hgext/win32text.py
author Augie Fackler <raf@durin42.com>
Fri, 17 Oct 2014 13:52:10 -0400
changeset 23031 3c0983cc279e
parent 20624 23146e4d9cee
child 25186 80c5b2666a96
permissions -rw-r--r--
i18n: cache the result of every gettext call In looking at profiler output for 'hg log' on mozilla-central, I noticed we spent a _huge_ amount of time in gettext relative to what it's doing. Caching provides a roughly 15% performance improvement even on repositories as small as hg. == hg repo on linux == Before: % cumulative self time seconds seconds name 5.05 0.19 0.19 i18n.py:62:gettext 4.84 0.18 0.18 revlog.py:88:decompress 2.95 0.17 0.11 changelog.py:201:node 2.32 0.09 0.09 ui.py:577:write 2.11 0.08 0.08 i18n.py:72:gettext 2.11 0.08 0.08 obsolete.py:196:_fm0readmarkers 1.89 0.07 0.07 obsolete.py:569:_load 1.68 0.63 0.06 localrepo.py:29:__get__ real 0m4.026s user 0m3.993s sys 0m0.034s After: % cumulative self time seconds seconds name 8.05 0.26 0.26 revlog.py:88:decompress 2.68 0.22 0.09 color.py:395:write 2.20 0.07 0.07 obsolete.py:196:_fm0readmarkers 1.95 0.06 0.06 obsolete.py:174:_fm0readmarkers 1.95 0.06 0.06 ui.py:577:write 1.95 0.06 0.06 util.py:1228:datestr 1.71 0.06 0.06 utf_8.py:16:decode 1.71 0.06 0.06 revlog.py:273:__len__ real 0m3.519s user 0m3.447s sys 0m0.073s == mozilla-central repo on linux == Before: % cumulative self time seconds seconds name 7.72 2.35 2.35 revlog.py:88:decompress 4.46 1.36 1.36 i18n.py:62:gettext 2.22 0.67 0.67 i18n.py:72:gettext 2.19 1.14 0.67 changelog.py:201:node 2.16 0.66 0.66 ui.py:577:write 1.96 0.60 0.60 utf_8.py:16:decode 1.93 1.97 0.59 color.py:395:write 1.85 0.81 0.56 changelog.py:136:tip real 0m30.822s user 0m30.660s sys 0m0.149s After: % cumulative self time seconds seconds name 9.82 2.49 2.49 revlog.py:88:decompress 2.67 1.31 0.68 localrepo.py:29:__get__ 2.57 0.65 0.65 utf_8.py:16:decode 2.48 1.01 0.63 changelog.py:201:node 2.10 0.82 0.53 changelog.py:136:tip 2.01 0.51 0.51 ui.py:577:write 1.91 0.49 0.49 util.py:1232:datestr 1.85 1.65 0.47 color.py:395:write real 0m25.619s user 0m25.446s sys 0m0.166s == cpython repo on os x = Before: % cumulative self time seconds seconds name 5.05 1.35 1.35 cmdutil.py:982:_show 4.59 1.22 1.22 revlog.py:274:__len__ 3.98 1.06 1.06 i18n.py:62:gettext 3.91 1.04 1.04 revlog.py:1016:revision 3.68 0.98 0.98 revlog.py:337:parents 3.45 0.92 0.92 revlog.py:88:decompress 2.91 0.78 0.78 revlog.py:309:rev 2.62 0.70 0.70 revlog.py:1033:revision real 0m30.414s user 0m28.145s sys 0m0.541s After: % cumulative self time seconds seconds name 7.98 1.66 1.66 cmdutil.py:982:_show 6.83 1.42 1.42 changelog.py:46:decodeextra 5.18 1.08 1.08 revlog.py:274:__len__ 3.94 0.82 0.82 revlog.py:1016:revision 3.41 0.71 0.71 revlog.py:309:rev 3.32 0.69 0.69 revlog.py:88:decompress 2.99 0.63 0.62 revlog.py:1033:revision 2.69 0.56 0.56 revlog.py:341:start real 0m22.811s user 0m21.883s sys 0m0.397s

# win32text.py - LF <-> CRLF/CR translation utilities for Windows/Mac users
#
#  Copyright 2005, 2007-2009 Matt Mackall <mpm@selenic.com> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''perform automatic newline conversion (DEPRECATED)

  Deprecation: The win32text extension requires each user to configure
  the extension again and again for each clone since the configuration
  is not copied when cloning.

  We have therefore made the ``eol`` as an alternative. The ``eol``
  uses a version controlled file for its configuration and each clone
  will therefore use the right settings from the start.

To perform automatic newline conversion, use::

  [extensions]
  win32text =
  [encode]
  ** = cleverencode:
  # or ** = macencode:

  [decode]
  ** = cleverdecode:
  # or ** = macdecode:

If not doing conversion, to make sure you do not commit CRLF/CR by accident::

  [hooks]
  pretxncommit.crlf = python:hgext.win32text.forbidcrlf
  # or pretxncommit.cr = python:hgext.win32text.forbidcr

To do the same check on a server to prevent CRLF/CR from being
pushed or pulled::

  [hooks]
  pretxnchangegroup.crlf = python:hgext.win32text.forbidcrlf
  # or pretxnchangegroup.cr = python:hgext.win32text.forbidcr
'''

from mercurial.i18n import _
from mercurial.node import short
from mercurial import util
import re

testedwith = 'internal'

# regexp for single LF without CR preceding.
re_single_lf = re.compile('(^|[^\r])\n', re.MULTILINE)

newlinestr = {'\r\n': 'CRLF', '\r': 'CR'}
filterstr = {'\r\n': 'clever', '\r': 'mac'}

def checknewline(s, newline, ui=None, repo=None, filename=None):
    # warn if already has 'newline' in repository.
    # it might cause unexpected eol conversion.
    # see issue 302:
    #   http://mercurial.selenic.com/bts/issue302
    if newline in s and ui and filename and repo:
        ui.warn(_('WARNING: %s already has %s line endings\n'
                  'and does not need EOL conversion by the win32text plugin.\n'
                  'Before your next commit, please reconsider your '
                  'encode/decode settings in \nMercurial.ini or %s.\n') %
                (filename, newlinestr[newline], repo.join('hgrc')))

def dumbdecode(s, cmd, **kwargs):
    checknewline(s, '\r\n', **kwargs)
    # replace single LF to CRLF
    return re_single_lf.sub('\\1\r\n', s)

def dumbencode(s, cmd):
    return s.replace('\r\n', '\n')

def macdumbdecode(s, cmd, **kwargs):
    checknewline(s, '\r', **kwargs)
    return s.replace('\n', '\r')

def macdumbencode(s, cmd):
    return s.replace('\r', '\n')

def cleverdecode(s, cmd, **kwargs):
    if not util.binary(s):
        return dumbdecode(s, cmd, **kwargs)
    return s

def cleverencode(s, cmd):
    if not util.binary(s):
        return dumbencode(s, cmd)
    return s

def macdecode(s, cmd, **kwargs):
    if not util.binary(s):
        return macdumbdecode(s, cmd, **kwargs)
    return s

def macencode(s, cmd):
    if not util.binary(s):
        return macdumbencode(s, cmd)
    return s

_filters = {
    'dumbdecode:': dumbdecode,
    'dumbencode:': dumbencode,
    'cleverdecode:': cleverdecode,
    'cleverencode:': cleverencode,
    'macdumbdecode:': macdumbdecode,
    'macdumbencode:': macdumbencode,
    'macdecode:': macdecode,
    'macencode:': macencode,
    }

def forbidnewline(ui, repo, hooktype, node, newline, **kwargs):
    halt = False
    seen = set()
    # we try to walk changesets in reverse order from newest to
    # oldest, so that if we see a file multiple times, we take the
    # newest version as canonical. this prevents us from blocking a
    # changegroup that contains an unacceptable commit followed later
    # by a commit that fixes the problem.
    tip = repo['tip']
    for rev in xrange(len(repo) - 1, repo[node].rev() - 1, -1):
        c = repo[rev]
        for f in c.files():
            if f in seen or f not in tip or f not in c:
                continue
            seen.add(f)
            data = c[f].data()
            if not util.binary(data) and newline in data:
                if not halt:
                    ui.warn(_('attempt to commit or push text file(s) '
                              'using %s line endings\n') %
                              newlinestr[newline])
                ui.warn(_('in %s: %s\n') % (short(c.node()), f))
                halt = True
    if halt and hooktype == 'pretxnchangegroup':
        crlf = newlinestr[newline].lower()
        filter = filterstr[newline]
        ui.warn(_('\nTo prevent this mistake in your local repository,\n'
                  'add to Mercurial.ini or .hg/hgrc:\n'
                  '\n'
                  '[hooks]\n'
                  'pretxncommit.%s = python:hgext.win32text.forbid%s\n'
                  '\n'
                  'and also consider adding:\n'
                  '\n'
                  '[extensions]\n'
                  'win32text =\n'
                  '[encode]\n'
                  '** = %sencode:\n'
                  '[decode]\n'
                  '** = %sdecode:\n') % (crlf, crlf, filter, filter))
    return halt

def forbidcrlf(ui, repo, hooktype, node, **kwargs):
    return forbidnewline(ui, repo, hooktype, node, '\r\n', **kwargs)

def forbidcr(ui, repo, hooktype, node, **kwargs):
    return forbidnewline(ui, repo, hooktype, node, '\r', **kwargs)

def reposetup(ui, repo):
    if not repo.local():
        return
    for name, fn in _filters.iteritems():
        repo.adddatafilter(name, fn)

def extsetup(ui):
    if ui.configbool('win32text', 'warn', True):
        ui.warn(_("win32text is deprecated: "
                  "http://mercurial.selenic.com/wiki/Win32TextExtension\n"))