From 05834f0b4212d4032ee2ff759ceaf614f294f9ed Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Fri, 30 Aug 2019 08:03:08 +0530
Subject: [PATCH] PDF Input: Fix < and > in the text not being correctly
 handled

---
 src/calibre/ebooks/pdf/pdftohtml.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/calibre/ebooks/pdf/pdftohtml.py b/src/calibre/ebooks/pdf/pdftohtml.py
index ac4d523da2..e7a0094266 100644
--- a/src/calibre/ebooks/pdf/pdftohtml.py
+++ b/src/calibre/ebooks/pdf/pdftohtml.py
@@ -11,7 +11,7 @@ import shutil
 import subprocess
 import sys
 
-from calibre import CurrentDir, replace_entities, prints
+from calibre import CurrentDir, xml_replace_entities, prints
 from calibre.constants import (
     filesystem_encoding, isbsd, islinux, isosx, ispy3, iswindows
 )
@@ -106,7 +106,7 @@ def pdftohtml(output_dir, pdf_path, no_images, as_xml=False):
                 raw = re.sub(r'<a\s+name=(\d+)', r'<a id="\1"', raw, flags=re.I)
                 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 = replace_entities(raw)
+                raw = xml_replace_entities(raw)
                 raw = raw.replace('\u00a0', ' ')
 
                 i.write(raw.encode('utf-8'))