hgext/convert/git.py
author timeless <timeless@mozdev.org>
Thu, 17 Mar 2016 18:19:36 +0000
changeset 28607 a88959ae5938
parent 28365 cd599bc179fb
child 28670 ff0d3b6b287f
permissions -rw-r--r--
remove: queue warnings until after status messages (issue5140) (API) Before this change, warnings were interspersed with (and easily drowned out by) status messages. API: abstractsubrepo.removefiles has an extra argument warnings, into which callees should append their warnings. Note: Callees should not assume that there will be items in the list, today, I'm lazily including any other subrepos warnings, but that may change. cmdutil.remove has an extra optional argument warnings, into which it will place warnings. If warnings is omitted, warnings will be reported via ui.warn() as before this change (albeit, after any status messages).

# git.py - git support for the convert extension
#
#  Copyright 2005-2009 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.
from __future__ import absolute_import

import os
import subprocess
from mercurial import (
    config,
    error,
    node as nodemod,
    util,
)
from mercurial.i18n import _

from . import (
    common,
)

class submodule(object):
    def __init__(self, path, node, url):
        self.path = path
        self.node = node
        self.url = url

    def hgsub(self):
        return "%s = [git]%s" % (self.path, self.url)

    def hgsubstate(self):
        return "%s %s" % (self.node, self.path)

class convert_git(common.converter_source):
    # Windows does not support GIT_DIR= construct while other systems
    # cannot remove environment variable. Just assume none have
    # both issues.
    if util.safehasattr(os, 'unsetenv'):
        def gitopen(self, s, err=None):
            prevgitdir = os.environ.get('GIT_DIR')
            os.environ['GIT_DIR'] = self.path
            try:
                if err == subprocess.PIPE:
                    (stdin, stdout, stderr) = util.popen3(s)
                    return stdout
                elif err == subprocess.STDOUT:
                    return self.popen_with_stderr(s)
                else:
                    return util.popen(s, 'rb')
            finally:
                if prevgitdir is None:
                    del os.environ['GIT_DIR']
                else:
                    os.environ['GIT_DIR'] = prevgitdir

        def gitpipe(self, s):
            prevgitdir = os.environ.get('GIT_DIR')
            os.environ['GIT_DIR'] = self.path
            try:
                return util.popen3(s)
            finally:
                if prevgitdir is None:
                    del os.environ['GIT_DIR']
                else:
                    os.environ['GIT_DIR'] = prevgitdir

    else:
        def gitopen(self, s, err=None):
            if err == subprocess.PIPE:
                (sin, so, se) = util.popen3('GIT_DIR=%s %s' % (self.path, s))
                return so
            elif err == subprocess.STDOUT:
                    return self.popen_with_stderr(s)
            else:
                return util.popen('GIT_DIR=%s %s' % (self.path, s), 'rb')

        def gitpipe(self, s):
            return util.popen3('GIT_DIR=%s %s' % (self.path, s))

    def popen_with_stderr(self, s):
        p = subprocess.Popen(s, shell=True, bufsize=-1,
                             close_fds=util.closefds,
                             stdin=subprocess.PIPE,
                             stdout=subprocess.PIPE,
                             stderr=subprocess.STDOUT,
                             universal_newlines=False,
                             env=None)
        return p.stdout

    def gitread(self, s):
        fh = self.gitopen(s)
        data = fh.read()
        return data, fh.close()

    def __init__(self, ui, path, revs=None):
        super(convert_git, self).__init__(ui, path, revs=revs)

        if os.path.isdir(path + "/.git"):
            path += "/.git"
        if not os.path.exists(path + "/objects"):
            raise common.NoRepo(_("%s does not look like a Git repository") %
                                path)

        # The default value (50) is based on the default for 'git diff'.
        similarity = ui.configint('convert', 'git.similarity', default=50)
        if similarity < 0 or similarity > 100:
            raise error.Abort(_('similarity must be between 0 and 100'))
        if similarity > 0:
            self.simopt = '-C%d%%' % similarity
            findcopiesharder = ui.configbool('convert', 'git.findcopiesharder',
                                             False)
            if findcopiesharder:
                self.simopt += ' --find-copies-harder'
        else:
            self.simopt = ''

        common.checktool('git', 'git')

        self.path = path
        self.submodules = []

        self.catfilepipe = self.gitpipe('git cat-file --batch')

    def after(self):
        for f in self.catfilepipe:
            f.close()

    def getheads(self):
        if not self.revs:
            heads, ret = self.gitread('git rev-parse --branches --remotes')
            heads = heads.splitlines()
            if ret:
                raise error.Abort(_('cannot retrieve git heads'))
        else:
            heads = []
            for rev in self.revs:
                rawhead, ret = self.gitread("git rev-parse --verify %s" % rev)
                heads.append(rawhead[:-1])
                if ret:
                    raise error.Abort(_('cannot retrieve git head "%s"') % rev)
        return heads

    def catfile(self, rev, type):
        if rev == nodemod.nullhex:
            raise IOError
        self.catfilepipe[0].write(rev+'\n')
        self.catfilepipe[0].flush()
        info = self.catfilepipe[1].readline().split()
        if info[1] != type:
            raise error.Abort(_('cannot read %r object at %s') % (type, rev))
        size = int(info[2])
        data = self.catfilepipe[1].read(size)
        if len(data) < size:
            raise error.Abort(_('cannot read %r object at %s: unexpected size')
                             % (type, rev))
        # read the trailing newline
        self.catfilepipe[1].read(1)
        return data

    def getfile(self, name, rev):
        if rev == nodemod.nullhex:
            return None, None
        if name == '.hgsub':
            data = '\n'.join([m.hgsub() for m in self.submoditer()])
            mode = ''
        elif name == '.hgsubstate':
            data = '\n'.join([m.hgsubstate() for m in self.submoditer()])
            mode = ''
        else:
            data = self.catfile(rev, "blob")
            mode = self.modecache[(name, rev)]
        return data, mode

    def submoditer(self):
        null = nodemod.nullhex
        for m in sorted(self.submodules, key=lambda p: p.path):
            if m.node != null:
                yield m

    def parsegitmodules(self, content):
        """Parse the formatted .gitmodules file, example file format:
        [submodule "sub"]\n
        \tpath = sub\n
        \turl = git://giturl\n
        """
        self.submodules = []
        c = config.config()
        # Each item in .gitmodules starts with whitespace that cant be parsed
        c.parse('.gitmodules', '\n'.join(line.strip() for line in
                               content.split('\n')))
        for sec in c.sections():
            s = c[sec]
            if 'url' in s and 'path' in s:
                self.submodules.append(submodule(s['path'], '', s['url']))

    def retrievegitmodules(self, version):
        modules, ret = self.gitread("git show %s:%s" % (version, '.gitmodules'))
        if ret:
            # This can happen if a file is in the repo that has permissions
            # 160000, but there is no .gitmodules file.
            self.ui.warn(_("warning: cannot read submodules config file in "
                           "%s\n") % version)
            return

        try:
            self.parsegitmodules(modules)
        except error.ParseError:
            self.ui.warn(_("warning: unable to parse .gitmodules in %s\n")
                         % version)
            return

        for m in self.submodules:
            node, ret = self.gitread("git rev-parse %s:%s" % (version, m.path))
            if ret:
                continue
            m.node = node.strip()

    def getchanges(self, version, full):
        if full:
            raise error.Abort(_("convert from git does not support --full"))
        self.modecache = {}
        fh = self.gitopen("git diff-tree -z --root -m -r %s %s" % (
            self.simopt, version))
        changes = []
        copies = {}
        seen = set()
        entry = None
        subexists = [False]
        subdeleted = [False]
        difftree = fh.read().split('\x00')
        lcount = len(difftree)
        i = 0

        skipsubmodules = self.ui.configbool('convert', 'git.skipsubmodules',
                                            False)
        def add(entry, f, isdest):
            seen.add(f)
            h = entry[3]
            p = (entry[1] == "100755")
            s = (entry[1] == "120000")
            renamesource = (not isdest and entry[4][0] == 'R')

            if f == '.gitmodules':
                if skipsubmodules:
                    return

                subexists[0] = True
                if entry[4] == 'D' or renamesource:
                    subdeleted[0] = True
                    changes.append(('.hgsub', nodemod.nullhex))
                else:
                    changes.append(('.hgsub', ''))
            elif entry[1] == '160000' or entry[0] == ':160000':
                if not skipsubmodules:
                    subexists[0] = True
            else:
                if renamesource:
                    h = nodemod.nullhex
                self.modecache[(f, h)] = (p and "x") or (s and "l") or ""
                changes.append((f, h))

        while i < lcount:
            l = difftree[i]
            i += 1
            if not entry:
                if not l.startswith(':'):
                    continue
                entry = l.split()
                continue
            f = l
            if entry[4][0] == 'C':
                copysrc = f
                copydest = difftree[i]
                i += 1
                f = copydest
                copies[copydest] = copysrc
            if f not in seen:
                add(entry, f, False)
            # A file can be copied multiple times, or modified and copied
            # simultaneously. So f can be repeated even if fdest isn't.
            if entry[4][0] == 'R':
                # rename: next line is the destination
                fdest = difftree[i]
                i += 1
                if fdest not in seen:
                    add(entry, fdest, True)
                    # .gitmodules isn't imported at all, so it being copied to
                    # and fro doesn't really make sense
                    if f != '.gitmodules' and fdest != '.gitmodules':
                        copies[fdest] = f
            entry = None
        if fh.close():
            raise error.Abort(_('cannot read changes in %s') % version)

        if subexists[0]:
            if subdeleted[0]:
                changes.append(('.hgsubstate', nodemod.nullhex))
            else:
                self.retrievegitmodules(version)
                changes.append(('.hgsubstate', ''))
        return (changes, copies, set())

    def getcommit(self, version):
        c = self.catfile(version, "commit") # read the commit hash
        end = c.find("\n\n")
        message = c[end + 2:]
        message = self.recode(message)
        l = c[:end].splitlines()
        parents = []
        author = committer = None
        for e in l[1:]:
            n, v = e.split(" ", 1)
            if n == "author":
                p = v.split()
                tm, tz = p[-2:]
                author = " ".join(p[:-2])
                if author[0] == "<": author = author[1:-1]
                author = self.recode(author)
            if n == "committer":
                p = v.split()
                tm, tz = p[-2:]
                committer = " ".join(p[:-2])
                if committer[0] == "<": committer = committer[1:-1]
                committer = self.recode(committer)
            if n == "parent":
                parents.append(v)

        if committer and committer != author:
            message += "\ncommitter: %s\n" % committer
        tzs, tzh, tzm = tz[-5:-4] + "1", tz[-4:-2], tz[-2:]
        tz = -int(tzs) * (int(tzh) * 3600 + int(tzm))
        date = tm + " " + str(tz)

        c = common.commit(parents=parents, date=date, author=author,
                          desc=message,
                          rev=version)
        return c

    def numcommits(self):
        return len([None for _ in self.gitopen('git rev-list --all')])

    def gettags(self):
        tags = {}
        alltags = {}
        fh = self.gitopen('git ls-remote --tags "%s"' % self.path,
                          err=subprocess.STDOUT)
        prefix = 'refs/tags/'

        # Build complete list of tags, both annotated and bare ones
        for line in fh:
            line = line.strip()
            if line.startswith("error:") or line.startswith("fatal:"):
                raise error.Abort(_('cannot read tags from %s') % self.path)
            node, tag = line.split(None, 1)
            if not tag.startswith(prefix):
                continue
            alltags[tag[len(prefix):]] = node
        if fh.close():
            raise error.Abort(_('cannot read tags from %s') % self.path)

        # Filter out tag objects for annotated tag refs
        for tag in alltags:
            if tag.endswith('^{}'):
                tags[tag[:-3]] = alltags[tag]
            else:
                if tag + '^{}' in alltags:
                    continue
                else:
                    tags[tag] = alltags[tag]

        return tags

    def getchangedfiles(self, version, i):
        changes = []
        if i is None:
            fh = self.gitopen("git diff-tree --root -m -r %s" % version)
            for l in fh:
                if "\t" not in l:
                    continue
                m, f = l[:-1].split("\t")
                changes.append(f)
        else:
            fh = self.gitopen('git diff-tree --name-only --root -r %s '
                              '"%s^%s" --' % (version, version, i + 1))
            changes = [f.rstrip('\n') for f in fh]
        if fh.close():
            raise error.Abort(_('cannot read changes in %s') % version)

        return changes

    def getbookmarks(self):
        bookmarks = {}

        # Handle local and remote branches
        remoteprefix = self.ui.config('convert', 'git.remoteprefix', 'remote')
        reftypes = [
            # (git prefix, hg prefix)
            ('refs/remotes/origin/', remoteprefix + '/'),
            ('refs/heads/', '')
        ]

        exclude = set([
            'refs/remotes/origin/HEAD',
        ])

        try:
            fh = self.gitopen('git show-ref', err=subprocess.PIPE)
            for line in fh:
                line = line.strip()
                rev, name = line.split(None, 1)
                # Process each type of branch
                for gitprefix, hgprefix in reftypes:
                    if not name.startswith(gitprefix) or name in exclude:
                        continue
                    name = '%s%s' % (hgprefix, name[len(gitprefix):])
                    bookmarks[name] = rev
        except Exception:
            pass

        return bookmarks

    def checkrevformat(self, revstr, mapname='splicemap'):
        """ git revision string is a 40 byte hex """
        self.checkhexformat(revstr, mapname)