def open_idx(filename):
if filename.endswith('.idx'):
f = open(filename, 'rb')
header = f.read(8)
if header[0:4] == '\377tOc':
version = struct.unpack('!I', header[4:8])[0]
if version == 2:
return PackIdxV2(filename, f)
else:
raise GitError('%s: expected idx file version 2, got %d'
% (filename, version))
elif len(header) == 8 and header[0:4] < '\377tOc':
return PackIdxV1(filename, f)
else:
raise GitError('%s: unrecognized idx file header' % filename)
elif filename.endswith('.midx'):
return midx.PackMidx(filename)
else:
raise GitError('idx filenames must end with .idx or .midx')
def refresh(self, skip_midx=False):
"""Refresh the index list.
This method verifies if .midx files were superseded (e.g. all of its
contents are in another, bigger .midx file) and removes the superseded
files.
If skip_midx is True, all work on .midx files will be skipped and .midx
files will be removed from the list.
The instance variable 'ignore_midx' can force this function to
always act as if skip_midx was True.
"""
if self.bloom is not None:
self.bloom.close()
self.bloom = None # Always reopen the bloom as it may have been relaced
self.do_bloom = False
skip_midx = skip_midx or self.ignore_midx
d = dict((p.name, p) for p in self.packs
if not skip_midx or not isinstance(p, midx.PackMidx))
if os.path.exists(self.dir):
if not skip_midx:
midxl = []
midxes = set(glob.glob(os.path.join(self.dir, b'*.midx')))
# remove any *.midx files from our list that no longer exist
for ix in list(d.values()):
if not isinstance(ix, midx.PackMidx):
continue
if ix.name in midxes:
continue
# remove the midx
del d[ix.name]
ix.close()
self.packs.remove(ix)
for ix in self.packs:
if isinstance(ix, midx.PackMidx):
for name in ix.idxnames:
d[os.path.join(self.dir, name)] = ix
for full in midxes:
if not d.get(full):
mx = midx.PackMidx(full)
(mxd, mxf) = os.path.split(mx.name)
broken = False
for n in mx.idxnames:
if not os.path.exists(os.path.join(mxd, n)):
log(('warning: index %s missing\n'
' used by %s\n') %
(path_msg(n), path_msg(mxf)))
broken = True
if broken:
mx.close()
del mx
unlink(full)
else:
midxl.append(mx)
midxl.sort(
key=lambda ix: (-len(ix), -xstat.stat(ix.name).st_mtime))
for ix in midxl:
any_needed = False
for sub in ix.idxnames:
found = d.get(os.path.join(self.dir, sub))
if not found or isinstance(found, PackIdx):
# doesn't exist, or exists but not in a midx
any_needed = True
break
if any_needed:
d[ix.name] = ix
for name in ix.idxnames:
d[os.path.join(self.dir, name)] = ix
elif not ix.force_keep:
debug1('midx: removing redundant: %s\n' %
path_msg(os.path.basename(ix.name)))
ix.close()
unlink(ix.name)
for full in glob.glob(os.path.join(self.dir, b'*.idx')):
if not d.get(full):
try:
ix = open_idx(full)
except GitError as e:
add_error(e)
continue
d[full] = ix
bfull = os.path.join(self.dir, b'bup.bloom')
if self.bloom is None and os.path.exists(bfull):
self.bloom = bloom.ShaBloom(bfull)
self.packs = list(set(d.values()))
self.packs.sort(reverse=True, key=lambda x: len(x))
if self.bloom and self.bloom.valid() and len(
self.bloom) >= len(self):
self.do_bloom = True
else:
self.bloom = None
debug1('PackIdxList: using %d index%s.\n' %
(len(self.packs), len(self.packs) != 1 and 'es' or ''))
def _do_midx(outdir, outfilename, infilenames, prefixstr):
global _first
if not outfilename:
assert (outdir)
sum = Sha1('\0'.join(infilenames)).hexdigest()
outfilename = '%s/midx-%s.midx' % (outdir, sum)
inp = []
total = 0
allfilenames = []
midxs = []
try:
for name in infilenames:
ix = git.open_idx(name)
midxs.append(ix)
inp.append((
ix.map,
len(ix),
ix.sha_ofs,
isinstance(ix, midx.PackMidx) and ix.which_ofs or 0,
len(allfilenames),
))
for n in ix.idxnames:
allfilenames.append(os.path.basename(n))
total += len(ix)
inp.sort(lambda x, y: cmp(str(y[0][y[2]:y[2] + 20]),
str(x[0][x[2]:x[2] + 20])))
if not _first: _first = outdir
dirprefix = (_first != outdir) and git.repo_rel(outdir) + ': ' or ''
debug1('midx: %s%screating from %d files (%d objects).\n' %
(dirprefix, prefixstr, len(infilenames), total))
if (opt.auto and (total < 1024 and len(infilenames) < 3)) \
or ((opt.auto or opt.force) and len(infilenames) < 2) \
or (opt.force and not total):
debug1('midx: nothing to do.\n')
return
pages = int(total / SHA_PER_PAGE) or 1
bits = int(math.ceil(math.log(pages, 2)))
entries = 2**bits
debug1('midx: table size: %d (%d bits)\n' % (entries * 4, bits))
unlink(outfilename)
f = open(outfilename + '.tmp', 'w+b')
f.write('MIDX')
f.write(struct.pack('!II', midx.MIDX_VERSION, bits))
assert (f.tell() == 12)
f.truncate(12 + 4 * entries + 20 * total + 4 * total)
f.flush()
fdatasync(f.fileno())
fmap = mmap_readwrite(f, close=False)
count = merge_into(fmap, bits, total, inp)
del fmap # Assume this calls msync() now.
finally:
for ix in midxs:
if isinstance(ix, midx.PackMidx):
ix.close()
midxs = None
inp = None
f.seek(0, os.SEEK_END)
f.write('\0'.join(allfilenames))
f.close()
os.rename(outfilename + '.tmp', outfilename)
# This is just for testing (if you enable this, don't clear inp above)
if 0:
p = midx.PackMidx(outfilename)
assert (len(p.idxnames) == len(infilenames))
print p.idxnames
assert (len(p) == total)
for pe, e in p, git.idxmerge(inp, final_progress=False):
pin = pi.next()
assert (i == pin)
assert (p.exists(i))
return total, outfilename
