churn: compute padding with unicode strings
Most UTF-8 aware terminals convert multibyte sequences into a single displayed
characters. Because the first column is padded by counting bytes, the second
column is not perfectly aligned in the presence of non ASCII characters.
--- a/hgext/churn.py Thu Apr 17 19:39:04 2014 -0400
+++ b/hgext/churn.py Sat Apr 19 15:11:25 2014 +0200
@@ -10,6 +10,7 @@
from mercurial.i18n import _
from mercurial import patch, cmdutil, scmutil, util, templater, commands
+from mercurial import encoding
import os
import time, datetime
@@ -124,7 +125,7 @@
Aliases will be split from the rightmost "=".
'''
def pad(s, l):
- return (s + " " * l)[:l]
+ return s + " " * (l - encoding.colwidth(s))
amap = {}
aliases = opts.get('aliases')
--- a/tests/test-churn.t Thu Apr 17 19:39:04 2014 -0400
+++ b/tests/test-churn.t Sat Apr 19 15:11:25 2014 +0200
@@ -159,4 +159,16 @@
user4@x.com 2 *****************************
with space 1 **************
+Test multibyte sequences in names
+
+ $ echo bar >> bar
+ $ hg --encoding utf-8 ci -m'changed bar' -u 'El Niño <nino@x.com>'
+ $ hg --encoding utf-8 churn -ct '{author|person}'
+ user1 4 **********************************************************
+ user3 3 ********************************************
+ user2 2 *****************************
+ user4 2 *****************************
+ El Ni\xc3\xb1o 1 *************** (esc)
+ with space 1 ***************
+
$ cd ..