Add ruff rules for self (#572)

Author: cbornet

examples/notebooks/langchain_dynamic_fewshot_SQL.ipynb

@@ -190,7 +190,7 @@
     "COMMIT;\n",
     "\"\"\"\n",
     "\n",
-    "with db._engine.begin() as conn:\n",
+    "with db._engine.begin() as conn:  # noqa: SLF001\n",
     "    conn.connection.executescript(PETS_SQL)"
    ]
   },

libs/colbert/ragstack_colbert/cassandra_database.py

@@ -68,7 +68,7 @@ def from_session(
         table_name: Optional[str] = "colbert",
     ):
         instance = super().__new__(cls)
-        instance._initialize(session=session, keyspace=keyspace, table_name=table_name)
+        instance._initialize(session=session, keyspace=keyspace, table_name=table_name)  # noqa: SLF001
         return instance
 
     def _initialize(

libs/e2e-tests/e2e_tests/conftest.py

@@ -138,9 +138,7 @@ def pytest_runtest_makereport(item, call):
                         import traceback
 
                         traceback.print_exception(
-                            call.excinfo._excinfo[0],
-                            call.excinfo._excinfo[1],
-                            call.excinfo._excinfo[2],
+                            call.excinfo.type, call.excinfo.value, call.excinfo.tb
                         )
                     except Exception:  # noqa: BLE001
                         logging.warning("Failed to print stacktrace", exc_info=True)

libs/e2e-tests/e2e_tests/llama_index/test_astra.py

@@ -109,7 +109,7 @@ def test_wrong_connection_parameters(environment: Environment):
 
     # This is expected to be a valid endpoint,
     # because we want to test an AUTHENTICATION error
-    api_endpoint = environment.vectorstore._astra_db.base_url
+    api_endpoint = environment.vectorstore._astra_db.base_url  # noqa: SLF001
     try:
         print("api_endpoint:", api_endpoint)
         AstraDBVectorStore(

libs/e2e-tests/e2e_tests/test_utils/astradb_vector_store_handler.py

@@ -57,16 +57,16 @@ def get_current_deletions(self):
         """
         Returns the number of ongoing deletions.
         """
-        return self.max_workers - self.semaphore._value
+        return self.max_workers - self.semaphore._value  # noqa: SLF001
 
     def await_ongoing_deletions_completed(self):
         """
         Blocks until all ongoing deletions are completed.
         """
-        while self.semaphore._value != self.max_workers:
+        pending_deletions = self.max_workers - self.semaphore._value  # noqa: SLF001
+        while pending_deletions >= 0:
             logging.debug(
-                "%s deletions still running, waiting to complete",
-                self.max_workers - self.semaphore._value,
+                "%s deletions still running, waiting to complete", pending_deletions
             )
             time.sleep(1)
         return

libs/knowledge-graph/ragstack_knowledge_graph/traverse.py

@@ -149,8 +149,9 @@ def handle_result(rows, source_distance: int, request: ResponseFuture):
             request.start_fetching_next_page()
         else:
             with condition:
-                if request._req_id in pending:
-                    pending.remove(request._req_id)
+                req_id = request._req_id  # noqa: SLF001
+                if req_id in pending:
+                    pending.remove(req_id)
                 if len(pending) == 0:
                     condition.notify()
 
@@ -178,7 +179,7 @@ def fetch_relationships(distance: int, source: Node) -> None:
             request: ResponseFuture = session.execute_async(
                 query, (source.name, source.type)
             )
-            pending.add(request._req_id)
+            pending.add(request._req_id)  # noqa: SLF001
             request.add_callbacks(
                 handle_result,
                 handle_error,

libs/langchain/ragstack_langchain/colbert/colbert_vector_store.py

@@ -244,8 +244,7 @@ def from_texts(
     ) -> CVS:
         """Return VectorStore initialized from texts and embeddings."""
 
-        instance = super().__new__(cls)
-        instance._initialize(database=database, embedding_model=embedding_model)
+        instance = cls(database=database, embedding_model=embedding_model, **kwargs)
         instance.add_texts(texts=texts, metadatas=metadatas)
         return instance
 
@@ -260,8 +259,7 @@ async def afrom_texts(
         **kwargs: Any,
     ) -> CVS:
         """Return VectorStore initialized from texts and embeddings."""
-        instance = super().__new__(cls)
-        instance._initialize(database=database, embedding_model=embedding_model)
+        instance = cls(database=database, embedding_model=embedding_model, **kwargs)
         await instance.aadd_texts(
             texts=texts, metadatas=metadatas, concurrent_inserts=concurrent_inserts
         )

libs/ragulate/ragstack_ragulate/cli_commands/run.py

@@ -55,23 +55,23 @@ def call_run(config_file: str, **kwargs):
 
     logger.debug("Found these ingest pipelines:")
     for ingest_pipeline in ingest_pipelines:
-        logger.debug(f"\t{ingest_pipeline._key()}")
+        logger.debug(f"\t{ingest_pipeline.key()}")
 
     ingest_pipelines = list(set(ingest_pipelines))
 
     logger.debug("Narrowed down to these ingest pipelines:")
     for ingest_pipeline in ingest_pipelines:
-        logger.debug(f"\t{ingest_pipeline._key()}")
+        logger.debug(f"\t{ingest_pipeline.key()}")
 
     logger.debug("Found these query pipelines:")
     for query_pipeline in query_pipelines:
-        logger.debug(f"\t{query_pipeline._key()}")
+        logger.debug(f"\t{query_pipeline.key()}")
 
     query_pipelines = list(set(query_pipelines))
 
     logger.debug("Narrowed down to these query pipelines:")
     for query_pipeline in query_pipelines:
-        logger.debug(f"\t{query_pipeline._key()}")
+        logger.debug(f"\t{query_pipeline.key()}")
 
     for ingest_pipeline in ingest_pipelines:
         ingest_pipeline.ingest()

libs/ragulate/ragstack_ragulate/pipelines/base_pipeline.py

@@ -107,7 +107,7 @@ def get_method(self):
     def dataset_names(self) -> List[str]:
         return [d.name for d in self.datasets]
 
-    def _key(self) -> str:
+    def key(self) -> str:
         key_parts = [
             self.pipeline_type,
             self.script_path,
@@ -119,8 +119,8 @@ def _key(self) -> str:
 
     def __eq__(self, other):
         if isinstance(other, BasePipeline):
-            return self._key() == other._key()
+            return self.key() == other.key()
         return False
 
     def __hash__(self):
-        return hash(self._key())
+        return hash(self.key())

pyproject.toml

@@ -99,6 +99,7 @@ select = [
     "RSE",
     "RUF",
     "SIM",
+    "SLF",
     "SLOT",
     "T10",
     "T20",

scripts/generate-testspace-report.py

@@ -72,7 +72,7 @@ def cdata(text: str) -> str:
     return f"<![CDATA[{text}]]>"
 
 
-xml.etree.ElementTree._escape_cdata = unsafe_escape_data
+xml.etree.ElementTree._escape_cdata = unsafe_escape_data  # noqa: SLF001
 
 
 def main(report_type: str, input_file: str, output_file: str):