From: Fred Date: Mon, 13 Feb 2017 20:07:28 +0000 (+0100) Subject: include; table - better character support X-Git-Url: https://source.tree.se/git?p=treecutter.git;a=commitdiff_plain;h=71402ca816ab990338fb24867efec892d99cc856 include; table - better character support adding codecs to table parsing, enabling utf-8 support --- diff --git a/xinclude/table.py b/xinclude/table.py index f338661..ab66427 100755 --- a/xinclude/table.py +++ b/xinclude/table.py @@ -3,6 +3,7 @@ import sys import re +import codecs from urlparse import urlparse from lxml import etree @@ -24,9 +25,9 @@ class Table(object): self.cols = [] def parse(self): - f = file(self.tablefile, 'r') + f = codecs.open(self.tablefile, encoding='utf-8') for line in f: - c = line.split() + c = re.split(r'\t+', line.rstrip()) self.cols.append(c) def db_xml(self):