progress: use 'encoding.colwidth' to get column width of items correctly

Before this patch, 'progress' extension applies 'len' on byte sequence
to get column width of it, but it causes incorrect result, when length
of byte sequence and columns in display are different from each other
in multi-byte characters.

This patch uses 'encoding.colwidth' to get column width of items in
output line correctly, even if it contains multi-byte characters.

hgext/progress.py

@@ -1,305 +1,305
 # progress.py show progress bars for some actions
 #
 # Copyright (C) 2010 Augie Fackler <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """show progress bars for some actions
 
 This extension uses the progress information logged by hg commands
 to draw progress bars that are as informative as possible. Some progress
 bars only offer indeterminate information, while others have a definite
 end point.
 
 The following settings are available::
 
   [progress]
   delay = 3 # number of seconds (float) before showing the progress bar
   changedelay = 1 # changedelay: minimum delay before showing a new topic.
                   # If set to less than 3 * refresh, that value will
                   # be used instead.
   refresh = 0.1 # time in seconds between refreshes of the progress bar
   format = topic bar number estimate # format of the progress bar
   width = <none> # if set, the maximum width of the progress information
                  # (that is, min(width, term width) will be used)
   clear-complete = True # clear the progress bar after it's done
   disable = False # if true, don't show a progress bar
   assume-tty = False # if true, ALWAYS show a progress bar, unless
                      # disable is given
 
 Valid entries for the format field are topic, bar, number, unit,
 estimate, speed, and item. item defaults to the last 20 characters of
 the item, but this can be changed by adding either ``-<num>`` which
 would take the last num characters, or ``+<num>`` for the first num
 characters.
 """
 
 import sys
 import time
 
 from mercurial.i18n import _
 testedwith = 'internal'
 
 from mercurial import encoding
 
 def spacejoin(*args):
     return ' '.join(s for s in args if s)
 
 def shouldprint(ui):
     return not ui.plain() and (ui._isatty(sys.stderr) or
                                ui.configbool('progress', 'assume-tty'))
 
 def fmtremaining(seconds):
     if seconds < 60:
         # i18n: format XX seconds as "XXs"
         return _("%02ds") % (seconds)
     minutes = seconds // 60
     if minutes < 60:
         seconds -= minutes * 60
         # i18n: format X minutes and YY seconds as "XmYYs"
         return _("%dm%02ds") % (minutes, seconds)
     # we're going to ignore seconds in this case
     minutes += 1
     hours = minutes // 60
     minutes -= hours * 60
     if hours < 30:
         # i18n: format X hours and YY minutes as "XhYYm"
         return _("%dh%02dm") % (hours, minutes)
     # we're going to ignore minutes in this case
     hours += 1
     days = hours // 24
     hours -= days * 24
     if days < 15:
         # i18n: format X days and YY hours as "XdYYh"
         return _("%dd%02dh") % (days, hours)
     # we're going to ignore hours in this case
     days += 1
     weeks = days // 7
     days -= weeks * 7
     if weeks < 55:
         # i18n: format X weeks and YY days as "XwYYd"
         return _("%dw%02dd") % (weeks, days)
     # we're going to ignore days and treat a year as 52 weeks
     weeks += 1
     years = weeks // 52
     weeks -= years * 52
     # i18n: format X years and YY weeks as "XyYYw"
     return _("%dy%02dw") % (years, weeks)
 
 class progbar(object):
     def __init__(self, ui):
         self.ui = ui
         self.resetstate()
 
     def resetstate(self):
         self.topics = []
         self.topicstates = {}
         self.starttimes = {}
         self.startvals = {}
         self.printed = False
         self.lastprint = time.time() + float(self.ui.config(
             'progress', 'delay', default=3))
         self.lasttopic = None
         self.indetcount = 0
         self.refresh = float(self.ui.config(
             'progress', 'refresh', default=0.1))
         self.changedelay = max(3 * self.refresh,
                                float(self.ui.config(
                                    'progress', 'changedelay', default=1)))
         self.order = self.ui.configlist(
             'progress', 'format',
             default=['topic', 'bar', 'number', 'estimate'])
 
     def show(self, now, topic, pos, item, unit, total):
         if not shouldprint(self.ui):
             return
         termwidth = self.width()
         self.printed = True
         head = ''
         needprogress = False
         tail = ''
         for indicator in self.order:
             add = ''
             if indicator == 'topic':
                 add = topic
             elif indicator == 'number':
                 if total:
                     add = ('% ' + str(len(str(total))) +
                            's/%s') % (pos, total)
                 else:
                     add = str(pos)
             elif indicator.startswith('item') and item:
                 slice = 'end'
                 if '-' in indicator:
                     wid = int(indicator.split('-')[1])
                 elif '+' in indicator:
                     slice = 'beginning'
                     wid = int(indicator.split('+')[1])
                 else:
                     wid = 20
                 if slice == 'end':
                     add = encoding.trim(item, wid, leftside=True)
                 else:
                     add = encoding.trim(item, wid)
-                add += (wid - len(add)) * ' '
+                add += (wid - encoding.colwidth(add)) * ' '
             elif indicator == 'bar':
                 add = ''
                 needprogress = True
             elif indicator == 'unit' and unit:
                 add = unit
             elif indicator == 'estimate':
                 add = self.estimate(topic, pos, total, now)
             elif indicator == 'speed':
                 add = self.speed(topic, pos, unit, now)
             if not needprogress:
                 head = spacejoin(head, add)
             else:
                 tail = spacejoin(tail, add)
         if needprogress:
             used = 0
             if head:
                 used += encoding.colwidth(head) + 1
             if tail:
                 used += encoding.colwidth(tail) + 1
             progwidth = termwidth - used - 3
             if total and pos <= total:
                 amt = pos * progwidth // total
                 bar = '=' * (amt - 1)
                 if amt > 0:
                     bar += '>'
                 bar += ' ' * (progwidth - amt)
             else:
                 progwidth -= 3
                 self.indetcount += 1
                 # mod the count by twice the width so we can make the
                 # cursor bounce between the right and left sides
                 amt = self.indetcount % (2 * progwidth)
                 amt -= progwidth
                 bar = (' ' * int(progwidth - abs(amt)) + '<=>' +
                        ' ' * int(abs(amt)))
             prog = ''.join(('[', bar , ']'))
             out = spacejoin(head, prog, tail)
         else:
             out = spacejoin(head, tail)
         sys.stderr.write('\r' + encoding.trim(out, termwidth))
         self.lasttopic = topic
         sys.stderr.flush()
 
     def clear(self):
         if not shouldprint(self.ui):
             return
         sys.stderr.write('\r%s\r' % (' ' * self.width()))
 
     def complete(self):
         if not shouldprint(self.ui):
             return
         if self.ui.configbool('progress', 'clear-complete', default=True):
             self.clear()
         else:
             sys.stderr.write('\n')
         sys.stderr.flush()
 
     def width(self):
         tw = self.ui.termwidth()
         return min(int(self.ui.config('progress', 'width', default=tw)), tw)
 
     def estimate(self, topic, pos, total, now):
         if total is None:
             return ''
         initialpos = self.startvals[topic]
         target = total - initialpos
         delta = pos - initialpos
         if delta > 0:
             elapsed = now - self.starttimes[topic]
             if elapsed > float(
                 self.ui.config('progress', 'estimate', default=2)):
                 seconds = (elapsed * (target - delta)) // delta + 1
                 return fmtremaining(seconds)
         return ''
 
     def speed(self, topic, pos, unit, now):
         initialpos = self.startvals[topic]
         delta = pos - initialpos
         elapsed = now - self.starttimes[topic]
         if elapsed > float(
             self.ui.config('progress', 'estimate', default=2)):
             return _('%d %s/sec') % (delta / elapsed, unit)
         return ''
 
     def progress(self, topic, pos, item='', unit='', total=None):
         now = time.time()
         if pos is None:
             self.starttimes.pop(topic, None)
             self.startvals.pop(topic, None)
             self.topicstates.pop(topic, None)
             # reset the progress bar if this is the outermost topic
             if self.topics and self.topics[0] == topic and self.printed:
                 self.complete()
                 self.resetstate()
             # truncate the list of topics assuming all topics within
             # this one are also closed
             if topic in self.topics:
                 self.topics = self.topics[:self.topics.index(topic)]
                 # reset the last topic to the one we just unwound to,
                 # so that higher-level topics will be stickier than
                 # lower-level topics
                 if self.topics:
                     self.lasttopic = self.topics[-1]
                 else:
                     self.lasttopic = None
         else:
             if topic not in self.topics:
                 self.starttimes[topic] = now
                 self.startvals[topic] = pos
                 self.topics.append(topic)
             self.topicstates[topic] = pos, item, unit, total
             if now - self.lastprint >= self.refresh and self.topics:
                 if (self.lasttopic is None # first time we printed
                     # not a topic change
                     or topic == self.lasttopic
                     # it's been long enough we should print anyway
                     or now - self.lastprint >= self.changedelay):
                     self.lastprint = now
                     self.show(now, topic, *self.topicstates[topic])
 
 _singleton = None
 
 def uisetup(ui):
     global _singleton
     class progressui(ui.__class__):
         _progbar = None
 
         def _quiet(self):
             return self.debugflag or self.quiet
 
         def progress(self, *args, **opts):
             if not self._quiet():
                 self._progbar.progress(*args, **opts)
             return super(progressui, self).progress(*args, **opts)
 
         def write(self, *args, **opts):
             if not self._quiet() and self._progbar.printed:
                 self._progbar.clear()
             return super(progressui, self).write(*args, **opts)
 
         def write_err(self, *args, **opts):
             if not self._quiet() and self._progbar.printed:
                 self._progbar.clear()
             return super(progressui, self).write_err(*args, **opts)
 
     # Apps that derive a class from ui.ui() can use
     # setconfig('progress', 'disable', 'True') to disable this extension
     if ui.configbool('progress', 'disable'):
         return
     if shouldprint(ui) and not ui.debugflag and not ui.quiet:
         ui.__class__ = progressui
         # we instantiate one globally shared progress bar to avoid
         # competing progress bars when multiple UI objects get created
         if not progressui._progbar:
             if _singleton is None:
                 _singleton = progbar(ui)
             progressui._progbar = _singleton
 
 def reposetup(ui, repo):
     uisetup(repo.ui)

tests/test-progress.t

@@ -1,336 +1,339
 
   $ cat > loop.py <<EOF
   > from mercurial import cmdutil, commands
   > import time
   > 
   > cmdtable = {}
   > command = cmdutil.command(cmdtable)
   > 
   > class incrementingtime(object):
   >     def __init__(self):
   >         self._time = 0.0
   >     def __call__(self):
   >         self._time += 0.25
   >         return self._time
   > time.time = incrementingtime()
   > 
   > @command('loop',
   >     [('', 'total', '', 'override for total'),
   >     ('', 'nested', False, 'show nested results'),
   >     ('', 'parallel', False, 'show parallel sets of results')],
   >     'hg loop LOOPS',
   >     norepo=True)
   > def loop(ui, loops, **opts):
   >     loops = int(loops)
   >     total = None
   >     if loops >= 0:
   >         total = loops
   >     if opts.get('total', None):
   >         total = int(opts.get('total'))
   >     nested = False
   >     if opts.get('nested', None):
   >         nested = True
   >     loops = abs(loops)
   > 
   >     for i in range(loops):
   >         ui.progress(topiclabel, i, getloopitem(i), 'loopnum', total)
   >         if opts.get('parallel'):
   >             ui.progress('other', i, 'other.%d' % i, 'othernum', total)
   >         if nested:
   >             nested_steps = 2
   >             if i and i % 4 == 0:
   >                 nested_steps = 5
   >             for j in range(nested_steps):
   >                 ui.progress(
   >                   'nested', j, 'nested.%d' % j, 'nestnum', nested_steps)
   >             ui.progress(
   >               'nested', None, 'nested.done', 'nestnum', nested_steps)
   >     ui.progress(topiclabel, None, 'loop.done', 'loopnum', total)
   > 
   > topiclabel = 'loop'
   > def getloopitem(i):
   >     return 'loop.%d' % i
   > 
   > EOF
 
   $ cp $HGRCPATH $HGRCPATH.orig
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "progress=" >> $HGRCPATH
   $ echo "loop=`pwd`/loop.py" >> $HGRCPATH
   $ echo "[progress]" >> $HGRCPATH
   $ echo "format = topic bar number" >> $HGRCPATH
   $ echo "assume-tty=1" >> $HGRCPATH
   $ echo "width=60" >> $HGRCPATH
 
 test default params, display nothing because of delay
 
   $ hg -y loop 3
   $ echo "delay=0" >> $HGRCPATH
   $ echo "refresh=0" >> $HGRCPATH
 
 test with delay=0, refresh=0
 
   $ hg -y loop 3
   \r (no-eol) (esc)
   loop [                                                ] 0/3\r (no-eol) (esc)
   loop [===============>                                ] 1/3\r (no-eol) (esc)
   loop [===============================>                ] 2/3\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 
 test nested short-lived topics (which shouldn't display with nestdelay):
 
   $ hg -y loop 3 --nested
   \r (no-eol) (esc)
   loop [                                                ] 0/3\r (no-eol) (esc)
   loop [===============>                                ] 1/3\r (no-eol) (esc)
   loop [===============================>                ] 2/3\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 Test nested long-lived topic which has the same name as a short-lived
 peer. We shouldn't get stuck showing the short-lived inner steps, and
 should go back to skipping the inner steps when the slow nested step
 finishes.
 
   $ hg -y loop 7 --nested
   \r (no-eol) (esc)
   loop [                                                ] 0/7\r (no-eol) (esc)
   loop [=====>                                          ] 1/7\r (no-eol) (esc)
   loop [============>                                   ] 2/7\r (no-eol) (esc)
   loop [===================>                            ] 3/7\r (no-eol) (esc)
   loop [==========================>                     ] 4/7\r (no-eol) (esc)
   nested [==========================>                   ] 3/5\r (no-eol) (esc)
   nested [===================================>          ] 4/5\r (no-eol) (esc)
   loop [=================================>              ] 5/7\r (no-eol) (esc)
   loop [========================================>       ] 6/7\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 
   $ hg --config progress.changedelay=0 -y loop 3 --nested
   \r (no-eol) (esc)
   loop [                                                ] 0/3\r (no-eol) (esc)
   nested [                                              ] 0/2\r (no-eol) (esc)
   nested [======================>                       ] 1/2\r (no-eol) (esc)
   loop [===============>                                ] 1/3\r (no-eol) (esc)
   nested [                                              ] 0/2\r (no-eol) (esc)
   nested [======================>                       ] 1/2\r (no-eol) (esc)
   loop [===============================>                ] 2/3\r (no-eol) (esc)
   nested [                                              ] 0/2\r (no-eol) (esc)
   nested [======================>                       ] 1/2\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 
 test two topics being printed in parallel (as when we're doing a local
 --pull clone, where you get the unbundle and bundle progress at the
 same time):
   $ hg loop 3 --parallel
   \r (no-eol) (esc)
   loop [                                                ] 0/3\r (no-eol) (esc)
   loop [===============>                                ] 1/3\r (no-eol) (esc)
   loop [===============================>                ] 2/3\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 test refresh is taken in account
 
   $ hg -y --config progress.refresh=100 loop 3
 
 test format options 1
 
   $ hg -y --config 'progress.format=number topic item+2' loop 2
   \r (no-eol) (esc)
   0/2 loop lo\r (no-eol) (esc)
   1/2 loop lo\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 test format options 2
 
   $ hg -y --config 'progress.format=number item-3 bar' loop 2
   \r (no-eol) (esc)
   0/2 p.0 [                                                 ]\r (no-eol) (esc)
   1/2 p.1 [=======================>                         ]\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 test format options and indeterminate progress
 
   $ hg -y --config 'progress.format=number item bar' loop -- -2
   \r (no-eol) (esc)
   0 loop.0               [ <=>                              ]\r (no-eol) (esc)
   1 loop.1               [  <=>                             ]\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 make sure things don't fall over if count > total
 
   $ hg -y loop --total 4 6
   \r (no-eol) (esc)
   loop [                                                ] 0/4\r (no-eol) (esc)
   loop [===========>                                    ] 1/4\r (no-eol) (esc)
   loop [=======================>                        ] 2/4\r (no-eol) (esc)
   loop [===================================>            ] 3/4\r (no-eol) (esc)
   loop [===============================================>] 4/4\r (no-eol) (esc)
   loop [ <=>                                            ] 5/4\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 test immediate progress completion
 
   $ hg -y loop 0
 
 test delay time estimates
 
   $ cat > mocktime.py <<EOF
   > import os
   > import time
   > 
   > class mocktime(object):
   >     def __init__(self, increment):
   >         self.time = 0
   >         self.increment = increment
   >     def __call__(self):
   >         self.time += self.increment
   >         return self.time
   > 
   > def uisetup(ui):
   >     time.time = mocktime(int(os.environ.get('MOCKTIME', '11')))
   > EOF
 
   $ cp $HGRCPATH.orig $HGRCPATH
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "mocktime=`pwd`/mocktime.py" >> $HGRCPATH
   $ echo "progress=" >> $HGRCPATH
   $ echo "loop=`pwd`/loop.py" >> $HGRCPATH
   $ echo "[progress]" >> $HGRCPATH
   $ echo "assume-tty=1" >> $HGRCPATH
   $ echo "delay=25" >> $HGRCPATH
   $ echo "width=60" >> $HGRCPATH
 
   $ hg -y loop 8
   \r (no-eol) (esc)
   loop [=========>                                ] 2/8 1m07s\r (no-eol) (esc)
   loop [===============>                            ] 3/8 56s\r (no-eol) (esc)
   loop [=====================>                      ] 4/8 45s\r (no-eol) (esc)
   loop [==========================>                 ] 5/8 34s\r (no-eol) (esc)
   loop [================================>           ] 6/8 23s\r (no-eol) (esc)
   loop [=====================================>      ] 7/8 12s\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
   $ MOCKTIME=10000 hg -y loop 4
   \r (no-eol) (esc)
   loop [                                                ] 0/4\r (no-eol) (esc)
   loop [=========>                                ] 1/4 8h21m\r (no-eol) (esc)
   loop [====================>                     ] 2/4 5h34m\r (no-eol) (esc)
   loop [==============================>           ] 3/4 2h47m\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
   $ MOCKTIME=1000000 hg -y loop 4
   \r (no-eol) (esc)
   loop [                                                ] 0/4\r (no-eol) (esc)
   loop [=========>                                ] 1/4 5w00d\r (no-eol) (esc)
   loop [====================>                     ] 2/4 3w03d\r (no-eol) (esc)
   loop [=============================>           ] 3/4 11d14h\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 
   $ MOCKTIME=14000000 hg -y loop 4
   \r (no-eol) (esc)
   loop [                                                ] 0/4\r (no-eol) (esc)
   loop [=========>                                ] 1/4 1y18w\r (no-eol) (esc)
   loop [===================>                     ] 2/4 46w03d\r (no-eol) (esc)
   loop [=============================>           ] 3/4 23w02d\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 Time estimates should not fail when there's no end point:
   $ hg -y loop -- -4
   \r (no-eol) (esc)
   loop [ <=>                                              ] 2\r (no-eol) (esc)
   loop [  <=>                                             ] 3\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 test line trimming by '[progress] width', when progress topic contains
 multi-byte characters, of which length of byte sequence and columns in
 display are different from each other.
 
   $ cp $HGRCPATH.orig $HGRCPATH
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > progress=
   > loop=`pwd`/loop.py
   > [progress]
   > assume-tty = 1
   > delay = 0
   > refresh = 0
   > EOF
 
   $ rm -f loop.pyc
   $ cat >> loop.py <<EOF
   > # use non-ascii characters as topic label of progress
   > # 2 x 4 = 8 columns, but 3 x 4 = 12 bytes
   > topiclabel = u'\u3042\u3044\u3046\u3048'.encode('utf-8')
   > EOF
 
   $ cat >> $HGRCPATH <<EOF
   > [progress]
   > format = topic number
   > width= 12
   > EOF
 
   $ hg --encoding utf-8 -y loop --total 3 3
   \r (no-eol) (esc)
   \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88 0/3\r (no-eol) (esc)
   \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88 1/3\r (no-eol) (esc)
   \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88 2/3\r (no-eol) (esc)
               \r (no-eol) (esc)
 
 test calculation of bar width, when progress topic contains multi-byte
 characters, of which length of byte sequence and columns in display
 are different from each other.
 
   $ cat >> $HGRCPATH <<EOF
   > [progress]
   > format = topic bar
   > width= 21
   > # progwidth should be 9 (= 21 - (8+1) - 3)
   > EOF
 
   $ hg --encoding utf-8 -y loop --total 3 3
   \r (no-eol) (esc)
   \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88 [         ]\r (no-eol) (esc)
   \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88 [==>      ]\r (no-eol) (esc)
   \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88 [=====>   ]\r (no-eol) (esc)
                        \r (no-eol) (esc)
 
 test triming progress items, when they contain multi-byte characters,
 of which length of byte sequence and columns in display are different
 from each other.
 
   $ rm -f loop.pyc
   $ cat >> loop.py <<EOF
   > # use non-ascii characters as loop items of progress
   > loopitems = [
+  >     u'\u3042\u3044'.encode('utf-8'), # 2 x 2 = 4 columns
   >     u'\u3042\u3044\u3046'.encode('utf-8'), # 2 x 3 = 6 columns
   >     u'\u3042\u3044\u3046\u3048'.encode('utf-8'), # 2 x 4 = 8 columns
   > ]
   > def getloopitem(i):
   >     return loopitems[i % len(loopitems)]
   > EOF
 
   $ cat >> $HGRCPATH <<EOF
   > [progress]
   > # trim at tail side
   > format = item+6
   > EOF
 
-  $ hg --encoding utf-8 -y loop --total 2 2
+  $ hg --encoding utf-8 -y loop --total 3 3
   \r (no-eol) (esc)
+  \xe3\x81\x82\xe3\x81\x84  \r (no-eol) (esc)
   \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\r (no-eol) (esc)
   \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\r (no-eol) (esc)
                        \r (no-eol) (esc)
 
   $ cat >> $HGRCPATH <<EOF
   > [progress]
   > # trim at left side
   > format = item-6
   > EOF
 
-  $ hg --encoding utf-8 -y loop --total 2 2
+  $ hg --encoding utf-8 -y loop --total 3 3
   \r (no-eol) (esc)
+  \xe3\x81\x82\xe3\x81\x84  \r (no-eol) (esc)
   \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\r (no-eol) (esc)
   \xe3\x81\x84\xe3\x81\x86\xe3\x81\x88\r (no-eol) (esc)
                        \r (no-eol) (esc)