From f67fbefb5e7561416417800535761dc0607e1885 Mon Sep 17 00:00:00 2001
From: Danielle McLean <dani@00dani.me>
Date: Sat, 21 Aug 2021 15:09:59 +1000
Subject: [PATCH] Preserve newlines in toot corpus

The original code was already trying to do this, but in a way that
Beautiful Soup ended up stripping out. This way preserves the newlines
properly, which will prevent the bot from smooshing together words
accidentally.
---
 functions.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/functions.py b/functions.py
index d9e38cb..c290358 100644
--- a/functions.py
+++ b/functions.py
@@ -80,10 +80,10 @@ def extract_toot(toot):
 	toot = html.unescape(toot)  # convert HTML escape codes to text
 	soup = BeautifulSoup(toot, "html.parser")
 	for lb in soup.select("br"):  # replace <br> with linebreak
-		lb.name = "\n"
+		lb.append('\n')
 
 	for p in soup.select("p"):  # ditto for <p>
-		p.name = "\n"
+		p.append('\n\n')
 
 	for ht in soup.select("a.hashtag"):  # convert hashtags from links to text
 		ht.unwrap()