view hgext/win32text.py @ 30561:7c0c722d568d

bdiff: early pruning of common prefix before doing expensive computations

It seems quite common that files don't change completely. New lines are often
pretty much appended, and modifications will often only change a small section
of the file which on average will be in the middle.

There can thus be a big win by pruning a common prefix before starting the more
expensive search for longest common substrings.

Worst case, it will scan through a long sequence of similar bytes without
encountering a newline. Splitlines will then have to do the same again ...
twice for each side. If similar lines are found, splitlines will save the
double iteration and hashing of the lines ... plus there will be less lines to
find common substrings in.

This change might in some cases make the algorith pick shorter or less optimal
common substrings. We can't have the cake and eat it.

This make hg --time bundle --base null -r 4.0 go from 14.5 to 15 s - a 3%
increase.

On mozilla-unified:
perfbdiff -m 3041e4d59df2
! wall 0.053088 comb 0.060000 user 0.060000 sys 0.000000 (best of 100) to
! wall 0.024618 comb 0.020000 user 0.020000 sys 0.000000 (best of 116)
perfbdiff 0e9928989e9c --alldata --count 10
! wall 0.702075 comb 0.700000 user 0.700000 sys 0.000000 (best of 15) to
! wall 0.579235 comb 0.580000 user 0.580000 sys 0.000000 (best of 18)

# win32text.py - LF <-> CRLF/CR translation utilities for Windows/Mac users
#
#  Copyright 2005, 2007-2009 Matt Mackall <[e-mail]> 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 __future__ import absolute_import

import re
from mercurial.i18n import _
from mercurial.node import (
    short,
)
from mercurial import (
    util,
)

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = 'ships-with-hg-core'

# 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:
    #   https://bz.mercurial-scm.org/302
    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):
    # deprecated config: win32text.warn
    if ui.configbool('win32text', 'warn', True):
        ui.warn(_("win32text is deprecated: "
                  "https://mercurial-scm.org/wiki/Win32TextExtension\n"))