Mercurial > hg
view mercurial/filelog.py @ 20836:a8b4541bb961
grep: reuse the first "util.binary()" result for efficiency
Before this patch, to check whether the file in the specified revision
is binary or not, "util.binary()" is invoked via internal function
"binary()" of "hg grep" once per a line of "hg grep" output, even
though binary-ness is not changed in the same file.
This patch reuses the first "util.binary()" invocation result by
annotating internal function "binary()" with "@util.cachefunc".
Performance improvement measured by "hgperf grep -r 88d8e568add1 vfs
mercurial/scmutil.py":
before this patch:
! wall 0.024000 comb 0.015600 user 0.015600 sys 0.000000 (best of 118)
after this patch:
! wall 0.023000 comb 0.015600 user 0.015600 sys 0.000000 (best of 123)
Status of recent(88d8e568add1) "mercurial/scmutil.py":
# of lines: 919 (may affect cost of search)
# of bytes: 29633 (may affect cost of "util.binary()")
# of matches: 22 (may affect frequency of "util.binary()")
author | FUJIWARA Katsunori <foozy@lares.dti.ne.jp> |
---|---|
date | Sat, 15 Feb 2014 19:52:36 +0900 |
parents | 3bda242bf244 |
children | 4669e26747c3 |
line wrap: on
line source
# filelog.py - file history 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. import revlog import re _mdre = re.compile('\1\n') def _parsemeta(text): """return (metadatadict, keylist, metadatasize)""" # text can be buffer, so we can't use .startswith or .index if text[:2] != '\1\n': return None, None, None s = _mdre.search(text, 2).start() mtext = text[2:s] meta = {} keys = [] for l in mtext.splitlines(): k, v = l.split(": ", 1) meta[k] = v keys.append(k) return meta, keys, (s + 2) def _packmeta(meta, keys=None): if not keys: keys = sorted(meta.iterkeys()) return "".join("%s: %s\n" % (k, meta[k]) for k in keys) class filelog(revlog.revlog): def __init__(self, opener, path): super(filelog, self).__init__(opener, "/".join(("data", path + ".i"))) def read(self, node): t = self.revision(node) if not t.startswith('\1\n'): return t s = t.index('\1\n', 2) return t[s + 2:] def add(self, text, meta, transaction, link, p1=None, p2=None): if meta or text.startswith('\1\n'): text = "\1\n%s\1\n%s" % (_packmeta(meta), text) return self.addrevision(text, transaction, link, p1, p2) def renamed(self, node): if self.parents(node)[0] != revlog.nullid: return False t = self.revision(node) m = _parsemeta(t)[0] if m and "copy" in m: return (m["copy"], revlog.bin(m["copyrev"])) return False def size(self, rev): """return the size of a given revision""" # for revisions with renames, we have to go the slow way node = self.node(rev) if self.renamed(node): return len(self.read(node)) # XXX if self.read(node).startswith("\1\n"), this returns (size+4) return super(filelog, self).size(rev) def cmp(self, node, text): """compare text with a given file revision returns True if text is different than what is stored. """ t = text if text.startswith('\1\n'): t = '\1\n\1\n' + text samehashes = not super(filelog, self).cmp(node, t) if samehashes: return False # renaming a file produces a different hash, even if the data # remains unchanged. Check if it's the case (slow): if self.renamed(node): t2 = self.read(node) return t2 != text return True def _file(self, f): return filelog(self.opener, f)