1
# Copyright (C) 2006, 2007, 2009, 2010 Canonical Ltd
3
# This program is free software; you can redistribute it and/or modify
4
# it under the terms of the GNU General Public License as published by
5
# the Free Software Foundation; either version 2 of the License, or
6
# (at your option) any later version.
8
# This program is distributed in the hope that it will be useful,
9
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
# GNU General Public License for more details.
13
# You should have received a copy of the GNU General Public License
14
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
17
"""Common code for generating file or revision ids."""
19
from bzrlib.lazy_import import lazy_import
20
lazy_import(globals(), """
35
# the regex removes any weird characters; we don't escape them
36
# but rather just pull them out
37
_file_id_chars_re = lazy_regex.lazy_compile(r'[^\w.]')
38
_rev_id_chars_re = lazy_regex.lazy_compile(r'[^-\w.+@]')
39
_gen_file_id_suffix = None
40
_gen_file_id_serial = 0
43
def _next_id_suffix():
44
"""Create a new file id suffix that is reasonably unique.
46
On the first call we combine the current time with 64 bits of randomness to
47
give a highly probably globally unique number. Then each call in the same
48
process adds 1 to a serial number we append to that unique value.
50
# XXX TODO: change bzrlib.add.smart_add_tree to call workingtree.add() rather
51
# than having to move the id randomness out of the inner loop like this.
52
# XXX TODO: for the global randomness this uses we should add the thread-id
53
# before the serial #.
54
# XXX TODO: jam 20061102 I think it would be good to reset every 100 or
55
# 1000 calls, or perhaps if time.time() increases by a certain
56
# amount. time.time() shouldn't be terribly expensive to call,
57
# and it means that long-lived processes wouldn't use the same
59
global _gen_file_id_suffix, _gen_file_id_serial
60
if _gen_file_id_suffix is None:
61
_gen_file_id_suffix = "-%s-%s-" % (osutils.compact_date(time.time()),
62
osutils.rand_chars(16))
63
_gen_file_id_serial += 1
64
return _gen_file_id_suffix + str(_gen_file_id_serial)
67
def gen_file_id(name):
68
"""Return new file id for the basename 'name'.
70
The uniqueness is supplied from _next_id_suffix.
72
# The real randomness is in the _next_id_suffix, the
73
# rest of the identifier is just to be nice.
75
# 1) Remove non-ascii word characters to keep the ids portable
76
# 2) squash to lowercase, so the file id doesn't have to
77
# be escaped (case insensitive filesystems would bork for ids
78
# that only differ in case without escaping).
79
# 3) truncate the filename to 20 chars. Long filenames also bork on some
81
# 4) Removing starting '.' characters to prevent the file ids from
82
# being considered hidden.
83
ascii_word_only = str(_file_id_chars_re.sub('', name.lower()))
84
short_no_dots = ascii_word_only.lstrip('.')[:20]
85
return short_no_dots + _next_id_suffix()
89
"""Return a new tree-root file id."""
90
return gen_file_id('tree_root')
93
def gen_revision_id(username, timestamp=None):
94
"""Return new revision-id.
96
:param username: The username of the committer, in the format returned by
97
config.username(). This is typically a real name, followed by an
98
email address. If found, we will use just the email address portion.
99
Otherwise we flatten the real name, and use that.
100
:return: A new revision id.
103
user_or_email = config.extract_email_address(username)
104
except errors.NoEmailInUsername:
105
user_or_email = username
107
user_or_email = user_or_email.lower()
108
user_or_email = user_or_email.replace(' ', '_')
109
user_or_email = _rev_id_chars_re.sub('', user_or_email)
111
# This gives 36^16 ~= 2^82.7 ~= 83 bits of entropy
112
unique_chunk = osutils.rand_chars(16)
114
if timestamp is None:
115
timestamp = time.time()
117
rev_id = u'-'.join((user_or_email,
118
osutils.compact_date(timestamp),
120
return rev_id.encode('utf8')