view mercurial/changelog.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 d1bee415406e
children c728424d44c6
line wrap: on
line source

# changelog.py - changelog class for mercurial
#
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms
# of the GNU General Public License, incorporated herein by reference.

from revlog import *
from i18n import _
import os, time, util

def _string_escape(text):
    """
    >>> d = {'nl': chr(10), 'bs': chr(92), 'cr': chr(13), 'nul': chr(0)}
    >>> s = "ab%(nl)scd%(bs)s%(bs)sn%(nul)sab%(cr)scd%(bs)s%(nl)s" % d
    >>> s
    'ab\\ncd\\\\\\\\n\\x00ab\\rcd\\\\\\n'
    >>> res = _string_escape(s)
    >>> s == _string_unescape(res)
    True
    """
    # subset of the string_escape codec
    text = text.replace('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r')
    return text.replace('\0', '\\0')

def _string_unescape(text):
    return text.decode('string_escape')

class appender:
    '''the changelog index must be update last on disk, so we use this class
    to delay writes to it'''
    def __init__(self, fp, buf):
        self.data = buf
        self.fp = fp
        self.offset = fp.tell()
        self.size = util.fstat(fp).st_size

    def end(self):
        return self.size + len("".join(self.data))
    def tell(self):
        return self.offset
    def flush(self):
        pass
    def close(self):
        self.fp.close()

    def seek(self, offset, whence=0):
        '''virtual file offset spans real file and data'''
        if whence == 0:
            self.offset = offset
        elif whence == 1:
            self.offset += offset
        elif whence == 2:
            self.offset = self.end() + offset
        if self.offset < self.size:
            self.fp.seek(self.offset)

    def read(self, count=-1):
        '''only trick here is reads that span real file and data'''
        ret = ""
        if self.offset < self.size:
            s = self.fp.read(count)
            ret = s
            self.offset += len(s)
            if count > 0:
                count -= len(s)
        if count != 0:
            doff = self.offset - self.size
            self.data.insert(0, "".join(self.data))
            del self.data[1:]
            s = self.data[0][doff:doff+count]
            self.offset += len(s)
            ret += s
        return ret

    def write(self, s):
        self.data.append(s)
        self.offset += len(s)

class changelog(revlog):
    def __init__(self, opener):
        revlog.__init__(self, opener, "00changelog.i")

    def delayupdate(self):
        "delay visibility of index updates to other readers"
        self._realopener = self.opener
        self.opener = self._delayopener
        self._delaycount = self.count()
        self._delaybuf = []
        self._delayname = None

    def finalize(self, tr):
        "finalize index updates"
        self.opener = self._realopener
        # move redirected index data back into place
        if self._delayname:
            util.rename(self._delayname + ".a", self._delayname)
        elif self._delaybuf:
            fp = self.opener(self.indexfile, 'a')
            fp.write("".join(self._delaybuf))
            fp.close()
            del self._delaybuf
        # split when we're done
        self.checkinlinesize(tr)

    def _delayopener(self, name, mode='r'):
        fp = self._realopener(name, mode)
        # only divert the index
        if not name == self.indexfile:
            return fp
        # if we're doing an initial clone, divert to another file
        if self._delaycount == 0:
            self._delayname = fp.name
            return self._realopener(name + ".a", mode)
        # otherwise, divert to memory
        return appender(fp, self._delaybuf)

    def checkinlinesize(self, tr, fp=None):
        if self.opener == self._delayopener:
            return
        return revlog.checkinlinesize(self, tr, fp)

    def decode_extra(self, text):
        extra = {}
        for l in text.split('\0'):
            if not l:
                continue
            k, v = _string_unescape(l).split(':', 1)
            extra[k] = v
        return extra

    def encode_extra(self, d):
        # keys must be sorted to produce a deterministic changelog entry
        keys = d.keys()
        keys.sort()
        items = [_string_escape('%s:%s' % (k, d[k])) for k in keys]
        return "\0".join(items)

    def extract(self, text):
        """
        format used:
        nodeid\n        : manifest node in ascii
        user\n          : user, no \n or \r allowed
        time tz extra\n : date (time is int or float, timezone is int)
                        : extra is metadatas, encoded and separated by '\0'
                        : older versions ignore it
        files\n\n       : files modified by the cset, no \n or \r allowed
        (.*)            : comment (free text, ideally utf-8)

        changelog v0 doesn't use extra
        """
        if not text:
            return (nullid, "", (0, 0), [], "", {'branch': 'default'})
        last = text.index("\n\n")
        desc = util.tolocal(text[last + 2:])
        l = text[:last].split('\n')
        manifest = bin(l[0])
        user = util.tolocal(l[1])

        extra_data = l[2].split(' ', 2)
        if len(extra_data) != 3:
            time = float(extra_data.pop(0))
            try:
                # various tools did silly things with the time zone field.
                timezone = int(extra_data[0])
            except:
                timezone = 0
            extra = {}
        else:
            time, timezone, extra = extra_data
            time, timezone = float(time), int(timezone)
            extra = self.decode_extra(extra)
        if not extra.get('branch'):
            extra['branch'] = 'default'
        files = l[3:]
        return (manifest, user, (time, timezone), files, desc, extra)

    def read(self, node):
        return self.extract(self.revision(node))

    def add(self, manifest, list, desc, transaction, p1=None, p2=None,
                  user=None, date=None, extra={}):

        user, desc = util.fromlocal(user), util.fromlocal(desc)

        if date:
            parseddate = "%d %d" % util.parsedate(date)
        else:
            parseddate = "%d %d" % util.makedate()
        if extra and extra.get("branch") in ("default", ""):
            del extra["branch"]
        if extra:
            extra = self.encode_extra(extra)
            parseddate = "%s %s" % (parseddate, extra)
        list.sort()
        l = [hex(manifest), user, parseddate] + list + ["", desc]
        text = "\n".join(l)
        return self.addrevision(text, transaction, self.count(), p1, p2)