/usr/share/pyshared/dmedia/schema.py is in python-dmedia 0.6.0~repack-1build1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 | # Authors:
# Jason Gerard DeRose <jderose@novacut.com>
#
# dmedia: distributed media library
# Copyright (C) 2011 Jason Gerard DeRose <jderose@novacut.com>
#
# This file is part of `dmedia`.
#
# `dmedia` 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.
#
# `dmedia` 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 `dmedia`. If not, see <http://www.gnu.org/licenses/>.
"""
Test-driven definition of dmedia CouchDB schema.
The goal of this module is to:
1. Unambiguously define the CouchDB schema via a series of test functions
2. Provide exceedingly helpful error messages when values do not conform
with the schema
For example:
>>> good = {
... '_id': 'NZXXMYLDOV2F6ZTUO5PWM5DX',
... 'ver': 0,
... 'type': 'dmedia/foo',
... 'time': 1234567890,
... }
...
>>> check_dmedia(good) # Returns None
>>> bad = {
... '_id': 'NZXXMYLDOV2F6ZTUO5PWM5DX',
... 'ver': 0,
... 'kind': 'dmedia/foo',
... 'timestamp': 1234567890,
... }
...
>>> check_dmedia(bad)
Traceback (most recent call last):
...
ValueError: doc missing keys: ['time', 'type']
These test functions are used in the dmedia test suite, and 3rd-party apps would
be well served by doing the same. Please read on for the rationale of some key
dmedia schema design decisions...
Design Decision: base32-encoded document IDs
============================================
dmedia utilizes both random (abstract) IDs and intrinsic IDs (derived from file
content-hash). Both kinds of IDs will always be a multiple of 40-bits (5-bytes)
and will be base32-encoded. Base32-encoding was chosen because:
1. It's more compact than base16/hex
2. It can be used in URLs with no escaping
3. Importantly, it can be used to name files on case *insensitive*
filesystems (whereas base64-encoding cannot)
At its core, dmedia is a simple layered filesystem, so being able to create a
filename directly from a document ID is an important design consideration.
Random IDs
----------
Random IDs are 120-bit random numbers, base32-encoded. They're much like a
Version 4 (random) UUID, except dmedia random IDs have no reserved bits. For
example:
>>> random_id() #doctest: +SKIP
'NZXXMYLDOV2F6ZTUO5PWM5DX'
Intrinsic IDs
-------------
Files in the dmedia library are uniquely identified by their content-hash.
dmedia *is* a distributed filesystem, but a quite simple one in that it only
stores intrinsically-named, read-only files.
The content-hash is computed as a hash-list (a 1 deep tree-hash). Currently
this is done using the sha1 hash function with an 8 MiB leaf size, but both the
hash function and leaf size are designed to be configurable to allow for future
migration.
The content-hashes of the individual leaves are stored in the "leaves"
attachment in the CouchDB document. This allows for file integrity checks with
8 MiB granularity, and provides the basis for cryptographically robust swarm
upload and download.
The base32-encoded sha1 hash is 32-characters long. For example:
>>> from dmedia.filestore import HashList
>>> from dmedia.tests import sample_mov # Sample .MOV file
>>> src_fp = open(sample_mov, 'rb')
>>> hashlist = HashList(src_fp)
>>> hashlist.run()
'TGX33XXWU3EVHEEY5J7NBOJGKBFXLEBK'
After calling `HashList.run()`, the binary digests of the leaf content-hashes
are available via the ``leaves`` attribute (which is a ``list``):
>>> from base64 import b32encode
>>> for d in hashlist.leaves:
... print(repr(b32encode(d)))
...
'IXJTSUCYYFECGSG6JIB2R77CAJVJK4W3'
'MA3IAHUOKXR4TRG7CWAPOO7U4WCV5WJ4'
'FHF7KDMAGNYOVNYSYT6ZYWQLUOCTUADI'
The overall file content-hash (aka the top-hash) is a hash of the leaf hashes.
Note that this matches what was returned by `HashList.run()`:
>>> from hashlib import sha1
>>> b32encode(sha1(''.join(hashlist.leaves)).digest())
'ZR765XWSF6S7JQHLUI4GCG5BHGPE252O'
In the near future dmedia will very likely migrate to using a 200-bit Skein-512
hash. See:
http://packages.python.org/pyskein/
Design Decision: mime-like record types
=======================================
FIXME: This needs to be discussed with the desktopcouch people, but for now I'm
documenting it here to clarify the idea. --jderose 2011-02-04
The desktopcouch convention is for each document to have a "record_type"
attribute containing the URL of a webpage describing the schema. For example:
>>> doc = {
... 'record_type': 'http://www.freedesktop.org/wiki/Specifications/desktopcouch/contact',
... }
Although the "record_type" convention addresses an important need (standardizing
CouchDB schema for cross-application use), it has some practical problems that
have been encountered in dmedia:
1. URLs are too long and awkward if you need to frequently compare the
record_type with constant values (eg, in map functions, in client-side
JavaScript, etc)
2. URLs aren't the greatest long-term stable identifier, and there is a
tendency for the wiki documentation to lag behind the code
3. The "record_type" convention is fairly convenient when used from the
desktopcouch Python API, but gets a bit awkward when used from
JavaScript or otherwise making direct HTTP requests
So currently dmedia is using something similar in spirit, but a lot simpler in
practice. For example:
>>> doc = {
... 'type': 'dmedia/file',
... }
The current dmedia record types include:
dmedia/file
Each file has a corresponding CouchDB document, and this is its type
dmedia/machine
One for each unique machine (computer/phone/etc) that is a peer in a
dmedia library
dmedia/store
One for each "place" files can be stored - used for both FileStore on
dmedia peers and for services (like UbuntuOne or Amazon S3)
dmedia/import
One is created each time an SD/CF card is imported
dmedia/batch
One is created for each batch of imports (imports done in parallel with
multiple card readers)
For additional information on desktopcouch and record types, see:
http://www.freedesktop.org/wiki/Specifications/desktopcouch
https://launchpad.net/desktopcouch
Design Decision: Unix timestamps
================================
All timestamps in the core dmedia schema are ``int`` or ``float`` values
expressing the time in seconds since the epoch, UTC. This was chosen because:
1. It avoids the eternal mess of storing times in local-time
2. All useful comparisons (including deltas) can be quickly done without
first converting from a calendar representation to Unix time
All dmedia records have a "time" attribute, which is the timestamp of when the
document was first added to CouchDB. This allows a unified Zeitgeist-style
chronological view across all dmedia records regardless of record type. For
example:
>>> doc = {
... '_id': 'MZZG2ZDSOQVSW2TEMVZG643F',
... 'ver': 0,
... 'type': 'dmedia/batch',
... 'time': 1234567890,
... }
Design Decision: schema extensibility
=====================================
As the goal is to make dmedia suitable for use by a wide range of applications,
there is a special attribute namespace reserved for application-specific schema.
Attributes starting with ``"x_"`` are reserved for extensibility. The dmedia
schema will never include attributes starting with ``"x_"``. Additionally, the
special ``"x"`` attribute is a dictionary that allows groups of related
attributes to be placed under a single extension namespace. For example:
>>> doc = {
... '_id': 'GS5HPKZRK7DRXOECOYYXRUTUP26H3ECY',
... 'type': 'dmedia/file',
... 'time': 1234567890,
... 'x': {
... 'pitivi': {
... 'foo': 'PiTiVi-specific foo',
... 'bar': 'PiTiVi-specific bar',
... },
... },
... 'x_baz': 'other misc attribute not in dmedia schema',
... }
desktopcouch has an ``"application_annotations"`` attribute that is used exactly
the same way as the dmedia ``"x"`` attribute. Likewise, dmedia will honor the
``"application_annotations"`` convention and never store any of its own schema
under this key.
An important consequence of this extensibility is that when modifying documents,
applications must always losslessly round-trip any attributes they don't know
about.
Design Decision: transparently distributed
==========================================
When a new job is queued, a document like this is created:
>>> doc = {
... '_id': '2QBD5MP2AADUBCBBVCTTYTLV',
... 'type': 'dmedia/job',
... 'time': 1234567000,
... 'status': 'waiting',
... 'job': {'task': 'transcode', 'id': 'QOVCOHXGV657A4GEBXTJCXJOYB6VM6NB'},
... }
When execution of the job starts, the document is updated like this:
>>> doc = {
... '_id': '2QBD5MP2AADUBCBBVCTTYTLV',
... 'type': 'dmedia/job',
... 'time': 1234567000,
... 'time_start': 1234568000,
... 'status': 'executing',
... 'job': {'task': 'transcode', 'id': 'QOVCOHXGV657A4GEBXTJCXJOYB6VM6NB'},
... }
When the job is completed, the document is updated like this:
>>> doc = {
... '_id': '2QBD5MP2AADUBCBBVCTTYTLV',
... 'type': 'dmedia/job',
... 'time': 1234567000,
... 'time_start': 1234568000,
... 'time_end': 1234569000,
... 'status': 'complete',
... 'job': {'task': 'transcode', 'id': 'QOVCOHXGV657A4GEBXTJCXJOYB6VM6NB'},
... 'result': {'id': 'AQUUT2Y2PY2DRE5NJH5K43HIHQXSMRFL'},
... }
"""
from __future__ import print_function
import os
from hashlib import sha1
from base64 import b32encode, b32decode, b64encode
import re
import time
import socket
import platform
from .constants import TYPE_ERROR, EXT_PAT
# Some private helper functions that don't directly define any schema.
#
# If this seems unnecessary or even a bit un-Pythonic (where's my duck typing?),
# keep in mind that the goal of this module is to:
#
# 1. Unambiguously define the schema
#
# 2. Provide exceedingly helpful error messages when values do not conform
# with the schema
#
# That is all.
# FIXME: These functions are a step toward making the checks more concise and
# the error messages consistent and even more helpful. However, these functions
# aren't used much yet... but all the schema checks should be ported to these
# functions eventually.
def _label(path):
"""
Create a helpful debugging label to indicate the attribute in question.
For example:
>>> _label([])
'doc'
>>> _label(['log'])
"doc['log']"
>>> _label(['log', 'considered', 2, 'src'])
"doc['log']['considered'][2]['src']"
See also `_value()`.
"""
return 'doc' + ''.join('[{!r}]'.format(key) for key in path)
def _value(doc, path):
"""
Retrieve value from *doc* by traversing *path*.
For example:
>>> doc = {'log': {'considered': [None, None, {'src': 'hello'}, None]}}
>>> _value(doc, [])
{'log': {'considered': [None, None, {'src': 'hello'}, None]}}
>>> _value(doc, ['log'])
{'considered': [None, None, {'src': 'hello'}, None]}
>>> _value(doc, ['log', 'considered', 2, 'src'])
'hello'
Or if you try to retrieve something that doesn't exist:
>>> _value(doc, ['log', 'considered', 7])
Traceback (most recent call last):
...
ValueError: doc['log']['considered'][7] does not exists
Or if a key/index is missing higher up in the path:
>>> _value(doc, ['dog', 'considered', 7])
Traceback (most recent call last):
...
ValueError: doc['dog'] does not exists
See also `_label()`.
"""
value = doc
p = []
for key in path:
p.append(key)
try:
value = value[key]
except (KeyError, IndexError):
raise ValueError(
'{} does not exists'.format(_label(p))
)
return value
def _exists(doc, path):
"""
Return ``True`` if the end of *path* exists.
For example:
>>> doc = {'foo': {'hello': 'world'}, 'bar': ['hello', 'naughty', 'nurse']}
>>> _exists(doc, ['foo', 'hello'])
True
>>> _exists(doc, ['foo', 'sup'])
False
>>> _exists(doc, ['bar', 2])
True
>>> _exists(doc, ['bar', 3])
False
Or if a key/index is missing higher up the path:
>>> _exists(doc, ['stuff', 'junk'])
Traceback (most recent call last):
...
ValueError: doc['stuff'] does not exists
See also `_check_if_exists()`.
"""
if len(path) == 0:
return True
base = _value(doc, path[:-1])
key = path[-1]
try:
value = base[key]
return True
except (KeyError, IndexError):
return False
def _check(doc, path, *checks):
"""
Run a series of *checks* on the value in *doc* addressed by *path*.
For example:
>>> doc = {'foo': [None, {'bar': 'aye'}, None]}
>>> _check(doc, ['foo', 1, 'bar'],
... _check_str,
... (_check_in, 'bee', 'sea'),
... )
...
Traceback (most recent call last):
...
ValueError: doc['foo'][1]['bar'] value 'aye' not in ('bee', 'sea')
Or if a value is missing:
>>> _check(doc, ['foo', 3],
... _can_be_none,
... )
...
Traceback (most recent call last):
...
ValueError: doc['foo'][3] does not exists
See also `_check_if_exists()`.
"""
value = _value(doc, path)
label = _label(path)
for c in checks:
if isinstance(c, tuple):
(c, args) = (c[0], c[1:])
else:
args = tuple()
if c(value, label, *args) is True:
break
def _check_if_exists(doc, path, *checks):
"""
Run *checks* only if value at *path* exists.
For example:
>>> doc = {'name': 17}
>>> _check_if_exists(doc, ['dir'], _check_str)
>>> _check_if_exists(doc, ['name'], _check_str)
Traceback (most recent call last):
...
TypeError: doc['name']: need a <type 'basestring'>; got a <type 'int'>: 17
See also `_check()` and `_exists()`.
"""
if _exists(doc, path):
_check(doc, path, *checks)
def _can_be_none(value, label):
"""
Stop execution of check if *value* is ``None``.
`_check()` will abort upon a check function returning ``True``.
For example, here a ``TypeError`` is raised:
>>> doc = {'ext': None}
>>> _check(doc, ['ext'], _check_str)
Traceback (most recent call last):
...
TypeError: doc['ext']: need a <type 'basestring'>; got a <type 'NoneType'>: None
But here it is not:
>>> _check(doc, ['ext'], _can_be_none, _check_str)
"""
if value is None:
return True
# /FIXME new helper functions
def _check_dict(value, label):
"""
Verify that *value* is a ``dict`` instance.
For example:
>>> _check_dict(['foo', 'bar'], 'doc')
Traceback (most recent call last):
...
TypeError: doc: need a <type 'dict'>; got a <type 'list'>: ['foo', 'bar']
"""
if not isinstance(value, dict):
raise TypeError(TYPE_ERROR % (label, dict, type(value), value))
def _check_str(value, label):
"""
Verify that *value* is a ``basestring`` instance.
Or a ``str`` instance one dmedia is running under Python3.
For example:
>>> _check_str(17, 'import_id')
Traceback (most recent call last):
...
TypeError: import_id: need a <type 'basestring'>; got a <type 'int'>: 17
"""
if not isinstance(value, basestring):
raise TypeError(TYPE_ERROR % (label, basestring, type(value), value))
def _check_int(value, label):
"""
Verify that *value* is an ``int`` instance.
For example:
>>> _check_int(18.0, 'bytes')
Traceback (most recent call last):
...
TypeError: bytes: need a <type 'int'>; got a <type 'float'>: 18.0
"""
if not isinstance(value, int):
raise TypeError(TYPE_ERROR % (label, int, type(value), value))
def _check_int_float(value, label):
"""
Verify that *value* is an ``int`` or ``float`` instance.
For example:
>>> _check_int_float('18', 'time')
Traceback (most recent call last):
...
TypeError: time: need a (<type 'int'>, <type 'float'>); got a <type 'str'>: '18'
"""
if not isinstance(value, (int, float)):
raise TypeError(TYPE_ERROR % (label, (int, float), type(value), value))
def _check_at_least(value, label, minvalue=0):
"""
Verify that *value* is greater than or equal to *minvalue*.
For example:
>>> _check_at_least(0, 'bytes', 1)
Traceback (most recent call last):
...
ValueError: bytes must be >= 1; got 0
"""
if value < minvalue:
raise ValueError(
'%s must be >= %r; got %r' % (label, minvalue, value)
)
def _check_lowercase(value, label):
"""
Verify that *value* is lowercase.
For example:
>>> _check_lowercase('MOV', 'ext')
Traceback (most recent call last):
...
ValueError: ext must be lowercase; got 'MOV'
"""
if not value.islower():
raise ValueError(
"%s must be lowercase; got %r" % (label, value)
)
def _check_identifier(value, label):
"""
Verify that *value* is a lowercase Python identifier not starting with "_"
For example:
>>> _check_identifier('hello_world', 'msg')
>>> _check_identifier('hello-world', 'msg')
Traceback (most recent call last):
...
ValueError: msg: 'hello-world' does not match '^[a-z][_a-z0-9]*$'
"""
pat = '^[a-z][_a-z0-9]*$'
if not re.match(pat, value):
raise ValueError(
'%s: %r does not match %r' % (label, value, pat)
)
def _check_nonempty(value, label):
"""
Verify that *value* is not empty (ie len() > 0).
For example:
>>> _check_nonempty({}, 'stored')
Traceback (most recent call last):
...
ValueError: stored cannot be empty; got {}
"""
if len(value) == 0:
raise ValueError('%s cannot be empty; got %r' % (label, value))
def _check_required(d, required, label='doc'):
"""
Check that dictionary *d* contains all the keys in *required*.
For example:
>>> _check_required(dict(foo=1, bar=2, baz=3), ['foo', 'bar'], 'var_name')
>>> _check_required(dict(foo=1, car=2, baz=3), ['foo', 'bar'], 'var_name')
Traceback (most recent call last):
...
ValueError: var_name missing keys: ['bar']
"""
_check_dict(d, label)
required = frozenset(required)
if not required.issubset(d):
missing = sorted(required - set(d))
raise ValueError(
'%s missing keys: %r' % (label, missing)
)
def _check_in(value, label, *possible):
"""
Check that *value* is one of *possible*.
For example:
>>> _check_in('foo', "doc['media']", 'video', 'audio', 'image')
Traceback (most recent call last):
...
ValueError: doc['media'] value 'foo' not in ('video', 'audio', 'image')
"""
if value not in possible:
raise ValueError(
'{} value {!r} not in {!r}'.format(label, value, possible)
)
# The schema defining functions:
def check_base32(value, label='_id'):
"""
Verify that *value* is a valid dmedia document ID.
Document IDs must:
1. be ``str`` or ``unicode`` instances
2. be valid base32 encoding
3. decode to data that is a multiple of 5-bytes (40-bits ) in length
For example, a conforming value:
>>> check_base32('MZZG2ZDSOQVSW2TEMVZG643F')
And an invalid value:
>>> check_base32('MFQWCYLBMFQWCYI=')
Traceback (most recent call last):
...
ValueError: len(b32decode(_id)) not multiple of 5: 'MFQWCYLBMFQWCYI='
"""
_check_str(value, label)
try:
decoded = b32decode(value)
except TypeError as e:
raise ValueError('%s: invalid base32: %s; got %r' % (label, e, value))
if len(decoded) % 5 != 0:
raise ValueError(
'len(b32decode(%s)) not multiple of 5: %r' % (label, value)
)
def check_type(value, label='type'):
"""
Verify that *doc* has a valid dmedia record type.
Record types must:
1. be ``str`` or ``unicode`` instances
2. be lowercase
3. start with 'dmedia/'
4. be of the form 'dmedia/foo', where *foo* is a valid Python identifier
For example, a conforming value:
>>> check_type('dmedia/file')
And an invalid value:
>>> check_type('dmedia/foo/bar')
Traceback (most recent call last):
...
ValueError: type must contain only one '/'; got 'dmedia/foo/bar'
"""
_check_str(value, label)
_check_lowercase(value, label)
if not value.startswith('dmedia/'):
raise ValueError(
"%s must start with 'dmedia/'; got %r" % (label, value)
)
parts = value.split('/')
if len(parts) != 2:
raise ValueError(
"%s must contain only one '/'; got %r" % (label, value)
)
def check_time(value, label='time'):
"""
Verify that *value* is a Unix timestamp.
Timestamps must:
1. be ``int`` or ``float`` instances
2. be non-negative (must be >= 0)
For example, a conforming value:
>>> check_time(1234567890, label='time_end')
And an invalid value:
>>> check_time(-1234567890, label='time_end')
Traceback (most recent call last):
...
ValueError: time_end must be >= 0; got -1234567890
"""
_check_int_float(value, label)
_check_at_least(value, label, 0)
def check_dmedia(doc):
"""
Verify that *doc* is a valid dmedia document.
This verifies that *doc* has the common schema requirements that all dmedia
documents should have. The *doc* must:
1. have '_id' that passes `check_base32()`
2. have a 'ver' equal to ``0``
3. have 'type' that passes `check_type()`
4. have 'time' that passes `check_time()`
For example, a conforming value:
>>> doc = {
... '_id': 'NZXXMYLDOV2F6ZTUO5PWM5DX',
... 'ver': 0,
... 'type': 'dmedia/file',
... 'time': 1234567890,
... }
...
>>> check_dmedia(doc)
And an invalid value:
>>> doc = {
... '_id': 'NZXXMYLDOV2F6ZTUO5PWM5DX',
... 'ver': 0,
... 'kind': 'dmedia/file',
... 'timestamp': 1234567890,
... }
...
>>> check_dmedia(doc)
Traceback (most recent call last):
...
ValueError: doc missing keys: ['time', 'type']
"""
_check_required(doc, ['_id', 'ver', 'type', 'time'])
check_base32(doc['_id'])
_check_int(doc['ver'], 'ver')
if doc['ver'] != 0:
raise ValueError(
"doc['ver'] must be 0; got {!r}".format(doc['ver'])
)
check_type(doc['type'])
check_time(doc['time'])
def check_stored(stored, label='stored'):
"""
Verify that *stored* is valid for a 'dmedia/file' record.
To be valid, *stored* must:
1. be a non-empty ``dict``
2. have keys that are document IDs according to `check_base32()`
3. have values that are themselves ``dict`` instances
4. values must have 'copies' that is an ``int`` >= 0
5. values must have 'time' that conforms with `check_time()`
For example, a conforming value:
>>> stored = {
... 'MZZG2ZDSOQVSW2TEMVZG643F': {
... 'copies': 2,
... 'time': 1234567890,
... },
... }
...
>>> check_stored(stored)
And an invalid value:
>>> stored = {
... 'MZZG2ZDSOQVSW2TEMVZG643F': {
... 'number': 2,
... 'time': 1234567890,
... },
... }
...
>>> check_stored(stored)
Traceback (most recent call last):
...
ValueError: stored['MZZG2ZDSOQVSW2TEMVZG643F'] missing keys: ['copies']
Also see `check_dmedia_file()`.
"""
_check_dict(stored, label)
_check_nonempty(stored, label)
for (key, value) in stored.iteritems():
check_base32(key, '<key in %s>' % label)
l2 = '%s[%r]' % (label, key) # eg "stored['OVRHK3TUOUQCWIDMNFXGC4TP']"
_check_required(value, ['copies', 'time'], l2)
# Check 'copies':
copies = value['copies']
l3 = l2 + "['copies']"
_check_int(copies, l3)
_check_at_least(copies, l3, 0)
# Check 'time':
check_time(value['time'], l2 + "['time']")
def check_ext(value, label='ext'):
"""
Verify that *value* is a file extension suitable for 'dmedia/file' records.
The extension *value* can be ``None``, or otherwise *value* must:
1. be a non-empty ``str`` or ``unicode`` instance
2. be lowercase
3. neither start nor end with a period
4. contain only letters, numbers, and at most on internal period
For example, some conforming values:
>>> check_ext(None)
>>> check_ext('mov')
>>> check_ext('tar.gz')
And an invalid value:
>>> check_ext('.mov')
Traceback (most recent call last):
...
ValueError: ext cannot start with a period; got '.mov'
"""
if value is None:
return
_check_str(value, label)
_check_nonempty(value, label)
_check_lowercase(value, label)
if value.startswith('.'):
raise ValueError(
'%s cannot start with a period; got %r' % (label, value)
)
if value.endswith('.'):
raise ValueError(
'%s cannot end with a period; got %r' % (label, value)
)
if not re.match(EXT_PAT, value):
raise ValueError(
'%s: %r does not match %r' % (label, value, EXT_PAT)
)
def check_origin(value, label='origin', strict=False):
"""
Verify that *value* is an 'origin' suitable for 'dmedia/file' records.
To be a valid origin, *value* must:
1. be a non-empty ``str`` or ``unicode`` instance
2. be lowercase
3. be a valid Python identifier not starting with "_"
4. if called with strict=True, must be either 'user', 'download',
'paid', 'proxy', 'cache', or 'render'
For example, some conforming values:
>>> check_origin('hello_world2')
>>> check_origin('user')
And an invalid value:
>>> check_origin('User')
Traceback (most recent call last):
...
ValueError: origin must be lowercase; got 'User'
"""
_check_str(value, label)
_check_nonempty(value, label)
_check_lowercase(value, label)
_check_identifier(value, label)
if not strict:
return
allowed = ['user', 'download', 'paid', 'proxy', 'cache', 'render']
if value not in allowed:
raise ValueError('%s: %r not in %r' % (label, value, allowed))
def check_dmedia_file(doc):
"""
Verify that *doc* is a valid 'dmedia/file' record type.
To be a valid 'dmedia/file' record, *doc* must:
1. conform with `check_dmedia()`
2. have 'type' equal to 'dmedia/file'
3. have 'bytes' that is an ``int`` >= 1
4. have 'ext' that conforms with `check_ext()`
5. have 'origin' that conforms with `check_origin()` with strict=True
6. have 'stored' that is a ``dict`` conforming with `check_stored()`
For example, a conforming value:
>>> doc = {
... '_id': 'ZR765XWSF6S7JQHLUI4GCG5BHGPE252O',
... 'ver': 0,
... 'type': 'dmedia/file',
... 'time': 1234567890,
... 'bytes': 20202333,
... 'ext': 'mov',
... 'origin': 'user',
... 'stored': {
... 'MZZG2ZDSOQVSW2TEMVZG643F': {
... 'copies': 2,
... 'time': 1234567890,
... },
... },
... }
...
>>> check_dmedia_file(doc)
And an invalid value:
>>> doc = {
... '_id': 'ZR765XWSF6S7JQHLUI4GCG5BHGPE252O',
... 'ver': 0,
... 'type': 'dmedia/file',
... 'time': 1234567890,
... 'bytes': 20202333,
... 'ext': 'mov',
... 'origin': 'user',
... 'stored': {
... 'MZZG2ZDSOQVSW2TEMVZG643F': {
... 'number': 2, # Changed!
... 'time': 1234567890,
... },
... },
... }
...
>>> check_dmedia_file(doc)
Traceback (most recent call last):
...
ValueError: stored['MZZG2ZDSOQVSW2TEMVZG643F'] missing keys: ['copies']
"""
check_dmedia(doc)
_check_required(doc, ['bytes', 'ext', 'origin', 'stored'])
# Check type:
if doc['type'] != 'dmedia/file':
raise ValueError(
"doc['type'] must be 'dmedia/file'; got %(type)r" % doc
)
# Check 'bytes':
b = doc['bytes']
_check_int(b, 'bytes')
_check_at_least(b, 'bytes', 1)
# Check 'ext':
check_ext(doc['ext'])
# Check 'origin':
check_origin(doc['origin'], strict=True)
# Check 'stored'
check_stored(doc['stored'])
check_dmedia_file_optional(doc)
def check_dmedia_file_optional(doc):
"""
Check the optional attributes in a 'dmedia/file' document.
"""
_check_dict(doc, 'doc')
# 'mime' like 'video/quicktime'
_check_if_exists(doc, ['mime'],
_can_be_none,
_check_str,
)
# 'media' like 'video'
_check_if_exists(doc, ['media'],
_can_be_none,
_check_str,
(_check_in, 'video', 'audio', 'image'),
)
# 'mtime' like 1234567890
_check_if_exists(doc, ['mtime'],
check_time
)
# 'atime' like 1234567890
_check_if_exists(doc, ['atime'],
check_time
)
# name like 'MVI_5899.MOV'
_check_if_exists(doc, ['name'],
_check_str,
)
# dir like 'DCIM/100EOS5D2'
_check_if_exists(doc, ['dir'],
_check_str,
)
# 'meta' like {'iso': 800}
_check_if_exists(doc, ['meta'],
_check_dict
)
# 'user' like {'title': 'cool sunset'}
_check_if_exists(doc, ['user'],
_check_dict
)
# 'tags' like {'burp': {'start': 6, 'end': 73}}
_check_if_exists(doc, ['tags'],
_check_dict
)
def check_dmedia_store(doc):
"""
Verify that *doc* is a valid 'dmedia/store' type document.
To be a valid 'dmedia/store' record, *doc* must:
1. conform with `check_dmedia()`
2. have 'plugin' that equal to 'filestore', 'removable_filestore',
'ubuntuone', or 's3'
3. have 'copies' that is an ``int`` >= 1
For example, a conforming value:
>>> doc = {
... '_id': 'NZXXMYLDOV2F6ZTUO5PWM5DX',
... 'ver': 0,
... 'type': 'dmedia/file',
... 'time': 1234567890,
... 'plugin': 'filestore',
... 'copies': 2,
... }
...
>>> check_dmedia_store(doc)
And an invalid value:
>>> doc = {
... '_id': 'NZXXMYLDOV2F6ZTUO5PWM5DX',
... 'ver': 0,
... 'type': 'dmedia/file',
... 'time': 1234567890,
... 'dispatch': 'filestore',
... 'copies': 2,
... }
...
>>> check_dmedia_store(doc)
Traceback (most recent call last):
...
ValueError: doc missing keys: ['plugin']
"""
check_dmedia(doc)
_check_required(doc, ['plugin', 'copies'])
# Test plugin
key = 'plugin'
p = doc[key]
_check_str(p, key)
plugins = ['filestore', 'removable_filestore', 'ubuntuone', 's3']
if p not in plugins:
raise ValueError(
'%s %r not in %r' % (key, p, plugins)
)
# Test copies
key = 'copies'
dc = doc[key]
_check_int(dc, key)
_check_at_least(dc, key, 1)
def random_id(random=None):
"""
Returns a 120-bit base32-encoded random ID.
The ID will be 24-characters long, URL and filesystem safe. For example:
>>> random_id() #doctest: +SKIP
'OVRHK3TUOUQCWIDMNFXGC4TP'
Optionally you can provide the 15-byte random seed yourself:
>>> random_id(random='abcdefghijklmno'.encode('utf-8'))
'MFRGGZDFMZTWQ2LKNNWG23TP'
:param random: optionally provide 15-byte random seed; when not provided,
seed is created by calling ``os.urandom(15)``
"""
random = (os.urandom(15) if random is None else random)
assert len(random) % 5 == 0
return b32encode(random)
# FIXME: There is current a recursize import issue with filestore, but FileStore
# shouldn't deal with the store.json file anyway, should not import
# `schema.create_store()`
def tophash_personalization(file_size):
return ' '.join(['dmedia/tophash', str(file_size)]).encode('utf-8')
def tophash(file_size, leaves):
"""
Initialize hash for a file that is *file_size* bytes.
"""
h = sha1(tophash_personalization(file_size))
h.update(leaves)
return b32encode(h.digest())
def create_file(file_size, leaves, store, copies=0, ext=None, origin='user'):
"""
Create a minimal 'dmedia/file' document.
:param file_size: an ``int``, the file size in bytes, eg ``20202333``
:param leaves: a ``list`` containing the content hash of each leaf
:param store: the ID of the store where this file is initially stored, eg
``'Y4J3WQCMKV5GHATOCZZBHF4Y'``
:param copies: an ``int`` to represent the durability of the file on this
store; default is ``0``
:param ext: the file extension, eg ``'mov'``; default is ``None``
:param origin: the file's origin (for durability/reclamation purposes);
default is ``'user'``
"""
ts = time.time()
packed = b''.join(leaves)
return {
'_id': tophash(file_size, packed),
'_attachments': {
'leaves': {
'data': b64encode(packed),
'content_type': 'application/octet-stream',
}
},
'ver': 0,
'type': 'dmedia/file',
'time': ts,
'bytes': file_size,
'ext': ext,
'origin': origin,
'stored': {
store: {
'copies': copies,
'time': ts,
}
}
}
def create_machine():
"""
Create a 'dmedia/machine' document.
"""
return {
'_id': random_id(),
'ver': 0,
'type': 'dmedia/machine',
'time': time.time(),
'hostname': socket.gethostname(),
'distribution': list(platform.linux_distribution()),
}
def create_store(parentdir, machine_id, copies=1):
"""
Create a 'dmedia/store' document.
"""
return {
'_id': random_id(),
'ver': 0,
'type': 'dmedia/store',
'time': time.time(),
'plugin': 'filestore',
'copies': copies,
'path': parentdir,
'machine_id': machine_id,
}
def create_batch(machine_id=None):
"""
Create initial 'dmedia/batch' accounting document.
"""
return {
'_id': random_id(),
'ver': 0,
'type': 'dmedia/batch',
'time': time.time(),
'machine_id': machine_id,
'imports': [],
'errors': [],
'stats': {
'considered': {'count': 0, 'bytes': 0},
'imported': {'count': 0, 'bytes': 0},
'skipped': {'count': 0, 'bytes': 0},
'empty': {'count': 0, 'bytes': 0},
'error': {'count': 0, 'bytes': 0},
}
}
def create_import(base, batch_id=None, machine_id=None):
"""
Create initial 'dmedia/import' accounting document.
"""
return {
'_id': random_id(),
'ver': 0,
'type': 'dmedia/import',
'time': time.time(),
'batch_id': batch_id,
'machine_id': machine_id,
'base': base,
'log': {
'imported': [],
'skipped': [],
'empty': [],
'error': [],
},
'stats': {
'imported': {'count': 0, 'bytes': 0},
'skipped': {'count': 0, 'bytes': 0},
'empty': {'count': 0, 'bytes': 0},
'error': {'count': 0, 'bytes': 0},
}
}
|