From 0b2147ac644596b66886f398012351641672ee54 Mon Sep 17 00:00:00 2001
From: Albert Villanova del Moral
<8515462+albertvillanova@users.noreply.github.com>
Date: Thu, 21 Dec 2023 15:43:35 +0100
Subject: [PATCH] Support commit_description parameter in push_to_hub (#6520)
Support commit_description param in push_to_hub
---
src/datasets/arrow_dataset.py | 8 ++++++++
src/datasets/dataset_dict.py | 8 ++++++++
2 files changed, 16 insertions(+)
diff --git a/src/datasets/arrow_dataset.py b/src/datasets/arrow_dataset.py
index 00f76338816..6ed7de81c12 100644
--- a/src/datasets/arrow_dataset.py
+++ b/src/datasets/arrow_dataset.py
@@ -5228,6 +5228,7 @@ def push_to_hub(
set_default: Optional[bool] = None,
split: Optional[str] = None,
commit_message: Optional[str] = None,
+ commit_description: Optional[str] = None,
private: Optional[bool] = False,
token: Optional[str] = None,
revision: Optional[str] = None,
@@ -5258,6 +5259,11 @@ def push_to_hub(
The name of the split that will be given to that dataset. Defaults to `self.split`.
commit_message (`str`, *optional*):
Message to commit while pushing. Will default to `"Upload dataset"`.
+ commit_description (`str`, *optional*):
+ Description of the commit that will be created.
+ Additionally, description of the PR if a PR is created (`create_pr` is True).
+
+
private (`bool`, *optional*, defaults to `False`):
Whether the dataset repository should be set to private or not. Only affects repository creation:
a repository that already exists will not be affected by that parameter.
@@ -5525,6 +5531,7 @@ def push_to_hub(
repo_id,
operations=additions + deletions,
commit_message=commit_message,
+ commit_description=commit_description,
token=token,
repo_type="dataset",
revision=revision,
@@ -5543,6 +5550,7 @@ def push_to_hub(
repo_id,
operations=operations,
commit_message=commit_message + f" (part {i:05d}-of-{num_commits:05d})",
+ commit_description=commit_description,
token=token,
repo_type="dataset",
revision=revision,
diff --git a/src/datasets/dataset_dict.py b/src/datasets/dataset_dict.py
index 3e912d64660..6ca6ec79a83 100644
--- a/src/datasets/dataset_dict.py
+++ b/src/datasets/dataset_dict.py
@@ -1559,6 +1559,7 @@ def push_to_hub(
config_name: str = "default",
set_default: Optional[bool] = None,
commit_message: Optional[str] = None,
+ commit_description: Optional[str] = None,
private: Optional[bool] = False,
token: Optional[str] = None,
revision: Optional[str] = None,
@@ -1589,6 +1590,11 @@ def push_to_hub(
named "default".
commit_message (`str`, *optional*):
Message to commit while pushing. Will default to `"Upload dataset"`.
+ commit_description (`str`, *optional*):
+ Description of the commit that will be created.
+ Additionally, description of the PR if a PR is created (`create_pr` is True).
+
+
private (`bool`, *optional*):
Whether the dataset repository should be set to private or not. Only affects repository creation:
a repository that already exists will not be affected by that parameter.
@@ -1802,6 +1808,7 @@ def push_to_hub(
repo_id,
operations=additions + deletions,
commit_message=commit_message,
+ commit_description=commit_description,
token=token,
repo_type="dataset",
revision=revision,
@@ -1820,6 +1827,7 @@ def push_to_hub(
repo_id,
operations=operations,
commit_message=commit_message + f" (part {i:05d}-of-{num_commits:05d})",
+ commit_description=commit_description,
token=token,
repo_type="dataset",
revision=revision,