#!/usr/bin/env python
-import sys, re, errno, stat, time, math
-from bup import hashsplit, git, options, index, client
+import sys, stat, time, math
+from bup import hashsplit, git, options, index, client, metadata
from bup.helpers import *
+from bup.hashsplit import GIT_MODE_TREE, GIT_MODE_FILE, GIT_MODE_SYMLINK
optspec = """
bup save [-tc] [-n name] <filenames...>
--
-r,remote= remote repository path
+r,remote= hostname:/path/to/repo of remote repository
t,tree output a tree id
c,commit output a commit id
n,name= name of backup set to update (if any)
+d,date= date for the commit (seconds since the epoch)
v,verbose increase log output (can be used more than once)
q,quiet don't show progress meter
smaller= only back up files smaller than n bytes
+bwlimit= maximum bytes/sec to transmit to server
+f,indexfile= the name of the index file (normally BUP_DIR/bupindex)
+strip strips the path to every filename given
+strip-path= path-prefix to be stripped when saving
+graft= a graft point *old_path*=*new_path* (can be used more than once)
+#,compress= set compression level to # (0-9, 9 is highest) [1]
"""
-o = options.Options('bup save', optspec)
+o = options.Options(optspec)
(opt, flags, extra) = o.parse(sys.argv[1:])
git.check_repo_or_die()
if not extra:
o.fatal("no filenames given")
-opt.progress = (istty and not opt.quiet)
+opt.progress = (istty2 and not opt.quiet)
opt.smaller = parse_num(opt.smaller or 0)
+if opt.bwlimit:
+ client.bwlimit = parse_num(opt.bwlimit)
+if opt.date:
+ date = parse_date_or_fatal(opt.date, o.fatal)
+else:
+ date = time.time()
+
+if opt.strip and opt.strip_path:
+ o.fatal("--strip is incompatible with --strip-path")
+
+graft_points = []
+if opt.graft:
+ if opt.strip:
+ o.fatal("--strip is incompatible with --graft")
+
+ if opt.strip_path:
+ o.fatal("--strip-path is incompatible with --graft")
+
+ for (option, parameter) in flags:
+ if option == "--graft":
+ splitted_parameter = parameter.split('=')
+ if len(splitted_parameter) != 2:
+ o.fatal("a graft point must be of the form old_path=new_path")
+ old_path, new_path = splitted_parameter
+ if not (old_path and new_path):
+ o.fatal("a graft point cannot be empty")
+ graft_points.append((realpath(old_path), realpath(new_path)))
+
+is_reverse = os.environ.get('BUP_SERVER_REVERSE')
+if is_reverse and opt.remote:
+ o.fatal("don't use -r in reverse mode; it's automatic")
+
+if opt.name and opt.name.startswith('.'):
+ o.fatal("'%s' is not a valid branch name" % opt.name)
refname = opt.name and 'refs/heads/%s' % opt.name or None
-if opt.remote:
+if opt.remote or is_reverse:
cli = client.Client(opt.remote)
oldref = refname and cli.read_ref(refname) or None
w = cli.new_packwriter()
else:
cli = None
oldref = refname and git.read_ref(refname) or None
- w = git.PackWriter()
+ w = git.PackWriter(compression_level=opt.compress)
+
+handle_ctrl_c()
def eatslash(dir):
return dir
+# Metadata is stored in a file named .bupm in each directory. The
+# first metadata entry will be the metadata for the current directory.
+# The remaining entries will be for each of the other directory
+# elements, in the order they're listed in the index.
+#
+# Since the git tree elements are sorted according to
+# git.shalist_item_sort_key, the metalist items are accumulated as
+# (sort_key, metadata) tuples, and then sorted when the .bupm file is
+# created. The sort_key must be computed using the element's real
+# name and mode rather than the git mode and (possibly mangled) name.
+
parts = ['']
shalists = [[]]
+metalists = [[]]
-def _push(part):
+def _push(part, metadata):
assert(part)
parts.append(part)
shalists.append([])
+ # First entry is dir metadata, which is represented with an empty name.
+ metalists.append([('', metadata)])
def _pop(force_tree):
assert(len(parts) >= 1)
part = parts.pop()
shalist = shalists.pop()
+ metalist = metalists.pop()
+ if metalist:
+ sorted_metalist = sorted(metalist, key = lambda x : x[0])
+ metadata = ''.join([m[1].encode() for m in sorted_metalist])
+ shalist.append((0100644, '.bupm', w.new_blob(metadata)))
tree = force_tree or w.new_tree(shalist)
if shalists:
- shalists[-1].append(('40000', part, tree))
- else: # this was the toplevel, so put it back for sanity
+ shalists[-1].append((GIT_MODE_TREE,
+ git.mangle_name(part,
+ GIT_MODE_TREE, GIT_MODE_TREE),
+ tree))
+ else:
+ # This was the toplevel, so put it back for sanity (i.e. cd .. from /).
shalists.append(shalist)
+ metalists.append(metalist)
return tree
lastremain = None
remainstr = '%dm%d' % (mins, secs)
else:
remainstr = '%ds' % secs
- progress('Saving: %.2f%% (%d/%dk, %d/%d files) %s %s\r'
- % (pct, cc/1024, total/1024, fcount, ftotal,
- remainstr, kpsstr))
+ qprogress('Saving: %.2f%% (%d/%dk, %d/%d files) %s %s\r'
+ % (pct, cc/1024, total/1024, fcount, ftotal,
+ remainstr, kpsstr))
-r = index.Reader(git.repo('bupindex'))
+indexfile = opt.indexfile or git.repo('bupindex')
+r = index.Reader(indexfile)
def already_saved(ent):
return ent.is_valid() and w.exists(ent.sha) and ent.sha
def wantrecurse_during(ent):
return not already_saved(ent) or ent.sha_missing()
+
total = ftotal = 0
-if opt.progress or 1:
+if opt.progress:
for (transname,ent) in r.filter(extra, wantrecurse=wantrecurse_pre):
if not (ftotal % 10024):
- progress('Reading index: %d\r' % ftotal)
+ qprogress('Reading index: %d\r' % ftotal)
exists = ent.exists()
hashvalid = already_saved(ent)
ent.set_sha_missing(not hashvalid)
continue
assert(dir.startswith('/'))
- dirp = dir.split('/')
- while parts > dirp:
+ if opt.strip:
+ dirp = stripped_path_components(dir, extra)
+ elif opt.strip_path:
+ dirp = stripped_path_components(dir, [opt.strip_path])
+ elif graft_points:
+ dirp = grafted_path_components(graft_points, dir)
+ else:
+ dirp = path_components(dir)
+
+ while parts > [x[0] for x in dirp]:
_pop(force_tree = None)
+
if dir != '/':
- for part in dirp[len(parts):]:
- _push(part)
+ for path_component in dirp[len(parts):]:
+ dir_name, fs_path = path_component
+ if fs_path:
+ meta = metadata.from_path(fs_path)
+ else:
+ meta = metadata.Metadata()
+ _push(dir_name, meta)
if not file:
+ # no filename portion means this is a subdir. But
# sub/parentdirectories already handled in the pop/push() part above.
oldtree = already_saved(ent) # may be None
newtree = _pop(force_tree = oldtree)
if lastskip_name and lastskip_name.startswith(ent.name):
ent.invalidate()
else:
- ent.validate(040000, newtree)
+ ent.validate(GIT_MODE_TREE, newtree)
ent.repack()
if exists and wasmissing:
count += oldsize
# it's not a directory
id = None
if hashvalid:
- mode = '%o' % ent.gitmode
id = ent.sha
- shalists[-1].append((mode, file, id))
+ git_name = git.mangle_name(file, ent.mode, ent.gitmode)
+ git_info = (ent.gitmode, git_name, id)
+ shalists[-1].append(git_info)
+ sort_key = git.shalist_item_sort_key((ent.mode, file, id))
+ metalists[-1].append((sort_key, metadata.from_path(ent.name)))
else:
if stat.S_ISREG(ent.mode):
try:
- f = open(ent.name)
- except IOError, e:
- add_error(e)
- lastskip_name = ent.name
- except OSError, e:
+ f = hashsplit.open_noatime(ent.name)
+ except (IOError, OSError), e:
add_error(e)
lastskip_name = ent.name
else:
- (mode, id) = hashsplit.split_to_blob_or_tree(w, [f])
+ try:
+ (mode, id) = hashsplit.split_to_blob_or_tree(
+ w.new_blob, w.new_tree, [f],
+ keep_boundaries=False)
+ except (IOError, OSError), e:
+ add_error('%s: %s' % (ent.name, e))
+ lastskip_name = ent.name
else:
if stat.S_ISDIR(ent.mode):
assert(0) # handled above
elif stat.S_ISLNK(ent.mode):
try:
rl = os.readlink(ent.name)
- except OSError, e:
- add_error(e)
- lastskip_name = ent.name
- except IOError, e:
+ except (OSError, IOError), e:
add_error(e)
lastskip_name = ent.name
else:
- (mode, id) = ('120000', w.new_blob(rl))
+ (mode, id) = (GIT_MODE_SYMLINK, w.new_blob(rl))
else:
- add_error(Exception('skipping special file "%s"' % ent.name))
- lastskip_name = ent.name
+ # Everything else should be fully described by its
+ # metadata, so just record an empty blob, so the paths
+ # in the tree and .bupm will match up.
+ (mode, id) = (GIT_MODE_FILE, w.new_blob(""))
+
if id:
- ent.validate(int(mode, 8), id)
+ ent.validate(mode, id)
ent.repack()
- shalists[-1].append((mode, file, id))
+ git_name = git.mangle_name(file, ent.mode, ent.gitmode)
+ git_info = (mode, git_name, id)
+ shalists[-1].append(git_info)
+ sort_key = git.shalist_item_sort_key((ent.mode, file, id))
+ metalists[-1].append((sort_key, metadata.from_path(ent.name)))
if exists and wasmissing:
count += oldsize
subcount = 0
progress('Saving: %.2f%% (%d/%dk, %d/%d files), done. \n'
% (pct, count/1024, total/1024, fcount, ftotal))
-while len(parts) > 1:
+while len(parts) > 1: # _pop() all the parts above the indexed items.
_pop(force_tree = None)
assert(len(shalists) == 1)
+assert(len(metalists) == 1)
+
+if not (opt.strip or opt.strip_path or graft_points):
+ # For now, only save metadata for the root directory when there
+ # isn't any path grafting or stripping that might create multiple
+ # roots.
+ shalist = shalists[-1]
+ metadata = ''.join([metadata.from_path('/').encode()])
+ shalist.append((0100644, '.bupm', w.new_blob(metadata)))
tree = w.new_tree(shalists[-1])
+
if opt.tree:
print tree.encode('hex')
if opt.commit or opt.name:
msg = 'bup save\n\nGenerated by command:\n%r' % sys.argv
- ref = opt.name and ('refs/heads/%s' % opt.name) or None
- commit = w.new_commit(oldref, tree, msg)
+ commit = w.new_commit(oldref, tree, date, msg)
if opt.commit:
print commit.encode('hex')
if saved_errors:
log('WARNING: %d errors encountered while saving.\n' % len(saved_errors))
+ sys.exit(1)