view hgext/win32text.py @ 20182:04036798ebed

branches: avoid unnecessary changectx.branch() calls This requires reading from the changelog, which can be costly over NFS. Note that this does not totally remove reading from the changelog; we still do that when calling changectx.closesbranch(). That call will be removed in a later patch. Running hg branches on the PyPy repo (with 996) over a busy NFS server, before this change: $ time hg --profile branches > /dev/null CallCount Recursive Total(s) Inline(s) module:lineno(function) 2042 0 2.2827 2.2827 <open> 2036 0 0.9840 0.9840 <method 'close' of 'file' objects> 2036 0 0.0464 0.0464 <method 'read' of 'file' objects> 5233 0 0.1985 0.0453 mercurial.repoview:161(changelog) 10462 0 0.0791 0.0314 mercurial.changelog:133(tip) 5233 0 0.0388 0.0176 mercurial.localrepo:26(__get__) 10462 0 0.0250 0.0126 <len> 5233 0 0.0059 0.0039 mercurial.repoview:112(filterrevs) 10462 0 0.0029 0.0029 <hash> 2034 0 0.0444 0.0444 <method 'seek' of 'file' objects> 5340 0 0.0390 0.0390 mercurial.revlog:296(rev) 2582 0 0.0371 0.0371 <zlib.decompress> 3155 0 0.1963 0.0366 mercurial.context:202(__init__) 3155 0 0.1238 0.0306 mercurial.repoview:161(changelog) 3155 0 0.0261 0.0080 mercurial.changelog:183(rev) 9465 0 0.0061 0.0061 <isinstance> 1096 0 0.0023 0.0023 <binascii.unhexlify> 4251 0 0.0014 0.0014 <len> 2059 0 3.7341 0.0332 mercurial.changelog:270(read) 2059 0 3.6304 0.0307 mercurial.revlog:907(revision) 2057 0 0.0262 0.0137 mercurial.changelog:28(decodeextra) 4118 0 0.0094 0.0094 <method 'split' of 'str' objects> 4118 0 0.0270 0.0048 mercurial.encoding:61(tolocal) 2059 0 0.0040 0.0040 <method 'index' of 'str' objects> 10462 0 0.0791 0.0314 mercurial.changelog:133(tip) 10462 0 0.0289 0.0207 mercurial.changelog:190(node) 10462 0 0.0188 0.0091 <len> 52433 20932 0.0478 0.0310 <len> 20932 0 0.0221 0.0168 mercurial.revlog:262(__len__) 2059 0 3.6304 0.0307 mercurial.revlog:907(revision) real 0m4.361s user 0m0.986s sys 0m0.237s After this change: $ time hg --profile branches > /dev/null CallCount Recursive Total(s) Inline(s) module:lineno(function) 1069 0 1.1098 1.1098 <open> 1063 0 0.4865 0.4865 <method 'close' of 'file' objects> 4122 0 0.1811 0.0404 mercurial.repoview:161(changelog) 8240 0 0.0712 0.0272 mercurial.changelog:133(tip) 4122 0 0.0378 0.0177 mercurial.localrepo:26(__get__) 8240 0 0.0221 0.0115 <len> 4122 0 0.0057 0.0033 mercurial.repoview:112(filterrevs) 8240 0 0.0025 0.0025 <hash> 3029 0 0.1979 0.0371 mercurial.context:202(__init__) 3029 0 0.1278 0.0310 mercurial.repoview:161(changelog) 3029 0 0.0230 0.0081 mercurial.changelog:183(rev) 9087 0 0.0061 0.0061 <isinstance> 1096 0 0.0026 0.0026 <binascii.unhexlify> 4125 0 0.0014 0.0014 <len> 4229 0 0.0337 0.0337 mercurial.revlog:296(rev) 1061 0 0.0296 0.0296 <method 'seek' of 'file' objects> 1063 0 0.0292 0.0292 <method 'read' of 'file' objects> 8240 0 0.0712 0.0272 mercurial.changelog:133(tip) 8240 0 0.0271 0.0196 mercurial.changelog:190(node) 8240 0 0.0169 0.0083 <len> 40476 16488 0.0422 0.0271 <len> 16488 0 0.0193 0.0152 mercurial.revlog:262(__len__) 1342 0 0.0241 0.0241 <zlib.decompress> 9445 0 0.0336 0.0224 mercurial.changelog:190(node) 9445 0 0.0112 0.0112 mercurial.revlog:317(node) 1074 0 1.9102 0.0224 mercurial.changelog:270(read) 1074 0 1.8397 0.0202 mercurial.revlog:907(revision) 1073 0 0.0187 0.0099 mercurial.changelog:28(decodeextra) 2148 0 0.0061 0.0061 <method 'split' of 'str' objects> 2148 0 0.0184 0.0034 mercurial.encoding:61(tolocal) real 0m2.402s user 0m0.735s sys 0m0.177s
author Brodie Rao <brodie@sf.io>
date Fri, 15 Nov 2013 23:18:08 -0500
parents b35e3364f94a
children 23146e4d9cee
line wrap: on
line source

# 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

  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"))