From 7de06490adb9148a66621b56e71503d4e4e54a6b Mon Sep 17 00:00:00 2001
From: Wauplin <lucainp@gmail.com>
Date: Fri, 7 Jun 2024 13:20:17 +0200
Subject: [PATCH 1/3] Better error handling in dataset_module_factory

---
 src/datasets/load.py | 40 ++++++++++++++++++----------------------
 1 file changed, 18 insertions(+), 22 deletions(-)

diff --git a/src/datasets/load.py b/src/datasets/load.py
index 824817843fd..216fcc12ebf 100644
--- a/src/datasets/load.py
+++ b/src/datasets/load.py
@@ -37,6 +37,7 @@
 import yaml
 from fsspec.core import url_to_fs
 from huggingface_hub import DatasetCard, DatasetCardData, HfApi, HfFileSystem
+from huggingface_hub.utils import GatedRepoError, RepositoryNotFoundError, RevisionNotFoundError
 
 from . import config
 from .arrow_dataset import Dataset
@@ -1836,28 +1837,23 @@ def dataset_module_factory(
                     token=download_config.token,
                     timeout=100.0,
                 )
-            except Exception as e:  # noqa catch any exception of hf_hub and consider that the dataset doesn't exist
-                if isinstance(
-                    e,
-                    (
-                        OfflineModeIsEnabled,
-                        requests.exceptions.ConnectTimeout,
-                        requests.exceptions.ConnectionError,
-                    ),
-                ):
-                    raise ConnectionError(f"Couldn't reach '{path}' on the Hub ({type(e).__name__})")
-                elif "404" in str(e):
-                    msg = f"Dataset '{path}' doesn't exist on the Hub or cannot be accessed"
-                    raise DatasetNotFoundError(msg + f" at revision '{revision}'" if revision else msg)
-                elif "401" in str(e):
-                    msg = f"Dataset '{path}' doesn't exist on the Hub or cannot be accessed"
-                    msg = msg + f" at revision '{revision}'" if revision else msg
-                    raise DatasetNotFoundError(
-                        msg
-                        + f". If the dataset is private or gated, make sure to log in with `huggingface-cli login` or visit the dataset page at https://huggingface.co/datasets/{path} to ask for access."
-                    )
-                else:
-                    raise e
+            except (
+                OfflineModeIsEnabled,
+                requests.exceptions.ConnectTimeout,
+                requests.exceptions.ConnectionError,
+            ) as e:
+                raise ConnectionError(f"Couldn't reach '{path}' on the Hub ({e.__class__.__name__})") from e
+            except GatedRepoError as e:
+                raise DatasetNotFoundError(
+                    f"Dataset '{path}' is a gated dataset on the Hub. Visit the dataset page at https://huggingface.co/datasets/{path} to ask for access."
+                ) from e
+            except RevisionNotFoundError as e:
+                raise DatasetNotFoundError(
+                    f"Revision '{revision}' doesn't exist for dataset '{path}' on the Hub."
+                ) from e
+            except RepositoryNotFoundError as e:
+                raise DatasetNotFoundError(f"Dataset '{path}' doesn't exist on the Hub or cannot be accessed.") from e
+
             if filename in [sibling.rfilename for sibling in dataset_info.siblings]:  # contains a dataset script
                 fs = HfFileSystem(endpoint=config.HF_ENDPOINT, token=download_config.token)
                 if _require_custom_configs or (revision and revision != "main"):

From ef8f7cee79ffb070d9b5190f21128fc523b3d3ee Mon Sep 17 00:00:00 2001
From: Wauplin <lucainp@gmail.com>
Date: Fri, 7 Jun 2024 13:37:42 +0200
Subject: [PATCH 2/3] fix test

---
 tests/test_load.py | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/tests/test_load.py b/tests/test_load.py
index c7c413ae10b..1986b3ccf0a 100644
--- a/tests/test_load.py
+++ b/tests/test_load.py
@@ -1048,13 +1048,9 @@ def test_load_dataset_from_hub(self):
             str(context.exception),
         )
         with self.assertRaises(DatasetNotFoundError) as context:
-            datasets.load_dataset("_dummy", revision="0.0.0")
+            datasets.load_dataset("HuggingFaceFW/fineweb-edu", revision="0.0.0")
         self.assertIn(
-            "Dataset '_dummy' doesn't exist on the Hub",
-            str(context.exception),
-        )
-        self.assertIn(
-            "at revision '0.0.0'",
+            "Revision '0.0.0' doesn't exist for dataset 'HuggingFaceFW/fineweb-edu' on the Hub.",
             str(context.exception),
         )
         for offline_simulation_mode in list(OfflineSimulationMode):

From 62350f5cddfe056c71ca2bb760250f76b5a49394 Mon Sep 17 00:00:00 2001
From: Wauplin <lucainp@gmail.com>
Date: Fri, 7 Jun 2024 13:44:44 +0200
Subject: [PATCH 3/3] Add custom message on GatedRepoError

---
 src/datasets/load.py | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/src/datasets/load.py b/src/datasets/load.py
index 216fcc12ebf..976d4942e4a 100644
--- a/src/datasets/load.py
+++ b/src/datasets/load.py
@@ -1844,9 +1844,12 @@ def dataset_module_factory(
             ) as e:
                 raise ConnectionError(f"Couldn't reach '{path}' on the Hub ({e.__class__.__name__})") from e
             except GatedRepoError as e:
-                raise DatasetNotFoundError(
-                    f"Dataset '{path}' is a gated dataset on the Hub. Visit the dataset page at https://huggingface.co/datasets/{path} to ask for access."
-                ) from e
+                message = f"Dataset '{path}' is a gated dataset on the Hub."
+                if "401 Client Error" in str(e):
+                    message += " You must be authenticated to access it."
+                elif "403 Client Error" in str(e):
+                    message += f" Visit the dataset page at https://huggingface.co/datasets/{path} to ask for access."
+                raise DatasetNotFoundError(message) from e
             except RevisionNotFoundError as e:
                 raise DatasetNotFoundError(
                     f"Revision '{revision}' doesn't exist for dataset '{path}' on the Hub."