_enum(self):
"""Test that OCEANBASE is in TextFieldType enum."""
assert hasattr(TextFieldType, 'OCEANBASE')
assert hasattr(TextFieldType, "OCEANBASE")
# OceanBase should use LONGTEXT like MySQL
assert TextFieldType.OCEANBASE.value == "LONGTEXT"
def test_oceanbase_database_inherits_mysql(self):
"""Test that OceanBase database inherits from PooledMySQLDatabase."""
from playhouse.pool import PooledMySQLDatabase
assert issubclass(RetryingPooledOceanBaseDatabase, PooledMySQLDatabase)
def test_oceanbase_database_init(self):
@@ -64,13 +65,13 @@ class TestOceanBaseDatabase:
def test_pooled_database_enum_values(self):
"""Test PooledDatabase enum has all expected values."""
expected = {'MYSQL', 'OCEANBASE', 'POSTGRES'}
expected = {"MYSQL", "OCEANBASE", "POSTGRES"}
actual = {e.name for e in PooledDatabase}
assert expected.issubset(actual), f"Missing: {expected - actual}"
def test_database_lock_enum_values(self):
"""Test DatabaseLock enum has all expected values."""
expected = {'MYSQL', 'OCEANBASE', 'POSTGRES'}
expected = {"MYSQL", "OCEANBASE", "POSTGRES"}
actual = set(DatabaseLock.__members__.keys())
assert expected.issubset(actual), f"Missing: {expected - actual}"
@@ -81,45 +82,49 @@ class TestOceanBaseConfiguration:
def test_settings_default_to_mysql(self):
"""Test that default DB_TYPE is mysql."""
import os
# Save original value
original = os.environ.get('DB_TYPE')
original = os.environ.get("DB_TYPE")
try:
# Remove DB_TYPE to test default
if 'DB_TYPE' in os.environ:
del os.environ['DB_TYPE']
if "DB_TYPE" in os.environ:
del os.environ["DB_TYPE"]
# Reload settings
from common import settings
settings.DATABASE_TYPE = os.getenv("DB_TYPE", "mysql")
assert settings.DATABASE_TYPE == "mysql"
finally:
# Restore original value
if original:
os.environ['DB_TYPE'] = original
os.environ["DB_TYPE"] = original
def test_settings_can_use_oceanbase(self):
"""Test that DB_TYPE can be set to oceanbase."""
import os
# Save original value
original = os.environ.get('DB_TYPE')
original = os.environ.get("DB_TYPE")
try:
os.environ['DB_TYPE'] = 'oceanbase'
os.environ["DB_TYPE"] = "oceanbase"
# Reload settings
from common import settings
settings.DATABASE_TYPE = os.getenv("DB_TYPE", "mysql")
assert settings.DATABASE_TYPE == "oceanbase"
finally:
# Restore original value
if original:
os.environ['DB_TYPE'] = original
os.environ["DB_TYPE"] = original
else:
if 'DB_TYPE' in os.environ:
del os.environ['DB_TYPE']
if "DB_TYPE" in os.environ:
del os.environ["DB_TYPE"]
if __name__ == "__main__":