Remove aiohttp from direct dependencies (#7294)

* Remove `aiohttp` from direct dependencies

It is only used for catching an exception from other code.

* Update setup.py

---------

Co-authored-by: Quentin Lhoest <42851186+lhoestq@users.noreply.github.com>

Author: akx

.github/conda/meta.yaml

@@ -26,7 +26,6 @@ requirements:
     - fsspec
     - huggingface_hub >=0.24.0,<1.0.0
     - packaging
-    - aiohttp
   run:
     - python
     - pip
@@ -42,7 +41,6 @@ requirements:
     - fsspec
     - huggingface_hub >=0.24.0,<1.0.0
     - packaging
-    - aiohttp
 
 test:
   imports:

setup.py

@@ -128,8 +128,6 @@
     # to save datasets locally or on any filesystem
     # minimum 2023.1.0 to support protocol=kwargs in fsspec's `open`, `get_fs_token_paths`, etc.: see https://github.com/fsspec/filesystem_spec/pull/1143
     "fsspec[http]>=2023.1.0,<=2025.3.0",
-    # for data streaming via http
-    "aiohttp",
     # To get datasets from the Datasets Hub on huggingface.co
     "huggingface-hub>=0.24.0",
     # Utilities from PyPA to e.g., compare versions
@@ -164,6 +162,7 @@
     "pytest-datadir",
     "pytest-xdist",
     # optional dependencies
+    "aiohttp",
     "elasticsearch>=7.17.12,<8.0.0",  # 8.0 asks users to provide hosts or cloud_id when instantiating ElasticSearch(); 7.9.1 has legacy numpy.float_ which was fixed in https://github.com/elastic/elasticsearch-py/pull/2551.
     "faiss-cpu>=1.8.0.post1",  # Pins numpy < 2
     "jax>=0.3.14; sys_platform != 'win32'",

src/datasets/utils/file_utils.py

@@ -27,7 +27,6 @@
 from urllib.parse import urlparse
 from xml.etree import ElementTree as ET
 
-import aiohttp.client_exceptions
 import fsspec
 import huggingface_hub
 import huggingface_hub.errors
@@ -45,6 +44,15 @@
 from .extract import ExtractManager
 from .track import TrackedIterableFromGenerator
 
+try:
+    from aiohttp.client_exceptions import ClientError as _AiohttpClientError
+except ImportError:
+    # aiohttp is not available; synthesize an exception type
+    # that will never be raised by any actual code for use in the `except`
+    # clause only.
+    class _AiohttpClientError(Exception):
+        pass
+
 
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
@@ -818,7 +826,7 @@ def read_with_retries(*args, **kwargs):
                 out = read(*args, **kwargs)
                 break
             except (
-                aiohttp.client_exceptions.ClientError,
+                _AiohttpClientError,
                 asyncio.TimeoutError,
                 requests.exceptions.ConnectionError,
                 requests.exceptions.Timeout,