Avoid extra filelogs entries.
Right now, there are some situations in which localrepo.filecommit can
create filelog entries even though they're not needed. For example:
- permissions for a file have changed;
- qrefresh can create a filelog entry identical to its parent (see the
added test);
- convert-repo creates extra filelog entries in every merge where the
first parent has added files (for example, changeset ebebe9577a1a of
the kernel repo added extra filelog entries to files in the
arch/blackfin directory, even though the merge should only touch the
drivers/ata directory). This makes "hg log file" in a converted repo
less useful than it could be, since it may mention many merges that
don't actually touch that specific file.
They all come from the same basic problem: localrepo.commit (through
filecommit) creates new filelog entries for all files passed to it
(except for some cases during a merge).
Patch and test case provided by Benoit.
This should fix issue351.
# transaction.py - simple journalling scheme for mercurial
#
# This transaction scheme is intended to gracefully handle program
# errors and interruptions. More serious failures like system crashes
# can be recovered with an fsck-like tool. As the whole repository is
# effectively log-structured, this should amount to simply truncating
# anything that isn't referenced in the changelog.
#
# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms
# of the GNU General Public License, incorporated herein by reference.
from i18n import _
import os
class transaction(object):
def __init__(self, report, opener, journal, after=None):
self.journal = None
# abort here if the journal already exists
if os.path.exists(journal):
raise AssertionError(_("journal already exists - run hg recover"))
self.count = 1
self.report = report
self.opener = opener
self.after = after
self.entries = []
self.map = {}
self.journal = journal
self.file = open(self.journal, "w")
def __del__(self):
if self.journal:
if self.entries: self.abort()
self.file.close()
try: os.unlink(self.journal)
except: pass
def add(self, file, offset, data=None):
if file in self.map: return
self.entries.append((file, offset, data))
self.map[file] = len(self.entries) - 1
# add enough data to the journal to do the truncate
self.file.write("%s\0%d\n" % (file, offset))
self.file.flush()
def find(self, file):
if file in self.map:
return self.entries[self.map[file]]
return None
def replace(self, file, offset, data=None):
if file not in self.map:
raise KeyError(file)
index = self.map[file]
self.entries[index] = (file, offset, data)
self.file.write("%s\0%d\n" % (file, offset))
self.file.flush()
def nest(self):
self.count += 1
return self
def running(self):
return self.count > 0
def close(self):
self.count -= 1
if self.count != 0:
return
self.file.close()
self.entries = []
if self.after:
self.after()
else:
os.unlink(self.journal)
self.journal = None
def abort(self):
if not self.entries: return
self.report(_("transaction abort!\n"))
for f, o, ignore in self.entries:
try:
self.opener(f, "a").truncate(o)
except:
self.report(_("failed to truncate %s\n") % f)
self.entries = []
self.report(_("rollback completed\n"))
def rollback(opener, file):
files = {}
for l in open(file).readlines():
f, o = l.split('\0')
files[f] = o
for f in files:
o = files[f]
opener(f, "a").truncate(int(o))
os.unlink(file)