##// END OF EJS Templates
wireproto: support disabling bundle1 only if repo is generaldelta...
wireproto: support disabling bundle1 only if repo is generaldelta I recently implemented the server.bundle1* options to control whether bundle1 exchange is allowed. After thinking about Mozilla's strategy for handling generaldelta rollout a bit more, I think server operators need an additional lever: disable bundle1 if and only if the repo is generaldelta. bundle1 exchange for non-generaldelta repos will not have the potential for CPU explosion that generaldelta repos do. Therefore, it makes sense for server operators to continue to allow bundle1 exchange for non-generaldelta repos without having to set a per-repo hgrc option to change the policy depending on whether the repo is generaldelta. This patch introduces a new set of options to control bundle1 behavior for generaldelta repos. These options enable server operators to limit bundle1 restrictions to the class of repos that can be performance issues. It also allows server operators to tie bundle1 access to store format. In many server environments (including Mozilla's), legacy repos will not be generaldelta and new repos will or might be. New repos often aren't bound by legacy access requirements, so setting a global policy that disallows access to new/generaldelta repos via bundle1 could be a reasonable policy in many server environments. This patch makes this policy very easy to implement (modify global hgrc, add options to existing generaldelta repos to grandfather them in).

File last commit:

r27359:a56c47ed default
r27633:37d7cf56 default
Show More
similar.py
108 lines | 3.6 KiB | text/x-python | PythonLexer
# similar.py - mechanisms for finding similar files
#
# 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 __future__ import absolute_import
from .i18n import _
from . import (
bdiff,
mdiff,
util,
)
def _findexactmatches(repo, added, removed):
'''find renamed files that have no changes
Takes a list of new filectxs and a list of removed filectxs, and yields
(before, after) tuples of exact matches.
'''
numfiles = len(added) + len(removed)
# Get hashes of removed files.
hashes = {}
for i, fctx in enumerate(removed):
repo.ui.progress(_('searching for exact renames'), i, total=numfiles)
h = util.sha1(fctx.data()).digest()
hashes[h] = fctx
# For each added file, see if it corresponds to a removed file.
for i, fctx in enumerate(added):
repo.ui.progress(_('searching for exact renames'), i + len(removed),
total=numfiles)
h = util.sha1(fctx.data()).digest()
if h in hashes:
yield (hashes[h], fctx)
# Done
repo.ui.progress(_('searching for exact renames'), None)
def _findsimilarmatches(repo, added, removed, threshold):
'''find potentially renamed files based on similar file content
Takes a list of new filectxs and a list of removed filectxs, and yields
(before, after, score) tuples of partial matches.
'''
copies = {}
for i, r in enumerate(removed):
repo.ui.progress(_('searching for similar files'), i,
total=len(removed))
# lazily load text
@util.cachefunc
def data():
orig = r.data()
return orig, mdiff.splitnewlines(orig)
def score(text):
orig, lines = data()
# bdiff.blocks() returns blocks of matching lines
# count the number of bytes in each
equal = 0
matches = bdiff.blocks(text, orig)
for x1, x2, y1, y2 in matches:
for line in lines[y1:y2]:
equal += len(line)
lengths = len(text) + len(orig)
return equal * 2.0 / lengths
for a in added:
bestscore = copies.get(a, (None, threshold))[1]
myscore = score(a.data())
if myscore >= bestscore:
copies[a] = (r, myscore)
repo.ui.progress(_('searching'), None)
for dest, v in copies.iteritems():
source, score = v
yield source, dest, score
def findrenames(repo, added, removed, threshold):
'''find renamed files -- yields (before, after, score) tuples'''
parentctx = repo['.']
workingctx = repo[None]
# Zero length files will be frequently unrelated to each other, and
# tracking the deletion/addition of such a file will probably cause more
# harm than good. We strip them out here to avoid matching them later on.
addedfiles = set([workingctx[fp] for fp in added
if workingctx[fp].size() > 0])
removedfiles = set([parentctx[fp] for fp in removed
if fp in parentctx and parentctx[fp].size() > 0])
# Find exact matches.
for (a, b) in _findexactmatches(repo,
sorted(addedfiles), sorted(removedfiles)):
addedfiles.remove(b)
yield (a.path(), b.path(), 1.0)
# If the user requested similar files to be matched, search for them also.
if threshold < 1.0:
for (a, b, score) in _findsimilarmatches(repo,
sorted(addedfiles), sorted(removedfiles), threshold):
yield (a.path(), b.path(), score)