mercurial/archival.py

filemerge: add support for partial conflict resolution by external tool

A common class of merge conflicts is in imports/#includes/etc. It's
relatively easy to write a tool that can resolve these conflicts,
perhaps by naively just unioning the statements and leaving any
cleanup to other tools to do later [1]. Such specialized tools cannot
generally resolve all conflicts in a file, of course. Let's therefore
call them "partial merge tools". Note that the internal simplemerge
algorithm is such a partial merge tool - one that only resolves
trivial "conflicts" where one side is unchanged or both sides change
in the same way.

One can also imagine having smarter language-aware partial tools that
merge the AST. It may be useful for such tools to interactively let
the user resolve any conflicts it can't resolve itself. However,
having the option of implementing it as a partial merge tool means
that the developer doesn't *need* to create a UI for it. Instead, the
user can resolve any remaining conflicts with their regular merge tool
(e.g. `:merge3` or `meld).

We don't currently have a way to let the user define such partial
merge tools. That's what this patch addresses. It lets the user
configure partial merge tools to run. Each tool can be configured to
run only on files matching certain patterns (e.g. "*.py"). The tool
takes three inputs (local, base, other) and resolves conflicts by
updating these in place. For example, let's say the inputs are these:


base:
```
import sys

def main():
  print('Hello')
```

local:
```
import os
import sys

def main():
  print('Hi')
```

other:
```
import re
import sys

def main():
  print('Howdy')
```

A partial merge tool could now resolve the conflicting imports by
replacing the import statements in *all* files by the following
snippet, while leaving the remainder of the files unchanged.

```
import os
import re
import sys
```

As a result, simplemerge and any regular merge tool that runs after
the partial merge tool(s) will consider the imports to be
non-conflicting and will only present the conflict in `main()` to the
user.

Differential Revision: https://phab.mercurial-scm.org/D12356

# archival.py - revision archival for mercurial
#
# Copyright 2006 Vadim Gelfer <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.


import gzip
import os
import struct
import tarfile
import time
import zipfile
import zlib

from .i18n import _
from .node import nullrev
from .pycompat import open

from . import (
    error,
    formatter,
    match as matchmod,
    pycompat,
    scmutil,
    util,
    vfs as vfsmod,
)

from .utils import stringutil

stringio = util.stringio

# from unzip source code:
_UNX_IFREG = 0x8000
_UNX_IFLNK = 0xA000


def tidyprefix(dest, kind, prefix):
    """choose prefix to use for names in archive.  make sure prefix is
    safe for consumers."""

    if prefix:
        prefix = util.normpath(prefix)
    else:
        if not isinstance(dest, bytes):
            raise ValueError(b'dest must be string if no prefix')
        prefix = os.path.basename(dest)
        lower = prefix.lower()
        for sfx in exts.get(kind, []):
            if lower.endswith(sfx):
                prefix = prefix[: -len(sfx)]
                break
    lpfx = os.path.normpath(util.localpath(prefix))
    prefix = util.pconvert(lpfx)
    if not prefix.endswith(b'/'):
        prefix += b'/'
    # Drop the leading '.' path component if present, so Windows can read the
    # zip files (issue4634)
    if prefix.startswith(b'./'):
        prefix = prefix[2:]
    if prefix.startswith(b'../') or os.path.isabs(lpfx) or b'/../' in prefix:
        raise error.Abort(_(b'archive prefix contains illegal components'))
    return prefix


exts = {
    b'tar': [b'.tar'],
    b'tbz2': [b'.tbz2', b'.tar.bz2'],
    b'tgz': [b'.tgz', b'.tar.gz'],
    b'zip': [b'.zip'],
    b'txz': [b'.txz', b'.tar.xz'],
}


def guesskind(dest):
    for kind, extensions in exts.items():
        if any(dest.endswith(ext) for ext in extensions):
            return kind
    return None


def _rootctx(repo):
    # repo[0] may be hidden
    for rev in repo:
        return repo[rev]
    return repo[nullrev]


# {tags} on ctx includes local tags and 'tip', with no current way to limit
# that to global tags.  Therefore, use {latesttag} as a substitute when
# the distance is 0, since that will be the list of global tags on ctx.
_defaultmetatemplate = br'''
repo: {root}
node: {ifcontains(rev, revset("wdir()"), "{p1node}{dirty}", "{node}")}
branch: {branch|utf8}
{ifeq(latesttagdistance, 0, join(latesttag % "tag: {tag}", "\n"),
      separate("\n",
               join(latesttag % "latesttag: {tag}", "\n"),
               "latesttagdistance: {latesttagdistance}",
               "changessincelatesttag: {changessincelatesttag}"))}
'''[
    1:
]  # drop leading '\n'


def buildmetadata(ctx):
    '''build content of .hg_archival.txt'''
    repo = ctx.repo()

    opts = {
        b'template': repo.ui.config(
            b'experimental', b'archivemetatemplate', _defaultmetatemplate
        )
    }

    out = util.stringio()

    fm = formatter.formatter(repo.ui, out, b'archive', opts)
    fm.startitem()
    fm.context(ctx=ctx)
    fm.data(root=_rootctx(repo).hex())

    if ctx.rev() is None:
        dirty = b''
        if ctx.dirty(missing=True):
            dirty = b'+'
        fm.data(dirty=dirty)
    fm.end()

    return out.getvalue()


class tarit:
    """write archive to tar file or stream.  can write uncompressed,
    or compress with gzip or bzip2."""

    def __init__(self, dest, mtime, kind=b''):
        self.mtime = mtime
        self.fileobj = None

        def taropen(mode, name=b'', fileobj=None):
            if kind == b'gz':
                mode = mode[0:1]
                if not fileobj:
                    fileobj = open(name, mode + b'b')
                gzfileobj = gzip.GzipFile(
                    name,
                    pycompat.sysstr(mode + b'b'),
                    zlib.Z_BEST_COMPRESSION,
                    fileobj,
                    mtime=mtime,
                )
                self.fileobj = gzfileobj
                return (
                    tarfile.TarFile.taropen(  # pytype: disable=attribute-error
                        name, pycompat.sysstr(mode), gzfileobj
                    )
                )
            else:
                try:
                    return tarfile.open(
                        name, pycompat.sysstr(mode + kind), fileobj
                    )
                except tarfile.CompressionError as e:
                    raise error.Abort(stringutil.forcebytestr(e))

        if isinstance(dest, bytes):
            self.z = taropen(b'w:', name=dest)
        else:
            self.z = taropen(b'w|', fileobj=dest)

    def addfile(self, name, mode, islink, data):
        name = pycompat.fsdecode(name)
        i = tarfile.TarInfo(name)
        i.mtime = self.mtime
        i.size = len(data)
        if islink:
            i.type = tarfile.SYMTYPE
            i.mode = 0o777
            i.linkname = pycompat.fsdecode(data)
            data = None
            i.size = 0
        else:
            i.mode = mode
            data = stringio(data)
        self.z.addfile(i, data)

    def done(self):
        self.z.close()
        if self.fileobj:
            self.fileobj.close()


class zipit:
    """write archive to zip file or stream.  can write uncompressed,
    or compressed with deflate."""

    def __init__(self, dest, mtime, compress=True):
        if isinstance(dest, bytes):
            dest = pycompat.fsdecode(dest)
        self.z = zipfile.ZipFile(
            dest, 'w', compress and zipfile.ZIP_DEFLATED or zipfile.ZIP_STORED
        )

        # Python's zipfile module emits deprecation warnings if we try
        # to store files with a date before 1980.
        epoch = 315532800  # calendar.timegm((1980, 1, 1, 0, 0, 0, 1, 1, 0))
        if mtime < epoch:
            mtime = epoch

        self.mtime = mtime
        self.date_time = time.gmtime(mtime)[:6]

    def addfile(self, name, mode, islink, data):
        i = zipfile.ZipInfo(pycompat.fsdecode(name), self.date_time)
        i.compress_type = self.z.compression  # pytype: disable=attribute-error
        # unzip will not honor unix file modes unless file creator is
        # set to unix (id 3).
        i.create_system = 3
        ftype = _UNX_IFREG
        if islink:
            mode = 0o777
            ftype = _UNX_IFLNK
        i.external_attr = (mode | ftype) << 16
        # add "extended-timestamp" extra block, because zip archives
        # without this will be extracted with unexpected timestamp,
        # if TZ is not configured as GMT
        i.extra += struct.pack(
            b'<hhBl',
            0x5455,  # block type: "extended-timestamp"
            1 + 4,  # size of this block
            1,  # "modification time is present"
            int(self.mtime),
        )  # last modification (UTC)
        self.z.writestr(i, data)

    def done(self):
        self.z.close()


class fileit:
    '''write archive as files in directory.'''

    def __init__(self, name, mtime):
        self.basedir = name
        self.opener = vfsmod.vfs(self.basedir)
        self.mtime = mtime

    def addfile(self, name, mode, islink, data):
        if islink:
            self.opener.symlink(data, name)
            return
        f = self.opener(name, b"w", atomictemp=False)
        f.write(data)
        f.close()
        destfile = os.path.join(self.basedir, name)
        os.chmod(destfile, mode)
        if self.mtime is not None:
            os.utime(destfile, (self.mtime, self.mtime))

    def done(self):
        pass


archivers = {
    b'files': fileit,
    b'tar': tarit,
    b'tbz2': lambda name, mtime: tarit(name, mtime, b'bz2'),
    b'tgz': lambda name, mtime: tarit(name, mtime, b'gz'),
    b'txz': lambda name, mtime: tarit(name, mtime, b'xz'),
    b'uzip': lambda name, mtime: zipit(name, mtime, False),
    b'zip': zipit,
}


def archive(
    repo,
    dest,
    node,
    kind,
    decode=True,
    match=None,
    prefix=b'',
    mtime=None,
    subrepos=False,
):
    """create archive of repo as it was at node.

    dest can be name of directory, name of archive file, or file
    object to write archive to.

    kind is type of archive to create.

    decode tells whether to put files through decode filters from
    hgrc.

    match is a matcher to filter names of files to write to archive.

    prefix is name of path to put before every archive member.

    mtime is the modified time, in seconds, or None to use the changeset time.

    subrepos tells whether to include subrepos.
    """

    if kind == b'files':
        if prefix:
            raise error.Abort(_(b'cannot give prefix when archiving to files'))
    else:
        prefix = tidyprefix(dest, kind, prefix)

    def write(name, mode, islink, getdata):
        data = getdata()
        if decode:
            data = repo.wwritedata(name, data)
        archiver.addfile(prefix + name, mode, islink, data)

    if kind not in archivers:
        raise error.Abort(_(b"unknown archive type '%s'") % kind)

    ctx = repo[node]
    archiver = archivers[kind](dest, mtime or ctx.date()[0])

    if not match:
        match = scmutil.matchall(repo)

    if repo.ui.configbool(b"ui", b"archivemeta"):
        name = b'.hg_archival.txt'
        if match(name):
            write(name, 0o644, False, lambda: buildmetadata(ctx))

    files = list(ctx.manifest().walk(match))
    total = len(files)
    if total:
        files.sort()
        scmutil.prefetchfiles(
            repo, [(ctx.rev(), scmutil.matchfiles(repo, files))]
        )
        progress = repo.ui.makeprogress(
            _(b'archiving'), unit=_(b'files'), total=total
        )
        progress.update(0)
        for f in files:
            ff = ctx.flags(f)
            write(f, b'x' in ff and 0o755 or 0o644, b'l' in ff, ctx[f].data)
            progress.increment(item=f)
        progress.complete()

    if subrepos:
        for subpath in sorted(ctx.substate):
            sub = ctx.workingsub(subpath)
            submatch = matchmod.subdirmatcher(subpath, match)
            subprefix = prefix + subpath + b'/'
            total += sub.archive(archiver, subprefix, submatch, decode)

    if total == 0:
        raise error.Abort(_(b'no files match the archive pattern'))

    archiver.done()
    return total