From 20f4e43044230e0c4e6c39b2069598e9039fe6f8 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Tue, 2 Mar 2021 08:50:22 +0530
Subject: [PATCH] PDF input: Replace U+2029 with spaces. See #1917386 (search &
 replace doesnt work with "newlines" in PDF to MOBI conversion)

---
 src/calibre/ebooks/pdf/pdftohtml.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/calibre/ebooks/pdf/pdftohtml.py b/src/calibre/ebooks/pdf/pdftohtml.py
index 02c610536b..e823e834bf 100644
--- a/src/calibre/ebooks/pdf/pdftohtml.py
+++ b/src/calibre/ebooks/pdf/pdftohtml.py
@@ -101,7 +101,7 @@ def pdftohtml(output_dir, pdf_path, no_images, as_xml=False):
                 raw = re.sub(r'<a id="(\d+)"', r'<a id="p\1"', raw, flags=re.I)
                 raw = re.sub(r'<a href="index.html#(\d+)"', r'<a href="#p\1"', raw, flags=re.I)
                 raw = xml_replace_entities(raw)
-                raw = raw.replace('\u00a0', ' ')
+                raw = re.sub('[\u00a0\u2029]', ' ', raw)
 
                 i.write(raw.encode('utf-8'))