From 8915223714823074dae8d2950b92023e8e058cfa Mon Sep 17 00:00:00 2001 From: Parmeet Singh Bhatia Date: Sat, 29 Jan 2022 21:44:06 -0500 Subject: [PATCH] avoid BC breaking change in PennTreebank dataset --- torchtext/datasets/penntreebank.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/torchtext/datasets/penntreebank.py b/torchtext/datasets/penntreebank.py index 06d1f0401f..602a9477b7 100644 --- a/torchtext/datasets/penntreebank.py +++ b/torchtext/datasets/penntreebank.py @@ -50,4 +50,4 @@ def PennTreebank(root, split: Union[Tuple[str], str]): cache_dp = HttpReader(cache_dp).end_caching(mode="wb", same_filepath_fn=True) data_dp = FileOpener(cache_dp, mode="r") # remove single leading and trailing space from the dataset - return data_dp.readlines(return_path=False).map(lambda t: t.strip()) + return data_dp.readlines(return_path=False, strip_newline=False)