diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py
index e58bbca1bd..95f832c76a 100644
--- a/src/calibre/ebooks/conversion/utils.py
+++ b/src/calibre/ebooks/conversion/utils.py
@@ -342,11 +342,9 @@ class HeuristicProcessor(object):
return content
def txt_process(self, match):
- from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \
- separate_paragraphs_single_line
+ from calibre.ebooks.txt.processor import convert_basic, separate_paragraphs_single_line
content = match.group('text')
content = separate_paragraphs_single_line(content)
- content = preserve_spaces(content)
content = convert_basic(content, epub_split_size_kb=0)
return content
@@ -356,6 +354,8 @@ class HeuristicProcessor(object):
self.log.debug("Running Text Processing")
outerhtml = re.compile(r'.*?(?<=)(?P.*?)
', re.IGNORECASE|re.DOTALL)
html = outerhtml.sub(self.txt_process, html)
+ from calibre.ebooks.conversion.preprocess import convert_entities
+ html = re.sub(r'&(\S+?);', convert_entities, html)
else:
# Add markup naively
# TODO - find out if there are cases where there are more than one tag or
diff --git a/src/calibre/ebooks/lit/input.py b/src/calibre/ebooks/lit/input.py
index 9ccbba543f..4008f15d53 100644
--- a/src/calibre/ebooks/lit/input.py
+++ b/src/calibre/ebooks/lit/input.py
@@ -37,13 +37,12 @@ class LITInput(InputFormatPlugin):
body = body[0]
if len(body) == 1 and body[0].tag == XHTML('pre'):
pre = body[0]
- from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \
+ from calibre.ebooks.txt.processor import convert_basic, \
separate_paragraphs_single_line
from calibre.ebooks.chardet import xml_to_unicode
from lxml import etree
import copy
html = separate_paragraphs_single_line(pre.text)
- html = preserve_spaces(html)
html = convert_basic(html).replace('',
''%XHTML_NS)
html = xml_to_unicode(html, strip_encoding_pats=True,