view mercurial/subrepo.py @ 10189:e451e599fbcf

patch: support diff data loss detection and upgrade

In worst case, generating diff in upgrade mode can be two times more expensive
than generating it in git mode directly: we may have to regenerate the whole
diff again whenever a git feature is detected. Also, the first diff attempt is
completely buffered instead of being streamed. That said, even without having
profiled it yet, I am convinced we can fast-path the upgrade mode if necessary
were it to be used in regular diff commands, and not only in mq where avoiding
data loss is worth the price.

# subrepo.py - sub-repository handling for Mercurial
#
# Copyright 2006, 2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2, incorporated herein by reference.

import errno, os, re
from i18n import _
import config, util, node, error
hg = None

nullstate = ('', '', 'empty')

def state(ctx):
    p = config.config()
    def read(f, sections=None, remap=None):
        if f in ctx:
            p.parse(f, ctx[f].data(), sections, remap, read)
        else:
            raise util.Abort(_("subrepo spec file %s not found") % f)

    if '.hgsub' in ctx:
        read('.hgsub')

    rev = {}
    if '.hgsubstate' in ctx:
        try:
            for l in ctx['.hgsubstate'].data().splitlines():
                revision, path = l.split(" ", 1)
                rev[path] = revision
        except IOError, err:
            if err.errno != errno.ENOENT:
                raise

    state = {}
    for path, src in p[''].items():
        kind = 'hg'
        if src.startswith('['):
            if ']' not in src:
                raise util.Abort(_('missing ] in subrepo source'))
            kind, src = src.split(']', 1)
            kind = kind[1:]
        state[path] = (src, rev.get(path, ''), kind)

    return state

def writestate(repo, state):
    repo.wwrite('.hgsubstate',
                ''.join(['%s %s\n' % (state[s][1], s)
                         for s in sorted(state)]), '')

def submerge(repo, wctx, mctx, actx):
    # working context, merging context, ancestor context
    if mctx == actx: # backwards?
        actx = wctx.p1()
    s1 = wctx.substate
    s2 = mctx.substate
    sa = actx.substate
    sm = {}

    repo.ui.debug("subrepo merge %s %s %s\n" % (wctx, mctx, actx))

    def debug(s, msg, r=""):
        if r:
            r = "%s:%s:%s" % r
        repo.ui.debug("  subrepo %s: %s %s\n" % (s, msg, r))

    for s, l in s1.items():
        if wctx != actx and wctx.sub(s).dirty():
            l = (l[0], l[1] + "+")
        a = sa.get(s, nullstate)
        if s in s2:
            r = s2[s]
            if l == r or r == a: # no change or local is newer
                sm[s] = l
                continue
            elif l == a: # other side changed
                debug(s, "other changed, get", r)
                wctx.sub(s).get(r)
                sm[s] = r
            elif l[0] != r[0]: # sources differ
                if repo.ui.promptchoice(
                    _(' subrepository sources for %s differ\n'
                      'use (l)ocal source (%s) or (r)emote source (%s)?')
                      % (s, l[0], r[0]),
                      (_('&Local'), _('&Remote')), 0):
                    debug(s, "prompt changed, get", r)
                    wctx.sub(s).get(r)
                    sm[s] = r
            elif l[1] == a[1]: # local side is unchanged
                debug(s, "other side changed, get", r)
                wctx.sub(s).get(r)
                sm[s] = r
            else:
                debug(s, "both sides changed, merge with", r)
                wctx.sub(s).merge(r)
                sm[s] = l
        elif l == a: # remote removed, local unchanged
            debug(s, "remote removed, remove")
            wctx.sub(s).remove()
        else:
            if repo.ui.promptchoice(
                _(' local changed subrepository %s which remote removed\n'
                  'use (c)hanged version or (d)elete?') % s,
                (_('&Changed'), _('&Delete')), 0):
                debug(s, "prompt remove")
                wctx.sub(s).remove()

    for s, r in s2.items():
        if s in s1:
            continue
        elif s not in sa:
            debug(s, "remote added, get", r)
            mctx.sub(s).get(r)
            sm[s] = r
        elif r != sa[s]:
            if repo.ui.promptchoice(
                _(' remote changed subrepository %s which local removed\n'
                  'use (c)hanged version or (d)elete?') % s,
                (_('&Changed'), _('&Delete')), 0) == 0:
                debug(s, "prompt recreate", r)
                wctx.sub(s).get(r)
                sm[s] = r

    # record merged .hgsubstate
    writestate(repo, sm)

def _abssource(repo, push=False):
    if hasattr(repo, '_subparent'):
        source = repo._subsource
        if source.startswith('/') or '://' in source:
            return source
        parent = _abssource(repo._subparent)
        if '://' in parent:
            if parent[-1] == '/':
                parent = parent[:-1]
            return parent + '/' + source
        return os.path.join(parent, repo._subsource)
    if push and repo.ui.config('paths', 'default-push'):
        return repo.ui.config('paths', 'default-push', repo.root)
    return repo.ui.config('paths', 'default', repo.root)

def subrepo(ctx, path):
    # subrepo inherently violates our import layering rules
    # because it wants to make repo objects from deep inside the stack
    # so we manually delay the circular imports to not break
    # scripts that don't use our demand-loading
    global hg
    import hg as h
    hg = h

    util.path_auditor(ctx._repo.root)(path)
    state = ctx.substate.get(path, nullstate)
    if state[2] not in types:
        raise util.Abort(_('unknown subrepo type %s') % t)
    return types[state[2]](ctx, path, state[:2])

# subrepo classes need to implement the following methods:
# __init__(self, ctx, path, state)
# dirty(self): returns true if the dirstate of the subrepo
#   does not match current stored state
# commit(self, text, user, date): commit the current changes
#   to the subrepo with the given log message. Use given
#   user and date if possible. Return the new state of the subrepo.
# remove(self): remove the subrepo (should verify the dirstate
#   is not dirty first)
# get(self, state): run whatever commands are needed to put the
#   subrepo into this state
# merge(self, state): merge currently-saved state with the new state.
# push(self, force): perform whatever action is analagous to 'hg push'
#   This may be a no-op on some systems.

class hgsubrepo(object):
    def __init__(self, ctx, path, state):
        self._path = path
        self._state = state
        r = ctx._repo
        root = r.wjoin(path)
        if os.path.exists(os.path.join(root, '.hg')):
            self._repo = hg.repository(r.ui, root)
        else:
            util.makedirs(root)
            self._repo = hg.repository(r.ui, root, create=True)
            f = file(os.path.join(root, '.hg', 'hgrc'), 'w')
            f.write('[paths]\ndefault = %s\n' % state[0])
            f.close()
        self._repo._subparent = r
        self._repo._subsource = state[0]

    def dirty(self):
        r = self._state[1]
        if r == '':
            return True
        w = self._repo[None]
        if w.p1() != self._repo[r]: # version checked out changed
            return True
        return w.dirty() # working directory changed

    def commit(self, text, user, date):
        self._repo.ui.debug("committing subrepo %s\n" % self._path)
        n = self._repo.commit(text, user, date)
        if not n:
            return self._repo['.'].hex() # different version checked out
        return node.hex(n)

    def remove(self):
        # we can't fully delete the repository as it may contain
        # local-only history
        self._repo.ui.note(_('removing subrepo %s\n') % self._path)
        hg.clean(self._repo, node.nullid, False)

    def _get(self, state):
        source, revision, kind = state
        try:
            self._repo.lookup(revision)
        except error.RepoError:
            self._repo._subsource = source
            self._repo.ui.status(_('pulling subrepo %s\n') % self._path)
            srcurl = _abssource(self._repo)
            other = hg.repository(self._repo.ui, srcurl)
            self._repo.pull(other)

    def get(self, state):
        self._get(state)
        source, revision, kind = state
        self._repo.ui.debug("getting subrepo %s\n" % self._path)
        hg.clean(self._repo, revision, False)

    def merge(self, state):
        self._get(state)
        cur = self._repo['.']
        dst = self._repo[state[1]]
        if dst.ancestor(cur) == cur:
            self._repo.ui.debug("updating subrepo %s\n" % self._path)
            hg.update(self._repo, state[1])
        else:
            self._repo.ui.debug("merging subrepo %s\n" % self._path)
            hg.merge(self._repo, state[1], remind=False)

    def push(self, force):
        # push subrepos depth-first for coherent ordering
        c = self._repo['']
        subs = c.substate # only repos that are committed
        for s in sorted(subs):
            c.sub(s).push(force)

        self._repo.ui.status(_('pushing subrepo %s\n') % self._path)
        dsturl = _abssource(self._repo, True)
        other = hg.repository(self._repo.ui, dsturl)
        self._repo.push(other, force)

class svnsubrepo(object):
    def __init__(self, ctx, path, state):
        self._path = path
        self._state = state
        self._ctx = ctx
        self._ui = ctx._repo.ui

    def _svncommand(self, commands):
        cmd = ['svn'] + commands + [self._path]
        cmd = [util.shellquote(arg) for arg in cmd]
        cmd = util.quotecommand(' '.join(cmd))
        write, read, err = util.popen3(cmd)
        retdata = read.read()
        err = err.read().strip()
        if err:
            raise util.Abort(err)
        return retdata

    def _wcrev(self):
        info = self._svncommand(['info'])
        mat = re.search('Revision: ([\d]+)\n', info)
        if not mat:
            return 0
        return mat.groups()[0]

    def _url(self):
        info = self._svncommand(['info'])
        mat = re.search('URL: ([^\n]+)\n', info)
        if not mat:
            return 0
        return mat.groups()[0]

    def _wcclean(self):
        status = self._svncommand(['status'])
        status = '\n'.join([s for s in status.splitlines() if s[0] != '?'])
        if status.strip():
            return False
        return True

    def dirty(self):
        if self._wcrev() == self._state[1] and self._wcclean():
            return False
        return True

    def commit(self, text, user, date):
        # user and date are out of our hands since svn is centralized
        if self._wcclean():
            return self._wcrev()
        commitinfo = self._svncommand(['commit', '-m', text])
        self._ui.status(commitinfo)
        newrev = re.search('Committed revision ([\d]+).', commitinfo)
        if not newrev:
            raise util.Abort(commitinfo.splitlines()[-1])
        newrev = newrev.groups()[0]
        self._ui.status(self._svncommand(['update', '-r', newrev]))
        return newrev

    def remove(self):
        if self.dirty():
            self._repo.ui.warn(_('not removing repo %s because'
                                 'it has changes.\n' % self._path))
            return
        self._repo.ui.note('removing subrepo %s\n' % self._path)
        shutil.rmtree(self._ctx.repo.join(self._path))

    def get(self, state):
        status = self._svncommand(['checkout', state[0], '--revision', state[1]])
        if not re.search('Checked out revision [\d]+.', status):
            raise util.Abort(status.splitlines()[-1])
        self._ui.status(status)

    def merge(self, state):
        old = int(self._state[1])
        new = int(state[1])
        if new > old:
            self.get(state)

    def push(self, force):
        # nothing for svn
        pass

types = {
    'hg': hgsubrepo,
    'svn': svnsubrepo,
    }