Mercurial > hg
view mercurial/manifest.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 | 9724f8f8850b |
line wrap: on
line source
# manifest.py - manifest revision 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 i18n import _ import mdiff, parsers, error, revlog, util import array, struct class manifestdict(dict): def __init__(self, mapping=None, flags=None): if mapping is None: mapping = {} if flags is None: flags = {} dict.__init__(self, mapping) self._flags = flags def flags(self, f): return self._flags.get(f, "") def withflags(self): return set(self._flags.keys()) def set(self, f, flags): self._flags[f] = flags def copy(self): return manifestdict(self, dict.copy(self._flags)) class manifest(revlog.revlog): def __init__(self, opener): self._mancache = None revlog.revlog.__init__(self, opener, "00manifest.i") def parse(self, lines): mfdict = manifestdict() parsers.parse_manifest(mfdict, mfdict._flags, lines) return mfdict def readdelta(self, node): r = self.rev(node) return self.parse(mdiff.patchtext(self.revdiff(self.deltaparent(r), r))) def readfast(self, node): '''use the faster of readdelta or read''' r = self.rev(node) deltaparent = self.deltaparent(r) if deltaparent != revlog.nullrev and deltaparent in self.parentrevs(r): return self.readdelta(node) return self.read(node) def read(self, node): if node == revlog.nullid: return manifestdict() # don't upset local cache if self._mancache and self._mancache[0] == node: return self._mancache[1] text = self.revision(node) arraytext = array.array('c', text) mapping = self.parse(text) self._mancache = (node, mapping, arraytext) return mapping def _search(self, m, s, lo=0, hi=None): '''return a tuple (start, end) that says where to find s within m. If the string is found m[start:end] are the line containing that string. If start == end the string was not found and they indicate the proper sorted insertion point. This was taken from bisect_left, and modified to find line start/end as it goes along. m should be a buffer or a string s is a string''' def advance(i, c): while i < lenm and m[i] != c: i += 1 return i if not s: return (lo, lo) lenm = len(m) if not hi: hi = lenm while lo < hi: mid = (lo + hi) // 2 start = mid while start > 0 and m[start - 1] != '\n': start -= 1 end = advance(start, '\0') if m[start:end] < s: # we know that after the null there are 40 bytes of sha1 # this translates to the bisect lo = mid + 1 lo = advance(end + 40, '\n') + 1 else: # this translates to the bisect hi = mid hi = start end = advance(lo, '\0') found = m[lo:end] if s == found: # we know that after the null there are 40 bytes of sha1 end = advance(end + 40, '\n') return (lo, end + 1) else: return (lo, lo) def find(self, node, f): '''look up entry for a single file efficiently. return (node, flags) pair if found, (None, None) if not.''' if self._mancache and self._mancache[0] == node: return self._mancache[1].get(f), self._mancache[1].flags(f) text = self.revision(node) start, end = self._search(text, f) if start == end: return None, None l = text[start:end] f, n = l.split('\0') return revlog.bin(n[:40]), n[40:-1] def add(self, map, transaction, link, p1=None, p2=None, changed=None): # apply the changes collected during the bisect loop to our addlist # return a delta suitable for addrevision def addlistdelta(addlist, x): # start from the bottom up # so changes to the offsets don't mess things up. for start, end, content in reversed(x): if content: addlist[start:end] = array.array('c', content) else: del addlist[start:end] return "".join(struct.pack(">lll", start, end, len(content)) + content for start, end, content in x) def checkforbidden(l): for f in l: if '\n' in f or '\r' in f: raise error.RevlogError( _("'\\n' and '\\r' disallowed in filenames: %r") % f) # if we're using the cache, make sure it is valid and # parented by the same node we're diffing against if not (changed and self._mancache and p1 and self._mancache[0] == p1): files = sorted(map) checkforbidden(files) # if this is changed to support newlines in filenames, # be sure to check the templates/ dir again (especially *-raw.tmpl) hex, flags = revlog.hex, map.flags text = ''.join("%s\0%s%s\n" % (f, hex(map[f]), flags(f)) for f in files) arraytext = array.array('c', text) cachedelta = None else: added, removed = changed addlist = self._mancache[2] checkforbidden(added) # combine the changed lists into one list for sorting work = [(x, False) for x in added] work.extend((x, True) for x in removed) # this could use heapq.merge() (from python2.6+) or equivalent # since the lists are already sorted work.sort() delta = [] dstart = None dend = None dline = [""] start = 0 # zero copy representation of addlist as a buffer addbuf = util.buffer(addlist) # start with a readonly loop that finds the offset of # each line and creates the deltas for f, todelete in work: # bs will either be the index of the item or the insert point start, end = self._search(addbuf, f, start) if not todelete: l = "%s\0%s%s\n" % (f, revlog.hex(map[f]), map.flags(f)) else: if start == end: # item we want to delete was not found, error out raise AssertionError( _("failed to remove %s from manifest") % f) l = "" if dstart is not None and dstart <= start and dend >= start: if dend < end: dend = end if l: dline.append(l) else: if dstart is not None: delta.append([dstart, dend, "".join(dline)]) dstart = start dend = end dline = [l] if dstart is not None: delta.append([dstart, dend, "".join(dline)]) # apply the delta to the addlist, and get a delta for addrevision cachedelta = (self.rev(p1), addlistdelta(addlist, delta)) arraytext = addlist text = util.buffer(arraytext) n = self.addrevision(text, transaction, link, p1, p2, cachedelta) self._mancache = (n, map, arraytext) return n