treemanifest: don't iterate entire matching submanifests on match()
Before 2773540c3650 (match: remove unnecessary optimization where
visitdir() returns 'all', 2015-05-06), match.visitdir() used to return
the special value 'all' to indicate that it was known that all
subdirectories would also be included in the match. The purpose for
that value was to avoid calling the matcher on all the paths. It
turned out that calling the matcher was not a problem, so the special
return value was removed and the code was simplified. However, if we
use the same special value for not just avoiding calling the matcher
on each file, but to avoid iterating over each file, it's a much
bigger win. On commands like
hg st --rev .^ --rev . dom/
we run the matcher (dom/) on the two manifests, then diff the narrowed
manifest. If the size of the match is much larger than the size of the
diff, this is wasteful. In the above case, we would end up iterating
over the 15k-or-so files in dom/ for each of the manifests, only to
later discover that they are mostly the same. This means that runningt
the command above is usually slower than getting the status for the
entire repo, because that code avoids calling treemanifest.match() and
only calls treemanifest.diff(), which loads only what's needed for the
diff.
Let's fix this by reintroducing the 'all' value in match.visitdir()
and making treemanifest.match() return a lazy copy of the manifest
from dom/ and down (in the above case). This speeds up the above
command on the Firefox repo from 0.357s to 0.137s (best of 5). The
wider the match, the bigger the speedup.
# progress.py progress bars related code
#
# Copyright (C) 2010 Augie Fackler <durin42@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
import sys
import threading
import time
from .i18n import _
from . import encoding
def spacejoin(*args):
return ' '.join(s for s in args if s)
def shouldprint(ui):
return not (ui.quiet or ui.plain()) and (
ui._isatty(sys.stderr) or ui.configbool('progress', 'assume-tty'))
def fmtremaining(seconds):
"""format a number of remaining seconds in human readable way
This will properly display seconds, minutes, hours, days if needed"""
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._refreshlock = threading.Lock()
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.curtopic = None
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 - 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()))
if self.printed:
# force immediate re-paint of progress bar
self.lastprint = 0
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]
# experimental config: progress.estimate
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 _oktoprint(self, now):
'''Check if conditions are met to print - e.g. changedelay elapsed'''
if (self.lasttopic is None # first time we printed
# not a topic change
or self.curtopic == self.lasttopic
# it's been long enough we should print anyway
or now - self.lastprint >= self.changedelay):
return True
else:
return False
def progress(self, topic, pos, item='', unit='', total=None):
now = time.time()
self._refreshlock.acquire()
try:
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
self.curtopic = topic
if now - self.lastprint >= self.refresh and self.topics:
if self._oktoprint(now):
self.lastprint = now
self.show(now, topic, *self.topicstates[topic])
finally:
self._refreshlock.release()