view hgext/convert/git.py @ 5192:33015dac5df5

convert: fix mercurial_sink.putcommit Changeset 4ebc8693ce72 added some code to putcommit to avoid creating a revision that touches no files, but this can break regular conversions from some repositories: - conceptually, since we're converting a repo, we should try to make the new hg repo as similar as possible to the original repo - we should create a new changeset, even if the original revision didn't touch any files (maybe the commit message had some important bit); - even if a "regular" revision that doesn't touch any file may seem weird (and maybe even broken), it's completely legitimate for a merge revision to not touch any file, and, if we just skip it, the converted repo will end up with wrong history and possibly an extra head. As an example, say the crew and main hg repos are sync'ed. Somebody sends an important patch to the mailing list. Matt quickly applies and pushes it. But at the same time somebody also applies it to crew and pushes it. Suppose the commit message ended up being a bit different (say, there was a typo and somebody didn't fix it) or that the date ended up being different (because of different patch-applying scripts): the changeset hashes will be different, but the manifests will be the same. Since both changesets were pushed to public repos, it's hard to recall them. If both are merged, the manifest from the resulting merge revision will have the exact same contents as its parents - i.e. the merge revision really doesn't touch any file at all. To keep the file filtering stuff "working", the generic code was changed to skip empty revisions if we're filtering the repo, fixing a bug in the process (we want parents[0] instead of tip).
author Alexis S. L. Carvalho <alexis@cecm.usp.br>
date Fri, 17 Aug 2007 20:18:05 -0300
parents ef338e34a906
children 7d3dcdd92a1a
line wrap: on
line source

# git support for the convert extension

import os

from common import NoRepo, commit, converter_source

class convert_git(converter_source):
    def gitcmd(self, s):
        return os.popen('GIT_DIR=%s %s' % (self.path, s))

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

        if os.path.isdir(path + "/.git"):
            path += "/.git"
        if not os.path.exists(path + "/objects"):
            raise NoRepo("couldn't open GIT repo %s" % path)
        self.path = path

    def getheads(self):
        if not self.rev:
            return self.gitcmd('git-rev-parse --branches').read().splitlines()
        else:
            fh = self.gitcmd("git-rev-parse --verify %s" % self.rev)
            return [fh.read()[:-1]]

    def catfile(self, rev, type):
        if rev == "0" * 40: raise IOError()
        fh = self.gitcmd("git-cat-file %s %s 2>/dev/null" % (type, rev))
        return fh.read()

    def getfile(self, name, rev):
        return self.catfile(rev, "blob")

    def getmode(self, name, rev):
        return self.modecache[(name, rev)]

    def getchanges(self, version):
        self.modecache = {}
        fh = self.gitcmd("git-diff-tree --root -m -r %s" % version)
        changes = []
        for l in fh:
            if "\t" not in l: continue
            m, f = l[:-1].split("\t")
            m = m.split()
            h = m[3]
            p = (m[1] == "100755")
            s = (m[1] == "120000")
            self.modecache[(f, h)] = (p and "x") or (s and "l") or ""
            changes.append((f, h))
        return (changes, {})

    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()
        manifest = l[0].split()[1]
        parents = []
        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)
                message += "\ncommitter: %s\n" % committer
            if n == "parent": parents.append(v)

        tzs, tzh, tzm = tz[-5:-4] + "1", tz[-4:-2], tz[-2:]
        tz = -int(tzs) * (int(tzh) * 3600 + int(tzm))
        date = tm + " " + str(tz)
        author = author or "unknown"

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

    def gettags(self):
        tags = {}
        fh = self.gitcmd('git-ls-remote --tags "%s" 2>/dev/null' % self.path)
        prefix = 'refs/tags/'
        for line in fh:
            line = line.strip()
            if not line.endswith("^{}"):
                continue
            node, tag = line.split(None, 1)
            if not tag.startswith(prefix):
                continue
            tag = tag[len(prefix):-3]
            tags[tag] = node

        return tags