Mercurial > hg
view mercurial/changelog.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 | bc84a1aeaf5a |
children | 62c56c94c77e |
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 version 2 or any later version. from node import bin, hex, nullid from i18n import _ import util, error, revlog, encoding _defaultextra = {'branch': 'default'} 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 == res.decode('string_escape') True """ # subset of the string_escape codec text = text.replace('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r') return text.replace('\0', '\\0') def decodeextra(text): """ >>> decodeextra(encodeextra({'foo': 'bar', 'baz': chr(0) + '2'})) {'foo': 'bar', 'baz': '\\x002', 'branch': 'default'} >>> decodeextra(encodeextra({'foo': 'bar', 'baz': chr(92) + chr(0) + '2'})) {'foo': 'bar', 'baz': '\\\\\\x002', 'branch': 'default'} """ extra = _defaultextra.copy() for l in text.split('\0'): if l: if '\\0' in l: # fix up \0 without getting into trouble with \\0 l = l.replace('\\\\', '\\\\\n') l = l.replace('\\0', '\0') l = l.replace('\n', '') k, v = l.decode('string_escape').split(':', 1) extra[k] = v return extra def encodeextra(d): # keys must be sorted to produce a deterministic changelog entry items = [_string_escape('%s:%s' % (k, d[k])) for k in sorted(d)] return "\0".join(items) class appender(object): '''the changelog index must be updated 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(str(s)) self.offset += len(s) def delayopener(opener, target, divert, buf): def o(name, mode='r'): if name != target: return opener(name, mode) if divert: return opener(name + ".a", mode.replace('a', 'w')) # otherwise, divert to memory return appender(opener(name, mode), buf) return o class changelog(revlog.revlog): def __init__(self, opener): revlog.revlog.__init__(self, opener, "00changelog.i") if self._initempty: # changelogs don't benefit from generaldelta self.version &= ~revlog.REVLOGGENERALDELTA self._generaldelta = False self._realopener = opener self._delayed = False self._divert = False # hiddenrevs: revs that should be hidden by command and tools self.hiddenrevs = set() def delayupdate(self): "delay visibility of index updates to other readers" self._delayed = True self._divert = (len(self) == 0) self._delaybuf = [] self.opener = delayopener(self._realopener, self.indexfile, self._divert, self._delaybuf) def finalize(self, tr): "finalize index updates" self._delayed = False self.opener = self._realopener # move redirected index data back into place if self._divert: nfile = self.opener(self.indexfile + ".a") n = nfile.name nfile.close() util.rename(n, n[:-2]) elif self._delaybuf: fp = self.opener(self.indexfile, 'a') fp.write("".join(self._delaybuf)) fp.close() self._delaybuf = [] # split when we're done self.checkinlinesize(tr) def readpending(self, file): r = revlog.revlog(self.opener, file) self.index = r.index self.nodemap = r.nodemap self._nodecache = r._nodecache self._chunkcache = r._chunkcache def writepending(self): "create a file containing the unfinalized state for pretxnchangegroup" if self._delaybuf: # make a temporary copy of the index fp1 = self._realopener(self.indexfile) fp2 = self._realopener(self.indexfile + ".a", "w") fp2.write(fp1.read()) # add pending data fp2.write("".join(self._delaybuf)) fp2.close() # switch modes so finalize can simply rename self._delaybuf = [] self._divert = True if self._divert: return True return False def checkinlinesize(self, tr, fp=None): if not self._delayed: revlog.revlog.checkinlinesize(self, tr, fp) def read(self, node): """ 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 """ text = self.revision(node) if not text: return (nullid, "", (0, 0), [], "", _defaultextra) last = text.index("\n\n") desc = encoding.tolocal(text[last + 2:]) l = text[:last].split('\n') manifest = bin(l[0]) user = encoding.tolocal(l[1]) tdata = l[2].split(' ', 2) if len(tdata) != 3: time = float(tdata[0]) try: # various tools did silly things with the time zone field. timezone = int(tdata[1]) except ValueError: timezone = 0 extra = _defaultextra else: time, timezone = float(tdata[0]), int(tdata[1]) extra = decodeextra(tdata[2]) files = l[3:] return (manifest, user, (time, timezone), files, desc, extra) def add(self, manifest, files, desc, transaction, p1, p2, user, date=None, extra=None): # Convert to UTF-8 encoded bytestrings as the very first # thing: calling any method on a localstr object will turn it # into a str object and the cached UTF-8 string is thus lost. user, desc = encoding.fromlocal(user), encoding.fromlocal(desc) user = user.strip() # An empty username or a username with a "\n" will make the # revision text contain two "\n\n" sequences -> corrupt # repository since read cannot unpack the revision. if not user: raise error.RevlogError(_("empty username")) if "\n" in user: raise error.RevlogError(_("username %s contains a newline") % repr(user)) # strip trailing whitespace and leading and trailing empty lines desc = '\n'.join([l.rstrip() for l in desc.splitlines()]).strip('\n') if date: parseddate = "%d %d" % util.parsedate(date) else: parseddate = "%d %d" % util.makedate() if extra: branch = extra.get("branch") if branch in ("default", ""): del extra["branch"] elif branch in (".", "null", "tip"): raise error.RevlogError(_('the name \'%s\' is reserved') % branch) if extra: extra = encodeextra(extra) parseddate = "%s %s" % (parseddate, extra) l = [hex(manifest), user, parseddate] + sorted(files) + ["", desc] text = "\n".join(l) return self.addrevision(text, transaction, len(self), p1, p2)