Merge main fix conflict

Author: JATAYU000

openml/_api/clients/http.py

@@ -12,7 +12,6 @@
 from typing import Any, cast
 from urllib.parse import urlencode, urljoin, urlparse
 
-import arff
 import requests
 import xmltodict
 from requests import Response
@@ -93,28 +92,32 @@ def _key_to_path(self, key: str) -> Path:
     def _get_body_filename_from_response(self, response: Response) -> str:
         content_type = response.headers.get("Content-Type", "").lower()
 
+        # check for .json
         if "application/json" in content_type:
             return "body.json"
 
+        # check for .xml
         if "text/xml" in content_type:
             return "body.xml"
 
+        # check for .zip
         if response.content.startswith(b"PK\x03\x04"):
             return "body.zip"
 
-        try:
-            arff.loads(response.text)
-            return "body.arff"
-        except arff.ArffException:
-            pass
+        # check for .arff
+        for raw_line in response.text.splitlines():
+            stripped_line = raw_line.strip()
+            # skip empty lines and comments
+            if not stripped_line or stripped_line.startswith("%"):
+                continue
+            if stripped_line.lower().startswith("@relation"):
+                return "body.arff"
+            break
 
         return "body.txt"
 
     def _get_body_filename_from_path(self, path: Path) -> str:
-        candidates = []
-        for p in path.iterdir():
-            if p.name.startswith("body.") and len(p.suffixes) == 1:
-                candidates.append(p)
+        candidates = [p for p in path.glob("body.*") if len(p.suffixes) == 1]
 
         if not candidates:
             raise FileNotFoundError(f"No body file found in path: {path}")

openml/_api/resources/base/resources.py

@@ -18,7 +18,9 @@
     from openml.estimation_procedures import OpenMLEstimationProcedure
     from openml.evaluations import OpenMLEvaluation
     from openml.flows.flow import OpenMLFlow
+    from openml.runs.run import OpenMLRun
     from openml.setups.setup import OpenMLSetup
+    from openml.tasks.task import TaskType
 
 
 class DatasetAPI(ResourceAPI):
@@ -191,6 +193,21 @@ class FlowAPI(ResourceAPI):
 
     resource_type: ResourceType = ResourceType.FLOW
 
+    @abstractmethod
+    def get(self, flow_id: int, *, reset_cache: bool = False) -> OpenMLFlow: ...
+
+    @abstractmethod
+    def list(
+        self,
+        limit: int | None = None,
+        offset: int | None = None,
+        tag: str | None = None,
+        uploader: str | None = None,
+    ) -> pd.DataFrame: ...
+
+    @abstractmethod
+    def exists(self, name: str, external_version: str) -> int | bool: ...
+
 
 class StudyAPI(ResourceAPI):
     """Abstract API interface for study resources."""
@@ -214,6 +231,46 @@ class RunAPI(ResourceAPI):
 
     resource_type: ResourceType = ResourceType.RUN
 
+    @abstractmethod
+    def get(
+        self,
+        run_id: int,
+        *,
+        reset_cache: bool = False,
+    ) -> OpenMLRun: ...
+
+    @abstractmethod
+    def list(  # type: ignore[valid-type]  # noqa: PLR0913
+        self,
+        limit: int,
+        offset: int,
+        *,
+        ids: builtins.list[int] | None = None,
+        task: builtins.list[int] | None = None,
+        setup: builtins.list[int] | None = None,
+        flow: builtins.list[int] | None = None,
+        uploader: builtins.list[int] | None = None,
+        study: int | None = None,
+        tag: str | None = None,
+        display_errors: bool = False,
+        task_type: TaskType | int | None = None,
+    ) -> pd.DataFrame: ...
+
+    @abstractmethod
+    def download_text_file(
+        self,
+        source: str,
+        *,
+        md5_checksum: str | None = None,
+    ) -> str: ...
+
+    @abstractmethod
+    def file_id_to_url(
+        self,
+        file_id: int,
+        filename: str | None = None,
+    ) -> str: ...
+
 
 class SetupAPI(ResourceAPI):
     """Abstract API interface for setup resources."""