From 5e84e5b41c9404dc1846a324c059988459182c3e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Danie=CC=88l=20de=20Kok?= <me@danieldk.eu>
Date: Thu, 19 Jan 2023 11:24:11 +0100
Subject: [PATCH] Only strip newline/carriage return

---
 spacy/training/corpus.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/spacy/training/corpus.py b/spacy/training/corpus.py
index b43b31c99..d626ad0e0 100644
--- a/spacy/training/corpus.py
+++ b/spacy/training/corpus.py
@@ -318,7 +318,7 @@ class PlainTextCorpus:
         for loc in walk_corpus(self.path, ".txt"):
             with open(loc, encoding="utf-8") as f:
                 for text in f:
-                    text = text.strip()
+                    text = text.rstrip("\r\n")
                     if len(text):
                         doc = nlp.make_doc(text)
                         if self.min_length >= 1 and len(doc) < self.min_length: