# scmutil.py - Mercurial core utility functions

#

#  Copyright Matt Mackall <mpm@selenic.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 contextlib

import errno

import glob

import hashlib

import os

import re

import shutil

import stat

import tempfile

import threading

from .i18n import _

from .node import wdirrev

from . import (

    encoding,

    error,

    match as matchmod,

    osutil,

    pathutil,

    phases,

    revset,

    similar,

    util,

)

if os.name == 'nt':

    from . import scmwindows as scmplatform

else:

    from . import scmposix as scmplatform

systemrcpath = scmplatform.systemrcpath

userrcpath = scmplatform.userrcpath

class status(tuple):

    '''Named tuple with a list of files per status. The 'deleted', 'unknown'

       and 'ignored' properties are only relevant to the working copy.

    '''

    __slots__ = ()

    def __new__(cls, modified, added, removed, deleted, unknown, ignored,

                clean):

        return tuple.__new__(cls, (modified, added, removed, deleted, unknown,

                                   ignored, clean))

    @property

    def modified(self):

        '''files that have been modified'''

        return self[0]

    @property

    def added(self):

        '''files that have been added'''

        return self[1]

    @property

    def removed(self):

        '''files that have been removed'''

        return self[2]

    @property

    def deleted(self):

        '''files that are in the dirstate, but have been deleted from the

           working copy (aka "missing")

        '''

        return self[3]

    @property

    def unknown(self):

        '''files not in the dirstate that are not ignored'''

        return self[4]

    @property

    def ignored(self):

        '''files not in the dirstate that are ignored (by _dirignore())'''

        return self[5]

    @property

    def clean(self):

        '''files that have not been modified'''

        return self[6]

    def __repr__(self, *args, **kwargs):

        return (('<status modified=%r, added=%r, removed=%r, deleted=%r, '

                 'unknown=%r, ignored=%r, clean=%r>') % self)

def itersubrepos(ctx1, ctx2):

    """find subrepos in ctx1 or ctx2"""

    # Create a (subpath, ctx) mapping where we prefer subpaths from

    # ctx1. The subpaths from ctx2 are important when the .hgsub file

    # has been modified (in ctx2) but not yet committed (in ctx1).

    subpaths = dict.fromkeys(ctx2.substate, ctx2)

    subpaths.update(dict.fromkeys(ctx1.substate, ctx1))

    missing = set()

    for subpath in ctx2.substate:

        if subpath not in ctx1.substate:

            del subpaths[subpath]

            missing.add(subpath)

    for subpath, ctx in sorted(subpaths.iteritems()):

        yield subpath, ctx.sub(subpath)

    # Yield an empty subrepo based on ctx1 for anything only in ctx2.  That way,

    # status and diff will have an accurate result when it does

    # 'sub.{status|diff}(rev2)'.  Otherwise, the ctx2 subrepo is compared

    # against itself.

    for subpath in missing:

        yield subpath, ctx2.nullsub(subpath, ctx1)

def nochangesfound(ui, repo, excluded=None):

    '''Report no changes for push/pull, excluded is None or a list of

    nodes excluded from the push/pull.

    '''

    secretlist = []

    if excluded:

        for n in excluded:

            if n not in repo:

                # discovery should not have included the filtered revision,

                # we have to explicitly exclude it until discovery is cleanup.

                continue

            ctx = repo[n]

            if ctx.phase() >= phases.secret and not ctx.extinct():

                secretlist.append(n)

    if secretlist:

        ui.status(_("no changes found (ignored %d secret changesets)\n")

                  % len(secretlist))

    else:

        ui.status(_("no changes found\n"))

def checknewlabel(repo, lbl, kind):

    # Do not use the "kind" parameter in ui output.

    # It makes strings difficult to translate.

    if lbl in ['tip', '.', 'null']:

        raise error.Abort(_("the name '%s' is reserved") % lbl)

    for c in (':', '\0', '\n', '\r'):

        if c in lbl:

            raise error.Abort(_("%r cannot be used in a name") % c)

    try:

        int(lbl)

        raise error.Abort(_("cannot use an integer as a name"))

    except ValueError:

        pass

def checkfilename(f):

    '''Check that the filename f is an acceptable filename for a tracked file'''

    if '\r' in f or '\n' in f:

        raise error.Abort(_("'\\n' and '\\r' disallowed in filenames: %r") % f)

def checkportable(ui, f):

    '''Check if filename f is portable and warn or abort depending on config'''

    checkfilename(f)

    abort, warn = checkportabilityalert(ui)

    if abort or warn:

        msg = util.checkwinfilename(f)

        if msg:

            msg = "%s: %r" % (msg, f)

            if abort:

                raise error.Abort(msg)

            ui.warn(_("warning: %s\n") % msg)

def checkportabilityalert(ui):

    '''check if the user's config requests nothing, a warning, or abort for

    non-portable filenames'''

    val = ui.config('ui', 'portablefilenames', 'warn')

    lval = val.lower()

    bval = util.parsebool(val)

    abort = os.name == 'nt' or lval == 'abort'

    warn = bval or lval == 'warn'

    if bval is None and not (warn or abort or lval == 'ignore'):

        raise error.ConfigError(

            _("ui.portablefilenames value is invalid ('%s')") % val)

    return abort, warn

class casecollisionauditor(object):

    def __init__(self, ui, abort, dirstate):

        self._ui = ui

        self._abort = abort

        allfiles = '\0'.join(dirstate._map)

        self._loweredfiles = set(encoding.lower(allfiles).split('\0'))

        self._dirstate = dirstate

        # The purpose of _newfiles is so that we don't complain about

        # case collisions if someone were to call this object with the

        # same filename twice.

        self._newfiles = set()

    def __call__(self, f):

        if f in self._newfiles:

            return

        fl = encoding.lower(f)

        if fl in self._loweredfiles and f not in self._dirstate:

            msg = _('possible case-folding collision for %s') % f

            if self._abort:

                raise error.Abort(msg)

            self._ui.warn(_("warning: %s\n") % msg)

        self._loweredfiles.add(fl)

        self._newfiles.add(f)

def filteredhash(repo, maxrev):

    """build hash of filtered revisions in the current repoview.

    Multiple caches perform up-to-date validation by checking that the

    tiprev and tipnode stored in the cache file match the current repository.

    However, this is not sufficient for validating repoviews because the set

    of revisions in the view may change without the repository tiprev and

    tipnode changing.

    This function hashes all the revs filtered from the view and returns

    that SHA-1 digest.

    """

    cl = repo.changelog

    if not cl.filteredrevs:

        return None

    key = None

    revs = sorted(r for r in cl.filteredrevs if r <= maxrev)

    if revs:

        s = hashlib.sha1()

        for rev in revs:

            s.update('%s;' % rev)

        key = s.digest()

    return key

class abstractvfs(object):

    """Abstract base class; cannot be instantiated"""

    def __init__(self, *args, **kwargs):

        '''Prevent instantiation; don't call this from subclasses.'''

        raise NotImplementedError('attempted instantiating ' + str(type(self)))

    def tryread(self, path):

        '''gracefully return an empty string for missing files'''

        try:

            return self.read(path)

        except IOError as inst:

            if inst.errno != errno.ENOENT:

                raise

        return ""

    def tryreadlines(self, path, mode='rb'):

        '''gracefully return an empty array for missing files'''

        try:

            return self.readlines(path, mode=mode)

        except IOError as inst:

            if inst.errno != errno.ENOENT:

                raise

        return []

    @util.propertycache

    def open(self):

        '''Open ``path`` file, which is relative to vfs root.

        Newly created directories are marked as "not to be indexed by

        the content indexing service", if ``notindexed`` is specified

        for "write" mode access.

        '''

        return self.__call__

    def read(self, path):

        with self(path, 'rb') as fp:

            return fp.read()

    def readlines(self, path, mode='rb'):

        with self(path, mode=mode) as fp:

            return fp.readlines()

    def write(self, path, data, backgroundclose=False):

        with self(path, 'wb', backgroundclose=backgroundclose) as fp:

            return fp.write(data)

    def writelines(self, path, data, mode='wb', notindexed=False):

        with self(path, mode=mode, notindexed=notindexed) as fp:

            return fp.writelines(data)

    def append(self, path, data):

        with self(path, 'ab') as fp:

            return fp.write(data)

    def basename(self, path):

        """return base element of a path (as os.path.basename would do)

        This exists to allow handling of strange encoding if needed."""

        return os.path.basename(path)

    def chmod(self, path, mode):

        return os.chmod(self.join(path), mode)

    def dirname(self, path):

        """return dirname element of a path (as os.path.dirname would do)

        This exists to allow handling of strange encoding if needed."""

        return os.path.dirname(path)

    def exists(self, path=None):

        return os.path.exists(self.join(path))

    def fstat(self, fp):

        return util.fstat(fp)

    def isdir(self, path=None):

        return os.path.isdir(self.join(path))

    def isfile(self, path=None):

        return os.path.isfile(self.join(path))

    def islink(self, path=None):

        return os.path.islink(self.join(path))

    def isfileorlink(self, path=None):

        '''return whether path is a regular file or a symlink

        Unlike isfile, this doesn't follow symlinks.'''

        try:

            st = self.lstat(path)

        except OSError:

            return False

        mode = st.st_mode

        return stat.S_ISREG(mode) or stat.S_ISLNK(mode)

    def reljoin(self, *paths):

        """join various elements of a path together (as os.path.join would do)

        The vfs base is not injected so that path stay relative. This exists

        to allow handling of strange encoding if needed."""

        return os.path.join(*paths)

    def split(self, path):

        """split top-most element of a path (as os.path.split would do)

        This exists to allow handling of strange encoding if needed."""

        return os.path.split(path)

    def lexists(self, path=None):

        return os.path.lexists(self.join(path))

    def lstat(self, path=None):

        return os.lstat(self.join(path))

    def listdir(self, path=None):

        return os.listdir(self.join(path))

    def makedir(self, path=None, notindexed=True):

        return util.makedir(self.join(path), notindexed)

    def makedirs(self, path=None, mode=None):

        return util.makedirs(self.join(path), mode)

    def makelock(self, info, path):

        return util.makelock(info, self.join(path))

    def mkdir(self, path=None):

        return os.mkdir(self.join(path))

    def mkstemp(self, suffix='', prefix='tmp', dir=None, text=False):

        fd, name = tempfile.mkstemp(suffix=suffix, prefix=prefix,

                                    dir=self.join(dir), text=text)

        dname, fname = util.split(name)

        if dir:

            return fd, os.path.join(dir, fname)

        else:

            return fd, fname

    def readdir(self, path=None, stat=None, skip=None):

        return osutil.listdir(self.join(path), stat, skip)

    def readlock(self, path):

        return util.readlock(self.join(path))

    def rename(self, src, dst, checkambig=False):

        """Rename from src to dst

        checkambig argument is used with util.filestat, and is useful

        only if destination file is guarded by any lock

        (e.g. repo.lock or repo.wlock).

        """

        dstpath = self.join(dst)

        oldstat = checkambig and util.filestat(dstpath)

        if oldstat and oldstat.stat:

            ret = util.rename(self.join(src), dstpath)

            newstat = util.filestat(dstpath)

            if newstat.isambig(oldstat):

                # stat of renamed file is ambiguous to original one

            return ret

        return util.rename(self.join(src), dstpath)

    def readlink(self, path):

        return os.readlink(self.join(path))

    def removedirs(self, path=None):

        """Remove a leaf directory and all empty intermediate ones

        """

        return util.removedirs(self.join(path))

    def rmtree(self, path=None, ignore_errors=False, forcibly=False):

        """Remove a directory tree recursively

        If ``forcibly``, this tries to remove READ-ONLY files, too.

        """

        if forcibly:

            def onerror(function, path, excinfo):

                if function is not os.remove:

                    raise

                # read-only files cannot be unlinked under Windows

                s = os.stat(path)

                if (s.st_mode & stat.S_IWRITE) != 0:

                    raise

                os.chmod(path, stat.S_IMODE(s.st_mode) | stat.S_IWRITE)

                os.remove(path)

        else:

            onerror = None

        return shutil.rmtree(self.join(path),

                             ignore_errors=ignore_errors, onerror=onerror)

    def setflags(self, path, l, x):

        return util.setflags(self.join(path), l, x)

    def stat(self, path=None):

        return os.stat(self.join(path))

    def unlink(self, path=None):

        return util.unlink(self.join(path))

    def unlinkpath(self, path=None, ignoremissing=False):

        return util.unlinkpath(self.join(path), ignoremissing)

    def utime(self, path=None, t=None):

        return os.utime(self.join(path), t)

    def walk(self, path=None, onerror=None):

        """Yield (dirpath, dirs, files) tuple for each directories under path

        ``dirpath`` is relative one from the root of this vfs. This

        uses ``os.sep`` as path separator, even you specify POSIX

        style ``path``.

        "The root of this vfs" is represented as empty ``dirpath``.

        """

        root = os.path.normpath(self.join(None))

        # when dirpath == root, dirpath[prefixlen:] becomes empty

        # because len(dirpath) < prefixlen.

        prefixlen = len(pathutil.normasprefix(root))

        for dirpath, dirs, files in os.walk(self.join(path), onerror=onerror):

            yield (dirpath[prefixlen:], dirs, files)

    @contextlib.contextmanager

    def backgroundclosing(self, ui, expectedcount=-1):

        """Allow files to be closed asynchronously.

        When this context manager is active, ``backgroundclose`` can be passed

        to ``__call__``/``open`` to result in the file possibly being closed

        asynchronously, on a background thread.

        """

        # This is an arbitrary restriction and could be changed if we ever

        # have a use case.

        vfs = getattr(self, 'vfs', self)

        if getattr(vfs, '_backgroundfilecloser', None):

            raise error.Abort(

                _('can only have 1 active background file closer'))

        with backgroundfilecloser(ui, expectedcount=expectedcount) as bfc:

            try:

                vfs._backgroundfilecloser = bfc

                yield bfc

            finally:

                vfs._backgroundfilecloser = None

class vfs(abstractvfs):

    '''Operate files relative to a base directory

    This class is used to hide the details of COW semantics and

    remote file access from higher level code.

    '''

    def __init__(self, base, audit=True, expandpath=False, realpath=False):

        if expandpath:

            base = util.expandpath(base)

        if realpath: