From 96ac81c3421586dac287a1683d621c458a5d3acb Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Thu, 4 Feb 2010 09:10:01 -0700 Subject: [PATCH] RTF Input: Don't eat up the space after \u escaped characters --- src/calibre/ebooks/rtf2xml/tokenize.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/calibre/ebooks/rtf2xml/tokenize.py b/src/calibre/ebooks/rtf2xml/tokenize.py index 45887f33e7..ad12daa211 100755 --- a/src/calibre/ebooks/rtf2xml/tokenize.py +++ b/src/calibre/ebooks/rtf2xml/tokenize.py @@ -72,7 +72,7 @@ class Tokenize: return line def __compile_expressions(self): self.__ms_hex_exp = re.compile(r"\\\'(..)") - self.__utf_exp = re.compile(r"\\u(-?\d{3,6}) {0,1}") + self.__utf_exp = re.compile(r"\\u(-?\d{3,6})") self.__splitexp = re.compile(r"(\\[\\{}]|{|}|\\[^\s\\{}&]+(?:\s)?)") self.__par_exp = re.compile(r'\\$') self.__mixed_exp = re.compile(r"(\\[a-zA-Z]+\d+)(\D+)")