/usr/lib/python3/dist-packages/simplestreams/util.py is in python3-simplestreams 0.1.0~bzr341-0ubuntu1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 | # Copyright (C) 2013 Canonical Ltd.
#
# Author: Scott Moser <scott.moser@canonical.com>
#
# Simplestreams is free software: you can redistribute it and/or modify it
# under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or (at your
# option) any later version.
#
# Simplestreams is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
# or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
# License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with Simplestreams. If not, see <http://www.gnu.org/licenses/>.
import errno
import hashlib
import os
import re
import subprocess
import tempfile
import time
import json
import simplestreams.contentsource as cs
from simplestreams.log import LOG
try:
ALGORITHMS = list(getattr(hashlib, 'algorithms'))
except AttributeError:
ALGORITHMS = list(hashlib.algorithms_available) # pylint: disable=E1101
ALIASNAME = "_aliases"
PGP_SIGNED_MESSAGE_HEADER = "-----BEGIN PGP SIGNED MESSAGE-----"
PGP_SIGNATURE_HEADER = "-----BEGIN PGP SIGNATURE-----"
PGP_SIGNATURE_FOOTER = "-----END PGP SIGNATURE-----"
_UNSET = object()
CHECKSUMS = ("md5", "sha256", "sha512")
READ_SIZE = (1024 * 10)
PRODUCTS_TREE_DATA = (
("products", "product_name"),
("versions", "version_name"),
("items", "item_name"),
)
PRODUCTS_TREE_HIERARCHY = [_k[0] for _k in PRODUCTS_TREE_DATA]
class SignatureMissingException(Exception):
pass
try:
# python2
_STRING_TYPES = (str, basestring, unicode)
except NameError:
# python3
_STRING_TYPES = (str,)
def stringitems(data):
f = {}
for k, v in data.items():
if isinstance(v, _STRING_TYPES):
f[k] = v
elif isinstance(v, (int, float)):
f[k] = str(v)
return f
def products_exdata(tree, pedigree, include_top=True, insert_fieldnames=True):
# given 'tree' and 'pedigree' return a 'flattened' dict that contains
# entries for all attributes of this item those that apply to its pedigree
harchy = PRODUCTS_TREE_DATA
exdata = {}
if include_top and tree:
exdata.update(stringitems(tree))
clevel = tree
for (n, key) in enumerate(pedigree):
dictname, fieldname = harchy[n]
clevel = clevel.get(dictname, {}).get(key, {})
exdata.update(stringitems(clevel))
if insert_fieldnames:
exdata[fieldname] = key
return exdata
def products_set(tree, data, pedigree):
harchy = PRODUCTS_TREE_HIERARCHY
cur = tree
for n in range(0, len(pedigree)):
if harchy[n] not in cur:
cur[harchy[n]] = {}
cur = cur[harchy[n]]
if n != (len(pedigree) - 1):
if pedigree[n] not in cur:
cur[pedigree[n]] = {}
cur = cur[pedigree[n]]
cur[pedigree[-1]] = data
def products_del(tree, pedigree):
harchy = PRODUCTS_TREE_HIERARCHY
cur = tree
for n in range(0, len(pedigree)):
if harchy[n] not in cur:
return
cur = cur[harchy[n]]
if n == (len(pedigree) - 1):
break
if pedigree[n] not in cur:
return
cur = cur[pedigree[n]]
if pedigree[-1] in cur:
del cur[pedigree[-1]]
def products_prune(tree):
for prodname in list(tree.get('products', {}).keys()):
keys = list(tree['products'][prodname].get('versions', {}).keys())
for vername in keys:
vtree = tree['products'][prodname]['versions'][vername]
for itemname in list(vtree.get('items', {}).keys()):
if not vtree['items'][itemname]:
del vtree['items'][itemname]
if 'items' not in vtree or not vtree['items']:
del tree['products'][prodname]['versions'][vername]
if ('versions' not in tree['products'][prodname] or
not tree['products'][prodname]['versions']):
del tree['products'][prodname]
if 'products' in tree and not tree['products']:
del tree['products']
def walk_products(tree, cb_product=None, cb_version=None, cb_item=None,
ret_finished=_UNSET):
# walk a product tree. callbacks are called with (item, tree, (pedigree))
for prodname, proddata in tree['products'].items():
if cb_product:
ret = cb_product(proddata, tree, (prodname,))
if ret_finished != _UNSET and ret == ret_finished:
return
if (not cb_version and not cb_item) or 'versions' not in proddata:
continue
for vername, verdata in proddata['versions'].items():
if cb_version:
ret = cb_version(verdata, tree, (prodname, vername))
if ret_finished != _UNSET and ret == ret_finished:
return
if not cb_item or 'items' not in verdata:
continue
for itemname, itemdata in verdata['items'].items():
ret = cb_item(itemdata, tree, (prodname, vername, itemname))
if ret_finished != _UNSET and ret == ret_finished:
return
def expand_tree(tree, refs=None, delete=False):
if refs is None:
refs = tree.get(ALIASNAME, None)
expand_data(tree, refs, delete)
def expand_data(data, refs=None, delete=False):
if isinstance(data, dict):
if isinstance(refs, dict):
for key in list(data.keys()):
if key == ALIASNAME:
continue
ref = refs.get(key)
if not ref:
continue
value = data.get(key)
if value and isinstance(value, str):
data.update(ref[value])
if delete:
del data[key]
for key in data:
expand_data(data[key], refs)
elif isinstance(data, list):
for item in data:
expand_data(item, refs)
def resolve_work(src, target, maxnum=None, keep=False, itemfilter=None,
sort_reverse=True):
# if more than maxnum items are in src, only the most recent maxnum will be
# stored in target. If keep is true, then the most recent maxnum items
# will be kept in target even if they are no longer in src.
# if keep is false the number in target will never be greater than that
# in src.
add = []
remove = []
reverse = sort_reverse
if maxnum is None and keep:
raise TypeError("maxnum(%s) cannot be None if keep is True" % maxnum)
if not (maxnum is None or isinstance(maxnum, int)):
raise TypeError("maxnum(%s) must be integer or None" % maxnum)
if not (keep is None or isinstance(keep, int)):
raise TypeError("keep(%s) must be integer or None" % keep)
# Ensure that all source items are passed through filters
# In case the filters have changed from the last run
for item in sorted(src, reverse=reverse):
if itemfilter is None or itemfilter(item):
if item not in target:
add.append(item)
for item in sorted(target, reverse=reverse):
if item not in src:
remove.append(item)
if keep and len(remove):
after_add = len(target) + len(add)
while len(remove) and (maxnum > (after_add - len(remove))):
remove.pop(0)
mtarget = sorted([f for f in target + add if f not in remove],
reverse=reverse)
if maxnum is not None and len(mtarget) > maxnum:
for item in mtarget[maxnum:]:
if item in target:
remove.append(item)
else:
add.pop(add.index(item))
remove = sorted(remove, reverse=bool(not reverse))
return(add, remove)
def policy_read_signed(content, path, keyring=None): # pylint: disable=W0613
# convenience wrapper around 'read_signed' for use MirrorReader policy
return read_signed(content=content, keyring=keyring)
def read_signed(content, keyring=None):
# ensure that content is signed by a key in keyring.
# if no keyring given use default.
if content.startswith(PGP_SIGNED_MESSAGE_HEADER):
# http://rfc-ref.org/RFC-TEXTS/2440/chapter7.html
cmd = ["gpg", "--batch", "--verify"]
if keyring:
cmd.append("--keyring=%s" % keyring)
cmd.append("-")
try:
_outerr = subp(cmd, data=content)
except subprocess.CalledProcessError as e:
LOG.debug("failed: %s\n out=%s\n err=%s" %
(' '.join(cmd), e.output[0], e.output[1]))
raise e
ret = {'body': '', 'signature': '', 'garbage': ''}
lines = content.splitlines()
i = 0
for i in range(0, len(lines)):
if lines[i] == PGP_SIGNED_MESSAGE_HEADER:
mode = "header"
continue
elif mode == "header":
if lines[i] != "":
mode = "body"
continue
elif lines[i] == PGP_SIGNATURE_HEADER:
mode = "signature"
continue
elif lines[i] == PGP_SIGNATURE_FOOTER:
mode = "garbage"
continue
# dash-escaped content in body
if lines[i].startswith("- ") and mode == "body":
ret[mode] += lines[i][2:] + "\n"
else:
ret[mode] += lines[i] + "\n"
return ret['body']
else:
raise SignatureMissingException("No signature found!")
def load_content(content):
if isinstance(content, bytes):
content = content.decode('utf-8')
return json.loads(content)
def dump_data(data):
return json.dumps(data, indent=1).encode('utf-8')
def timestamp(ts=None):
return time.strftime("%a, %d %b %Y %H:%M:%S +0000", time.gmtime(ts))
def item_checksums(item):
return {k: item[k] for k in CHECKSUMS if k in item}
class checksummer(object):
_hasher = None
algorithm = None
expected = None
def __init__(self, checksums):
# expects a dict of hashname/value
if not checksums:
self._hasher = None
return
for meth in CHECKSUMS:
if meth in checksums and meth in ALGORITHMS:
self._hasher = hashlib.new(meth)
self.algorithm = meth
self.expected = checksums.get(self.algorithm, None)
if not self._hasher:
raise TypeError("Unable to find suitable hash algorithm")
def update(self, data):
if self._hasher is None:
return
self._hasher.update(data)
def hexdigest(self):
if self._hasher is None:
return None
return self._hasher.hexdigest()
def check(self):
return (self.expected is None or self.expected == self.hexdigest())
def move_dups(src, target, sticky=None):
# given src = {e1: {a:a, b:c}, e2: {a:a, b:d, e:f}}
# update target with {a:a}, and delete 'a' from entries in dict1
# if a key exists in target, it will not be copied or deleted.
if sticky is None:
sticky = []
allkeys = set()
for entry in src:
allkeys.update(list(src[entry].keys()))
candidates = allkeys.difference(sticky)
updates = {}
for entry in list(src.keys()):
for k, v in src[entry].items():
if k not in candidates:
continue
if k in updates:
if v != updates[k] or not isinstance(v, str):
del updates[k]
candidates.remove(k)
else:
if isinstance(v, str) and target.get(k, v) == v:
updates[k] = v
else:
candidates.remove(k)
for entry in list(src.keys()):
for k in list(src[entry].keys()):
if k in updates:
del src[entry][k]
target.update(updates)
def products_condense(ptree, sticky=None):
# walk a products tree, copying up item keys as far as they'll go
def call_move_dups(cur, _tree, pedigree):
(_mtype, stname) = (("product", "versions"),
("version", "items"))[len(pedigree) - 1]
move_dups(cur.get(stname, {}), cur, sticky=sticky)
walk_products(ptree, cb_version=call_move_dups)
walk_products(ptree, cb_product=call_move_dups)
def assert_safe_path(path):
if path == "" or path is None:
return
path = str(path)
if os.path.isabs(path):
raise TypeError("Path '%s' is absolute path" % path)
bad = (".." + os.path.sep, "..." + os.path.sep)
for tok in bad:
if path.startswith(tok):
raise TypeError("Path '%s' starts with '%s'" % (path, tok))
bad = (os.path.sep + ".." + os.path.sep, os.path.sep + "..." + os.path.sep)
for tok in bad:
if tok in path:
raise TypeError("Path '%s' contains '%s'" % (path, tok))
def read_url(url):
return cs.UrlContentSource(url).read()
def mkdir_p(path):
try:
os.makedirs(path)
except OSError as exc:
if exc.errno != errno.EEXIST:
raise
return
def get_local_copy(contentsource, read_size=READ_SIZE):
(tfd, tpath) = tempfile.mkstemp()
tfile = os.fdopen(tfd, "wb")
try:
LOG.debug("getting local copy of %s", contentsource.url)
while True:
buf = contentsource.read(read_size)
tfile.write(buf)
if len(buf) != read_size:
break
return (tpath, True)
except Exception as e:
os.unlink(tpath)
raise e
def subp(args, data=None, capture=True, shell=False, env=None):
if not capture:
stdout, stderr = (None, None)
else:
stdout, stderr = (subprocess.PIPE, subprocess.PIPE)
sp = subprocess.Popen(args, stdout=stdout, stderr=stderr,
stdin=subprocess.PIPE, shell=shell, env=env)
if isinstance(data, str):
data = data.encode('utf-8')
(out, err) = sp.communicate(data)
if isinstance(out, bytes):
out = out.decode('utf-8')
if isinstance(err, bytes):
err = err.decode('utf-8')
rc = sp.returncode # pylint: disable=E1101
if rc != 0:
raise subprocess.CalledProcessError(rc, args, output=(out, err))
return (out, err)
def get_sign_cmd(path, output=None, inline=False):
cmd = ['gpg']
defkey = os.environ.get('SS_GPG_DEFAULT_KEY')
if defkey:
cmd.extend(['--default-key', defkey])
batch = os.environ.get('SS_GPG_BATCH', "1").lower()
if batch not in ("0", "false"):
cmd.append('--batch')
if output:
cmd.extend(['--output', output])
if inline:
cmd.append('--clearsign')
else:
cmd.extend(['--armor', '--detach-sign'])
cmd.extend([path])
return cmd
def make_signed_content_paths(content):
# loads json content. If it is a products:1.0 file
# then it fixes up 'path' elements to point to signed names (.sjson)
# returns tuple of (changed, updated)
data = json.loads(content)
if data.get("format") != "index:1.0":
return (False, None)
for content_ent in list(data.get('index', {}).values()):
path = content_ent.get('path')
if path.endswith(".json"):
content_ent['path'] = signed_fname(path, inline=True)
return (True, json.dumps(data, indent=1))
def signed_fname(fname, inline=True):
if inline:
sfname = fname[0:-len(".json")] + ".sjson"
else:
sfname = fname + ".gpg"
return sfname
def rm_f_file(fname, skip=None):
if skip is None:
skip = []
if fname in skip:
return
try:
os.unlink(fname)
except OSError as exc:
if exc.errno != errno.ENOENT:
raise
def sign_file(fname, inline=True, outfile=None):
if outfile is None:
outfile = signed_fname(fname, inline=inline)
rm_f_file(outfile, skip=["-"])
return subp(get_sign_cmd(path=fname, output=outfile, inline=inline))[0]
def sign_content(content, outfile="-", inline=True):
rm_f_file(outfile, skip=["-"])
return subp(args=get_sign_cmd(path="-", output=outfile, inline=inline),
data=content)[0]
def path_from_mirror_url(mirror, path):
if path is not None:
return (mirror, path)
path_regex = "streams/v1/.*[.](sjson|json)$"
result = re.search(path_regex, mirror)
if result:
path = mirror[result.start():]
mirror = mirror[:result.start()]
else:
path = "streams/v1/index.sjson"
return (mirror, path)
# vi: ts=4 expandtab
|