view hgext/win32text.py @ 51409:2f39c7aeb549

phases: large rewrite on retract boundary

The new code is still pure Python, so we still have room to going significantly
faster. However its complexity of the complex part is `O(|[min_new_draft, tip]|)` instead of
`O(|[min_draft, tip]|` which should help tremendously one repository with old
draft (like mercurial-devel or mozilla-try).

This is especially useful as the most common "retract boundary" operation
happens when we commit/rewrite new drafts or when we push new draft to a
non-publishing server. In this case, the smallest new_revs is very close to the
tip and there is very few work to do.

A few smaller optimisation could be done for these cases and will be introduced in
later changesets.

We still have iterate over large sets of roots, but this is already a great
improvement for a very small amount of work. We gather information on the
affected changeset as we go as we can put it to use in the next changesets.
This extra data collection might slowdown the `register_new` case a bit, however
for register_new, it should not really matters. The set of new nodes is either
small, so the impact is negligible, or the set of new nodes is large, and the
amount of work to do to had them will dominate the overhead the collecting
information in `changed_revs`.

As this new code compute the changes on the fly, it unlock other interesting
improvement to be done in later changeset.

# win32text.py - LF <-> CRLF/CR translation utilities for Windows/Mac users
#
#  Copyright 2005, 2007-2009 Olivia 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
'''


import re
from mercurial.i18n import _
from mercurial.node import short
from mercurial import (
    cmdutil,
    extensions,
    registrar,
)
from mercurial.utils import stringutil

# 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 = b'ships-with-hg-core'

configtable = {}
configitem = registrar.configitem(configtable)

configitem(
    b'win32text',
    b'warn',
    default=True,
)

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

newlinestr = {b'\r\n': b'CRLF', b'\r': b'CR'}
filterstr = {b'\r\n': b'clever', b'\r': b'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(
            _(
                b'WARNING: %s already has %s line endings\n'
                b'and does not need EOL conversion by the win32text plugin.\n'
                b'Before your next commit, please reconsider your '
                b'encode/decode settings in \nMercurial.ini or %s.\n'
            )
            % (filename, newlinestr[newline], repo.vfs.join(b'hgrc'))
        )


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


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


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


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


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


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


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


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


_filters = {
    b'dumbdecode:': dumbdecode,
    b'dumbencode:': dumbencode,
    b'cleverdecode:': cleverdecode,
    b'cleverencode:': cleverencode,
    b'macdumbdecode:': macdumbdecode,
    b'macdumbencode:': macdumbencode,
    b'macdecode:': macdecode,
    b'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[b'tip']
    for rev in range(repo.changelog.tiprev(), 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 stringutil.binary(data) and newline in data:
                if not halt:
                    ui.warn(
                        _(
                            b'attempt to commit or push text file(s) '
                            b'using %s line endings\n'
                        )
                        % newlinestr[newline]
                    )
                ui.warn(_(b'in %s: %s\n') % (short(c.node()), f))
                halt = True
    if halt and hooktype == b'pretxnchangegroup':
        crlf = newlinestr[newline].lower()
        filter = filterstr[newline]
        ui.warn(
            _(
                b'\nTo prevent this mistake in your local repository,\n'
                b'add to Mercurial.ini or .hg/hgrc:\n'
                b'\n'
                b'[hooks]\n'
                b'pretxncommit.%s = python:hgext.win32text.forbid%s\n'
                b'\n'
                b'and also consider adding:\n'
                b'\n'
                b'[extensions]\n'
                b'win32text =\n'
                b'[encode]\n'
                b'** = %sencode:\n'
                b'[decode]\n'
                b'** = %sdecode:\n'
            )
            % (crlf, crlf, filter, filter)
        )
    return halt


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


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


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


def wrap_revert(orig, repo, ctx, names, uipathfn, actions, *args, **kwargs):
    # reset dirstate cache for file we touch
    ds = repo.dirstate
    for filename in actions[b'revert'][0]:
        entry = ds.get_entry(filename)
        if entry is not None:
            if entry.p1_tracked:
                # If we revert the file, it is possibly dirty. However,
                # this extension meddle with the file content and therefore
                # its size. As a result, we cannot simply call
                # `dirstate.set_possibly_dirty` as it will not affet the
                # expected size of the file.
                #
                # At least, now, the quirk is properly documented.
                ds.hacky_extension_update_file(
                    filename,
                    entry.tracked,
                    p1_tracked=entry.p1_tracked,
                    p2_info=entry.p2_info,
                )
    return orig(repo, ctx, names, uipathfn, actions, *args, **kwargs)


def extsetup(ui):
    # deprecated config: win32text.warn
    if ui.configbool(b'win32text', b'warn'):
        ui.warn(
            _(
                b"win32text is deprecated: "
                b"https://mercurial-scm.org/wiki/Win32TextExtension\n"
            )
        )
    extensions.wrapfunction(cmdutil, '_performrevert', wrap_revert)