include; table - better character support
authorFred <fred@ash.tree.se>
Mon, 13 Feb 2017 20:07:28 +0000 (21:07 +0100)
committerFred <fred@ash.tree.se>
Mon, 13 Feb 2017 20:07:28 +0000 (21:07 +0100)
adding codecs to table parsing, enabling utf-8 support

xinclude/table.py

index f3386617060b15fe1006a00a1472c624da79b895..ab6642717fcdf4bda3004c7ac6a32aaf09a78d5f 100755 (executable)
@@ -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):