From f33381c4b0468544123ff05295033da7cc4bf61f Mon Sep 17 00:00:00 2001
From: Radek Czajka <radoslaw.czajka@nowoczesnapolska.org.pl>
Date: Thu, 2 Dec 2010 14:43:03 +0100
Subject: [PATCH] strip BOM
---
librarian/epub.py | 3 ++-
librarian/parser.py | 2 ++
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/librarian/epub.py b/librarian/epub.py
index e25ce8f..3bdd1cd 100644
--- a/librarian/epub.py
+++ b/librarian/epub.py
@@ -82,7 +82,8 @@ def replace_characters(node):
def replace_chars(text):
if text is None:
return None
- return text.replace("---", u"\u2014")\
+ return text.replace(u"\ufeff", u"")\
+ .replace("---", u"\u2014")\
.replace("--", u"\u2013")\
.replace(",,", u"\u201E")\
.replace('"', u"\u201D")\
diff --git a/librarian/parser.py b/librarian/parser.py
index 3f9f710..341eaf8 100644
--- a/librarian/parser.py
+++ b/librarian/parser.py
@@ -57,6 +57,8 @@ class WLDocument(object):
if not isinstance(data, unicode):
data = data.decode('utf-8')
+ data = data.replace(u'\ufeff', '')
+
if swap_endlines:
sub = u'<br/>'
if preserve_lines:
--
2.20.1