Mercurial > hg
view hgext/convert/cvs.py @ 16719:e7bf09acd410
localrepo: add branchtip() method for faster single-branch lookups
For the PyPy repo with 744 branches and 843 branch heads, this brings
hg log -r default over NFS from:
CallCount Recursive Total(ms) Inline(ms) module:lineno(function)
3249 0 1.3222 1.3222 <open>
3244 0 0.6211 0.6211 <method 'close' of 'file' objects>
3243 0 0.0800 0.0800 <method 'read' of 'file' objects>
3241 0 0.0660 0.0660 <method 'seek' of 'file' objects>
3905 0 0.0476 0.0476 <zlib.decompress>
3281 0 2.6756 0.0472 mercurial.changelog:182(read)
+3281 0 2.5256 0.0453 +mercurial.revlog:881(revision)
+3276 0 0.0389 0.0196 +mercurial.changelog:28(decodeextra)
+6562 0 0.0123 0.0123 +<method 'split' of 'str' objects>
+6562 0 0.0408 0.0073 +mercurial.encoding:61(tolocal)
+3281 0 0.0054 0.0054 +<method 'index' of 'str' objects>
3241 0 2.2464 0.0456 mercurial.revlog:818(_loadchunk)
+3241 0 0.6205 0.6205 +<method 'close' of 'file' objects>
+3241 0 0.0765 0.0765 +<method 'read' of 'file' objects>
+3241 0 0.0660 0.0660 +<method 'seek' of 'file' objects>
+3241 0 1.4209 0.0135 +mercurial.store:374(__call__)
+3241 0 0.0122 0.0107 +mercurial.revlog:810(_addchunk)
3281 0 2.5256 0.0453 mercurial.revlog:881(revision)
+3280 0 0.0175 0.0175 +mercurial.revlog:305(rev)
+3281 0 2.2819 0.0119 +mercurial.revlog:847(_chunkraw)
+3281 0 0.0603 0.0083 +mercurial.revlog:945(_checkhash)
+3281 0 0.0051 0.0051 +mercurial.revlog:349(flags)
+3281 0 0.0040 0.0040 +<mercurial.mpatch.patches>
13682 0 0.0479 0.0248 <method 'decode' of 'str' objects>
+7418 0 0.0228 0.0076 +encodings.utf_8:15(decode)
+1 0 0.0003 0.0000 +encodings:71(search_function)
3248 0 1.3995 0.0246 mercurial.scmutil:218(__call__)
+3248 0 1.3222 1.3222 +<open>
+3248 0 0.0235 0.0184 +os.path:80(split)
+3248 0 0.0084 0.0068 +mercurial.scmutil:92(__call__)
Time: real 2.750 secs (user 0.680+0.000 sys 0.360+0.000)
down to:
CallCount Recursive Total(ms) Inline(ms) module:lineno(function)
55 31 0.0197 0.0163 <__import__>
+1 0 0.0006 0.0002 +mercurial.context:8(<module>)
+1 0 0.0042 0.0001 +mercurial.revlog:12(<module>)
+1 0 0.0002 0.0001 +mercurial.match:8(<module>)
+1 0 0.0003 0.0001 +mercurial.dirstate:7(<module>)
+1 0 0.0057 0.0001 +mercurial.changelog:8(<module>)
1 0 0.0117 0.0032 mercurial.localrepo:525(_readbranchcache)
+844 0 0.0015 0.0015 +<binascii.unhexlify>
+845 0 0.0010 0.0010 +<method 'split' of 'str' objects>
+843 0 0.0045 0.0009 +mercurial.encoding:61(tolocal)
+843 0 0.0004 0.0004 +<method 'setdefault' of 'dict' objects>
+1 0 0.0003 0.0003 +<method 'close' of 'file' objects>
3 0 0.0029 0.0029 <method 'read' of 'file' objects>
9 0 0.0018 0.0018 <open>
990 0 0.0017 0.0017 <binascii.unhexlify>
53 0 0.0016 0.0016 mercurial.demandimport:43(__init__)
862 0 0.0015 0.0015 <_codecs.utf_8_decode>
862 0 0.0037 0.0014 <method 'decode' of 'str' objects>
+862 0 0.0023 0.0008 +encodings.utf_8:15(decode)
981 0 0.0011 0.0011 <method 'split' of 'str' objects>
861 0 0.0046 0.0009 mercurial.encoding:61(tolocal)
+861 0 0.0037 0.0014 +<method 'decode' of 'str' objects>
862 0 0.0023 0.0008 encodings.utf_8:15(decode)
+862 0 0.0015 0.0015 +<_codecs.utf_8_decode>
4 0 0.0008 0.0008 <method 'close' of 'file' objects>
179 154 0.0202 0.0004 mercurial.demandimport:83(__getattribute__)
+36 11 0.0199 0.0003 +mercurial.demandimport:55(_load)
+72 0 0.0001 0.0001 +mercurial.demandimport:83(__getattribute__)
+36 0 0.0000 0.0000 +<getattr>
1 0 0.0015 0.0004 mercurial.tags:148(_readtagcache)
Time: real 0.060 secs (user 0.030+0.000 sys 0.010+0.000)
author | Brodie Rao <brodie@sf.io> |
---|---|
date | Sun, 13 May 2012 14:04:04 +0200 |
parents | 525fdb738975 |
children | e7cfe3587ea4 |
line wrap: on
line source
# cvs.py: CVS conversion code inspired by hg-cvs-import and git-cvsimport # # 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. import os, re, socket, errno from cStringIO import StringIO from mercurial import encoding, util from mercurial.i18n import _ from common import NoRepo, commit, converter_source, checktool import cvsps class convert_cvs(converter_source): def __init__(self, ui, path, rev=None): super(convert_cvs, self).__init__(ui, path, rev=rev) cvs = os.path.join(path, "CVS") if not os.path.exists(cvs): raise NoRepo(_("%s does not look like a CVS checkout") % path) checktool('cvs') self.changeset = None self.files = {} self.tags = {} self.lastbranch = {} self.socket = None self.cvsroot = open(os.path.join(cvs, "Root")).read()[:-1] self.cvsrepo = open(os.path.join(cvs, "Repository")).read()[:-1] self.encoding = encoding.encoding self._connect() def _parse(self): if self.changeset is not None: return self.changeset = {} maxrev = 0 if self.rev: # TODO: handle tags try: # patchset number? maxrev = int(self.rev) except ValueError: raise util.Abort(_('revision %s is not a patchset number') % self.rev) d = os.getcwd() try: os.chdir(self.path) id = None cache = 'update' if not self.ui.configbool('convert', 'cvsps.cache', True): cache = None db = cvsps.createlog(self.ui, cache=cache) db = cvsps.createchangeset(self.ui, db, fuzz=int(self.ui.config('convert', 'cvsps.fuzz', 60)), mergeto=self.ui.config('convert', 'cvsps.mergeto', None), mergefrom=self.ui.config('convert', 'cvsps.mergefrom', None)) for cs in db: if maxrev and cs.id > maxrev: break id = str(cs.id) cs.author = self.recode(cs.author) self.lastbranch[cs.branch] = id cs.comment = self.recode(cs.comment) date = util.datestr(cs.date, '%Y-%m-%d %H:%M:%S %1%2') self.tags.update(dict.fromkeys(cs.tags, id)) files = {} for f in cs.entries: files[f.file] = "%s%s" % ('.'.join([str(x) for x in f.revision]), ['', '(DEAD)'][f.dead]) # add current commit to set c = commit(author=cs.author, date=date, parents=[str(p.id) for p in cs.parents], desc=cs.comment, branch=cs.branch or '') self.changeset[id] = c self.files[id] = files self.heads = self.lastbranch.values() finally: os.chdir(d) def _connect(self): root = self.cvsroot conntype = None user, host = None, None cmd = ['cvs', 'server'] self.ui.status(_("connecting to %s\n") % root) if root.startswith(":pserver:"): root = root[9:] m = re.match(r'(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?(.*)', root) if m: conntype = "pserver" user, passw, serv, port, root = m.groups() if not user: user = "anonymous" if not port: port = 2401 else: port = int(port) format0 = ":pserver:%s@%s:%s" % (user, serv, root) format1 = ":pserver:%s@%s:%d%s" % (user, serv, port, root) if not passw: passw = "A" cvspass = os.path.expanduser("~/.cvspass") try: pf = open(cvspass) for line in pf.read().splitlines(): part1, part2 = line.split(' ', 1) # /1 :pserver:user@example.com:2401/cvsroot/foo # Ah<Z if part1 == '/1': part1, part2 = part2.split(' ', 1) format = format1 # :pserver:user@example.com:/cvsroot/foo Ah<Z else: format = format0 if part1 == format: passw = part2 break pf.close() except IOError, inst: if inst.errno != errno.ENOENT: if not getattr(inst, 'filename', None): inst.filename = cvspass raise sck = socket.socket() sck.connect((serv, port)) sck.send("\n".join(["BEGIN AUTH REQUEST", root, user, passw, "END AUTH REQUEST", ""])) if sck.recv(128) != "I LOVE YOU\n": raise util.Abort(_("CVS pserver authentication failed")) self.writep = self.readp = sck.makefile('r+') if not conntype and root.startswith(":local:"): conntype = "local" root = root[7:] if not conntype: # :ext:user@host/home/user/path/to/cvsroot if root.startswith(":ext:"): root = root[5:] m = re.match(r'(?:([^@:/]+)@)?([^:/]+):?(.*)', root) # Do not take Windows path "c:\foo\bar" for a connection strings if os.path.isdir(root) or not m: conntype = "local" else: conntype = "rsh" user, host, root = m.group(1), m.group(2), m.group(3) if conntype != "pserver": if conntype == "rsh": rsh = os.environ.get("CVS_RSH") or "ssh" if user: cmd = [rsh, '-l', user, host] + cmd else: cmd = [rsh, host] + cmd # popen2 does not support argument lists under Windows cmd = [util.shellquote(arg) for arg in cmd] cmd = util.quotecommand(' '.join(cmd)) self.writep, self.readp = util.popen2(cmd) self.realroot = root self.writep.write("Root %s\n" % root) self.writep.write("Valid-responses ok error Valid-requests Mode" " M Mbinary E Checked-in Created Updated" " Merged Removed\n") self.writep.write("valid-requests\n") self.writep.flush() r = self.readp.readline() if not r.startswith("Valid-requests"): raise util.Abort(_('unexpected response from CVS server ' '(expected "Valid-requests", but got %r)') % r) if "UseUnchanged" in r: self.writep.write("UseUnchanged\n") self.writep.flush() r = self.readp.readline() def getheads(self): self._parse() return self.heads def getfile(self, name, rev): def chunkedread(fp, count): # file-objects returned by socked.makefile() do not handle # large read() requests very well. chunksize = 65536 output = StringIO() while count > 0: data = fp.read(min(count, chunksize)) if not data: raise util.Abort(_("%d bytes missing from remote file") % count) count -= len(data) output.write(data) return output.getvalue() self._parse() if rev.endswith("(DEAD)"): raise IOError args = ("-N -P -kk -r %s --" % rev).split() args.append(self.cvsrepo + '/' + name) for x in args: self.writep.write("Argument %s\n" % x) self.writep.write("Directory .\n%s\nco\n" % self.realroot) self.writep.flush() data = "" mode = None while True: line = self.readp.readline() if line.startswith("Created ") or line.startswith("Updated "): self.readp.readline() # path self.readp.readline() # entries mode = self.readp.readline()[:-1] count = int(self.readp.readline()[:-1]) data = chunkedread(self.readp, count) elif line.startswith(" "): data += line[1:] elif line.startswith("M "): pass elif line.startswith("Mbinary "): count = int(self.readp.readline()[:-1]) data = chunkedread(self.readp, count) else: if line == "ok\n": if mode is None: raise util.Abort(_('malformed response from CVS')) return (data, "x" in mode and "x" or "") elif line.startswith("E "): self.ui.warn(_("cvs server: %s\n") % line[2:]) elif line.startswith("Remove"): self.readp.readline() else: raise util.Abort(_("unknown CVS response: %s") % line) def getchanges(self, rev): self._parse() return sorted(self.files[rev].iteritems()), {} def getcommit(self, rev): self._parse() return self.changeset[rev] def gettags(self): self._parse() return self.tags def getchangedfiles(self, rev, i): self._parse() return sorted(self.files[rev])