DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (c68fe15a81fc)

VCS Links

Line Code
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 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792
#!/usr/bin/env python

# tooltool is a lookaside cache implemented in Python
# tooltool is a lookaside cache implemented in Python
# Copyright (C) 2011 John H. Ford <john@johnford.info>
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation version 2
# as published by the Free Software Foundation version 2
#
# This program 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 General Public License for more details.
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
# 02110-1301, USA.
# 02110-1301, USA.

# A manifest file specifies files in that directory that are stored
# elsewhere. This file should only list files in the same directory
# in which the manifest file resides and it should be called
# 'manifest.tt'

from __future__ import print_function
from __future__ import print_function
from __future__ import absolute_import

import base64
import calendar
import hashlib
import hashlib
import hmac
import json
import logging
import math
import optparse
import optparse
import os
import pprint
import re
import shutil
import sys
import sys
import tarfile
import tempfile
import threading
import time
import zipfile
from contextlib import contextmanager, closing
from functools import wraps
from functools import wraps

from io import open
from io import BytesIO
from random import random
from subprocess import PIPE
from subprocess import PIPE
from subprocess import Popen

__version__ = '1'

# Allowed request header characters:
# Allowed request header characters:
# !#$%&'()*+,-./:;<=>?@[]^_`{|}~ and space, a-z, A-Z, 0-9, \, "
REQUEST_HEADER_ATTRIBUTE_CHARS = re.compile(
    r"^[ a-zA-Z0-9_\!#\$%&'\(\)\*\+,\-\./\:;<\=>\?@\[\]\^`\{\|\}~]*$")
DEFAULT_MANIFEST_NAME = 'manifest.tt'
TOOLTOOL_PACKAGE_SUFFIX = '.TOOLTOOL-PACKAGE'
TOOLTOOL_PACKAGE_SUFFIX = '.TOOLTOOL-PACKAGE'
HAWK_VER = 1
PY3 = sys.version_info[0] == 3

if PY3:
    six_binary_type = bytes
    six_binary_type = bytes
    unicode = str  # Silence `pyflakes` from reporting `undefined name 'unicode'` in Python 3.
    import urllib.request as urllib2
    from http.client import HTTPSConnection, HTTPConnection
    from urllib.parse import urlparse, urljoin
    from urllib.request import Request
    from urllib.error import HTTPError, URLError
else:
else:
    six_binary_type = str
    import urllib2
    from httplib import HTTPSConnection, HTTPConnection
    from urllib2 import Request, HTTPError, URLError
    from urllib2 import Request, HTTPError, URLError
    from urlparse import urlparse, urljoin


log = logging.getLogger(__name__)



# Vendored code from `redo` module
def retrier(attempts=5, sleeptime=10, max_sleeptime=300, sleepscale=1.5, jitter=1):
    """
    This function originates from redo 2.0.3 https://github.com/mozilla-releng/redo
    This function originates from redo 2.0.3 https://github.com/mozilla-releng/redo
    A generator function that sleeps between retries, handles exponential
    backoff and jitter. The action you are retrying is meant to run after
    retrier yields.
    """
    jitter = jitter or 0  # py35 barfs on the next line if jitter is None
    jitter = jitter or 0  # py35 barfs on the next line if jitter is None
    if jitter > sleeptime:
        # To prevent negative sleep times
        raise Exception("jitter ({}) must be less than sleep time ({})".format(jitter, sleeptime))

    sleeptime_real = sleeptime
    sleeptime_real = sleeptime
    for _ in range(attempts):
        log.debug("attempt %i/%i", _ + 1, attempts)

        yield sleeptime_real


        if jitter:
            sleeptime_real = sleeptime + random.uniform(-jitter, jitter)
            # our jitter should scale along with the sleeptime
            jitter = jitter * sleepscale
        else:
        else:
            sleeptime_real = sleeptime

        sleeptime *= sleepscale

        if sleeptime_real > max_sleeptime:
            sleeptime_real = max_sleeptime


        # Don't need to sleep the last time
        if _ < attempts - 1:
            log.debug("sleeping for %.2fs (attempt %i/%i)", sleeptime_real, _ + 1, attempts)
            time.sleep(sleeptime_real)



def retry(
    action,
    attempts=5,
    sleeptime=60,
    sleeptime=60,
    max_sleeptime=5 * 60,
    sleepscale=1.5,
    jitter=1,
    retry_exceptions=(Exception,),
    cleanup=None,
    cleanup=None,
    args=(),
    kwargs={},
    log_args=True,
):
    """
    """
    This function originates from redo 2.0.3 https://github.com/mozilla-releng/redo
    Calls an action function until it succeeds, or we give up.
    """
    assert callable(action)
    assert not cleanup or callable(cleanup)
    assert not cleanup or callable(cleanup)

    action_name = getattr(action, "__name__", action)
    if log_args and (args or kwargs):
        log_attempt_args = ("retry: calling %s with args: %s," " kwargs: %s, attempt #%d",
                            action_name, args, kwargs)
                            action_name, args, kwargs)
    else:
        log_attempt_args = ("retry: calling %s, attempt #%d", action_name)

    if max_sleeptime < sleeptime:
        log.debug("max_sleeptime %d less than sleeptime %d", max_sleeptime, sleeptime)
        log.debug("max_sleeptime %d less than sleeptime %d", max_sleeptime, sleeptime)

    n = 1
    for _ in retrier(
            attempts=attempts,
            sleeptime=sleeptime,
            max_sleeptime=max_sleeptime,
            sleepscale=sleepscale,
            sleepscale=sleepscale,
            jitter=jitter):
        try:
            logfn = log.info if n != 1 else log.debug
            logfn_args = log_attempt_args + (n,)
            logfn(*logfn_args)
            logfn(*logfn_args)
            return action(*args, **kwargs)
        except retry_exceptions:
            log.debug("retry: Caught exception: ", exc_info=True)
            if cleanup:
                cleanup()
                cleanup()
            if n == attempts:
                log.info("retry: Giving up on %s", action_name)
                raise
            continue
        finally:
            n += 1



def retriable(*retry_args, **retry_kwargs):
    """
    This function originates from redo 2.0.3 https://github.com/mozilla-releng/redo
    This function originates from redo 2.0.3 https://github.com/mozilla-releng/redo
    A decorator factory for retry(). Wrap your function in @retriable(...) to
    give it retry powers!
    """

    def _retriable_factory(func):
    def _retriable_factory(func):
        @wraps(func)
        def _retriable_wrapper(*args, **kwargs):
            return retry(func, args=args, kwargs=kwargs, *retry_args, **retry_kwargs)

        return _retriable_wrapper
        return _retriable_wrapper

    return _retriable_factory

# end of vendored code from redo module



def request_has_data(req):
    if PY3:
        return req.data is not None
    return req.has_data()


def get_hexdigest(val):
def get_hexdigest(val):
    return hashlib.sha512(val).hexdigest()


class FileRecordJSONEncoderException(Exception):
    pass
    pass


class InvalidManifest(Exception):
    pass



class ExceptionWithFilename(Exception):

    def __init__(self, filename):
        Exception.__init__(self)
        Exception.__init__(self)
        self.filename = filename


class BadFilenameException(ExceptionWithFilename):
    pass
    pass


class DigestMismatchException(ExceptionWithFilename):
    pass



class MissingFileException(ExceptionWithFilename):
    pass


class InvalidCredentials(Exception):
class InvalidCredentials(Exception):
    pass


class BadHeaderValue(Exception):
    pass
    pass


def parse_url(url):
    url_parts = urlparse(url)
    url_dict = {
    url_dict = {
        'scheme': url_parts.scheme,
        'hostname': url_parts.hostname,
        'port': url_parts.port,
        'path': url_parts.path,
        'resource': url_parts.path,
        'resource': url_parts.path,
        'query': url_parts.query,
    }
    if len(url_dict['query']) > 0:
        url_dict['resource'] = '%s?%s' % (url_dict['resource'],  # pragma: no cover
                                          url_dict['query'])
                                          url_dict['query'])

    if url_parts.port is None:
        if url_parts.scheme == 'http':
            url_dict['port'] = 80
        elif url_parts.scheme == 'https':  # pragma: no cover
        elif url_parts.scheme == 'https':  # pragma: no cover
            url_dict['port'] = 443
    return url_dict


def utc_now(offset_in_seconds=0.0):
def utc_now(offset_in_seconds=0.0):
    return int(math.floor(calendar.timegm(time.gmtime()) + float(offset_in_seconds)))


def random_string(length):
    return base64.urlsafe_b64encode(os.urandom(length))[:length]
    return base64.urlsafe_b64encode(os.urandom(length))[:length]


def prepare_header_val(val):
    if isinstance(val, six_binary_type):
        val = val.decode('utf-8')


    if not REQUEST_HEADER_ATTRIBUTE_CHARS.match(val):
        raise BadHeaderValue(  # pragma: no cover
            'header value value={val} contained an illegal character'.format(val=repr(val)))

    return val
    return val


def parse_content_type(content_type):  # pragma: no cover
    if content_type:
        return content_type.split(';')[0].strip().lower()
        return content_type.split(';')[0].strip().lower()
    else:
        return ''


def calculate_payload_hash(algorithm, payload, content_type):  # pragma: no cover
def calculate_payload_hash(algorithm, payload, content_type):  # pragma: no cover
    parts = [
        part if isinstance(part, six_binary_type) else part.encode('utf8')
        for part in ['hawk.' + str(HAWK_VER) + '.payload\n',
                     parse_content_type(content_type) + '\n',
                     payload or '',
                     '\n',
                     ]
                     ]
    ]

    p_hash = hashlib.new(algorithm)
    for p in parts:
        p_hash.update(p)
        p_hash.update(p)

    log.debug('calculating payload hash from:\n{parts}'.format(parts=pprint.pformat(parts)))

    return base64.b64encode(p_hash.digest())



def validate_taskcluster_credentials(credentials):
    if not hasattr(credentials, '__getitem__'):
        raise InvalidCredentials('credentials must be a dict-like object')  # pragma: no cover
    try:
    try:
        credentials['clientId']
        credentials['accessToken']
    except KeyError:  # pragma: no cover
        etype, val, tb = sys.exc_info()
        raise InvalidCredentials('{etype}: {val}'.format(etype=etype, val=val))


def normalize_header_attr(val):
def normalize_header_attr(val):
    if isinstance(val, six_binary_type):
        return val.decode('utf-8')
    return val  # pragma: no cover



def normalize_string(mac_type,
                     timestamp,
                     nonce,
                     method,
                     name,
                     name,
                     host,
                     port,
                     content_hash,
                     ):
    return '\n'.join([
    return '\n'.join([
        normalize_header_attr(header)
        # The blank lines are important. They follow what the Node Hawk lib does.
        for header in ['hawk.' + str(HAWK_VER) + '.' + mac_type,
                       timestamp,
                       nonce,
                       nonce,
                       method or '',
                       name or '',
                       host,
                       port,
                       content_hash or '',
                       content_hash or '',
                       '',  # for ext which is empty in this case
                       '',  # Add trailing new line.
                       ]
    ])



def calculate_mac(mac_type,
                  access_token,
                  algorithm,
                  timestamp,
                  timestamp,
                  nonce,
                  method,
                  name,
                  host,
                  port,
                  port,
                  content_hash,
                  ):
    normalized = normalize_string(mac_type,
                                  timestamp,
                                  nonce,
                                  method,
                                  name,
                                  name,
                                  host,
                                  port,
                                  content_hash)
    log.debug(u'normalized resource for mac calc: {norm}'.format(norm=normalized))
    digestmod = getattr(hashlib, algorithm)
    digestmod = getattr(hashlib, algorithm)

    if not isinstance(normalized, six_binary_type):
        normalized = normalized.encode('utf8')


    if not isinstance(access_token, six_binary_type):
        access_token = access_token.encode('ascii')

    result = hmac.new(access_token, normalized, digestmod)
    return base64.b64encode(result.digest())
    return base64.b64encode(result.digest())


def make_taskcluster_header(credentials, req):
    validate_taskcluster_credentials(credentials)


    url = req.get_full_url()
    method = req.get_method()
    algorithm = 'sha256'
    algorithm = 'sha256'
    timestamp = str(utc_now())
    timestamp = str(utc_now())
    nonce = random_string(6)
    url_parts = parse_url(url)


    content_hash = None
    if request_has_data(req):
        if PY3:
            data = req.data
        else:
        else:
            data = req.get_data()
        content_hash = calculate_payload_hash(  # pragma: no cover
        content_hash = calculate_payload_hash(  # pragma: no cover
            algorithm,
            data,
            # maybe we should detect this from req.headers but we anyway expect json
            content_type='application/json',
        )
        )

    mac = calculate_mac('header',
                        credentials['accessToken'],
                        algorithm,
                        timestamp,
                        timestamp,
                        nonce,
                        method,
                        url_parts['resource'],
                        url_parts['hostname'],
                        str(url_parts['port']),
                        content_hash,
                        )
                        )

    header = u'Hawk mac="{}"'.format(prepare_header_val(mac))

    if content_hash:  # pragma: no cover
        header = u'{}, hash="{}"'.format(header, prepare_header_val(content_hash))

    header = u'{header}, id="{id}", ts="{ts}", nonce="{nonce}"'.format(
        header=header,
        id=prepare_header_val(credentials['clientId']),
        id=prepare_header_val(credentials['clientId']),
        ts=prepare_header_val(timestamp),
        nonce=prepare_header_val(nonce),
    )

    log.debug('Hawk header for URL={} method={}: {}'.format(url, method, header))
    log.debug('Hawk header for URL={} method={}: {}'.format(url, method, header))

    return header



class FileRecord(object):

    def __init__(self, filename, size, digest, algorithm, unpack=False,
                 version=None, visibility=None):
        object.__init__(self)
        object.__init__(self)
        if '/' in filename or '\\' in filename:
            log.error(
                "The filename provided contains path information and is, therefore, invalid.")
            raise BadFilenameException(filename=filename)
        self.filename = filename
        self.size = size
        self.digest = digest
        self.algorithm = algorithm
        self.algorithm = algorithm
        self.unpack = unpack
        self.version = version
        self.visibility = visibility

    def __eq__(self, other):
    def __eq__(self, other):
        if self is other:
            return True
        if self.filename == other.filename and \
           self.size == other.size and \
           self.digest == other.digest and \
           self.digest == other.digest and \
           self.algorithm == other.algorithm and \
           self.version == other.version and \
           self.visibility == other.visibility:
            return True
        else:
            return False


    def __ne__(self, other):
        return not self.__eq__(other)

    def __str__(self):
        return repr(self)
        return repr(self)

    def __repr__(self):
        return "%s.%s(filename='%s', size=%s, digest='%s', algorithm='%s', visibility=%r)" % (
            __name__, self.__class__.__name__, self.filename, self.size,
            self.digest, self.algorithm, self.visibility)
            self.digest, self.algorithm, self.visibility)

    def present(self):
        # Doesn't check validity
        return os.path.exists(self.filename)


    def validate_size(self):
        if self.present():
            return self.size == os.path.getsize(self.filename)
        else:
            log.debug(
            log.debug(
                "trying to validate size on a missing file, %s", self.filename)
            raise MissingFileException(filename=self.filename)

    def validate_digest(self):
        if self.present():
            with open(self.filename, 'rb') as f:
                return self.digest == digest_file(f, self.algorithm)
                return self.digest == digest_file(f, self.algorithm)
        else:
        else:
            log.debug(
                "trying to validate digest on a missing file, %s', self.filename")
            raise MissingFileException(filename=self.filename)

    def validate(self):
    def validate(self):
        if self.size is None or self.validate_size():
            if self.validate_digest():
                return True
        return False


    def describe(self):
        if self.present() and self.validate():
            return "'%s' is present and valid" % self.filename
            return "'%s' is present and valid" % self.filename
        elif self.present():
        elif self.present():
            return "'%s' is present and invalid" % self.filename
        else:
            return "'%s' is absent" % self.filename
            return "'%s' is absent" % self.filename


def create_file_record(filename, algorithm):
    fo = open(filename, 'rb')
    stored_filename = os.path.split(filename)[1]
    fr = FileRecord(stored_filename, os.path.getsize(
        filename), digest_file(fo, algorithm), algorithm)
    fo.close()
    return fr
    return fr


class FileRecordJSONEncoder(json.JSONEncoder):

    def encode_file_record(self, obj):
    def encode_file_record(self, obj):
        if not issubclass(type(obj), FileRecord):
            err = "FileRecordJSONEncoder is only for FileRecord and lists of FileRecords, " \
                  "not %s" % obj.__class__.__name__
                  "not %s" % obj.__class__.__name__
            log.warn(err)
            log.warn(err)
            raise FileRecordJSONEncoderException(err)
        else:
            rv = {
            rv = {
                'filename': obj.filename,
                'size': obj.size,
                'algorithm': obj.algorithm,
                'digest': obj.digest,
            }
            }
            if obj.unpack:
                rv['unpack'] = True
            if obj.version:
            if obj.version:
                rv['version'] = obj.version
            if obj.visibility is not None:
                rv['visibility'] = obj.visibility
            return rv


    def default(self, f):
        if issubclass(type(f), list):
            record_list = []
            for i in f:
                record_list.append(self.encode_file_record(i))
                record_list.append(self.encode_file_record(i))
            return record_list
        else:
            return self.encode_file_record(f)


class FileRecordJSONDecoder(json.JSONDecoder):


    """I help the json module materialize a FileRecord from
    a JSON file.  I understand FileRecords and lists of
    FileRecords.  I ignore things that I don't expect for now"""
    # TODO: make this more explicit in what it's looking for
    # and error out on unexpected things
    # and error out on unexpected things

    def process_file_records(self, obj):
        if isinstance(obj, list):
            record_list = []
            for i in obj:
            for i in obj:
                record = self.process_file_records(i)
                if issubclass(type(record), FileRecord):
                    record_list.append(record)
            return record_list
        required_fields = [
        required_fields = [
            'filename',
            'size',
            'algorithm',
            'digest',
        ]
        ]
        if isinstance(obj, dict):
            missing = False
            for req in required_fields:
                if req not in obj:
                    missing = True
                    missing = True
                    break

            if not missing:
                unpack = obj.get('unpack', False)
                version = obj.get('version', None)
                version = obj.get('version', None)
                visibility = obj.get('visibility', None)
                rv = FileRecord(
                    obj['filename'], obj['size'], obj['digest'], obj['algorithm'],
                    unpack, version, visibility)
                    unpack, version, visibility)
                log.debug("materialized %s" % rv)
                return rv
        return obj

    def decode(self, s):
    def decode(self, s):
        decoded = json.JSONDecoder.decode(self, s)
        rv = self.process_file_records(decoded)
        return rv



class Manifest(object):

    valid_formats = ('json',)

    def __init__(self, file_records=None):
    def __init__(self, file_records=None):
        self.file_records = file_records or []

    def __eq__(self, other):
        if self is other:
            return True
            return True
        if len(self.file_records) != len(other.file_records):
            log.debug('Manifests differ in number of files')
            return False
            return False
        # sort the file records by filename before comparing
        mine = sorted((fr.filename, fr) for fr in self.file_records)
        theirs = sorted((fr.filename, fr) for fr in other.file_records)
        return mine == theirs


    def __ne__(self, other):
        return not self.__eq__(other)

    def __deepcopy__(self, memo):
        # This is required for a deep copy
        # This is required for a deep copy
        return Manifest(self.file_records[:])

    def __copy__(self):
        return Manifest(self.file_records)


    def copy(self):
        return Manifest(self.file_records[:])

    def present(self):
        return all(i.present() for i in self.file_records)
        return all(i.present() for i in self.file_records)

    def validate_sizes(self):
        return all(i.validate_size() for i in self.file_records)

    def validate_digests(self):
        return all(i.validate_digest() for i in self.file_records)


    def validate(self):
        return all(i.validate() for i in self.file_records)

    def load(self, data_file, fmt='json'):
        assert fmt in self.valid_formats
        assert fmt in self.valid_formats
        if fmt == 'json':
            try:
                self.file_records.extend(
                    json.load(data_file, cls=FileRecordJSONDecoder))
            except ValueError:
            except ValueError:
                raise InvalidManifest("trying to read invalid manifest file")

    def loads(self, data_string, fmt='json'):
        assert fmt in self.valid_formats
        assert fmt in self.valid_formats
        if fmt == 'json':
            try:
                self.file_records.extend(
                    json.loads(data_string, cls=FileRecordJSONDecoder))
            except ValueError:
                raise InvalidManifest("trying to read invalid manifest file")
                raise InvalidManifest("trying to read invalid manifest file")

    def dump(self, output_file, fmt='json'):
        assert fmt in self.valid_formats
        if fmt == 'json':
            return json.dump(
            return json.dump(
                self.file_records, output_file,
                indent=2, separators=(',', ': '),
                cls=FileRecordJSONEncoder,
            )


    def dumps(self, fmt='json'):
        assert fmt in self.valid_formats
        if fmt == 'json':
        if fmt == 'json':
            return json.dumps(
            return json.dumps(
                self.file_records,
                indent=2, separators=(',', ': '),
                cls=FileRecordJSONEncoder,
                cls=FileRecordJSONEncoder,
            )


def digest_file(f, a):
    """I take a file like object 'f' and return a hex-string containing
    """I take a file like object 'f' and return a hex-string containing
    of the result of the algorithm 'a' applied to 'f'."""
    of the result of the algorithm 'a' applied to 'f'."""
    h = hashlib.new(a)
    chunk_size = 1024 * 10
    data = f.read(chunk_size)
    data = f.read(chunk_size)
    while data:
        h.update(data)
        data = f.read(chunk_size)
    name = repr(f.name) if hasattr(f, 'name') else 'a file'
    log.debug('hashed %s with %s to be %s', name, a, h.hexdigest())
    log.debug('hashed %s with %s to be %s', name, a, h.hexdigest())
    return h.hexdigest()


def execute(cmd):
    """Execute CMD, logging its stdout at the info level"""
    """Execute CMD, logging its stdout at the info level"""
    process = Popen(cmd, shell=True, stdout=PIPE)
    while True:
        line = process.stdout.readline()
        if not line:
            break
            break
        log.info(line.replace('\n', ' '))
    return process.wait() == 0


def open_manifest(manifest_file):
    """I know how to take a filename and load it into a Manifest object"""
    if os.path.exists(manifest_file):
        manifest = Manifest()
        with open(manifest_file, "rb") as f:
        with open(manifest_file, "rb") as f:
            manifest.load(f)
            log.debug("loaded manifest from file '%s'" % manifest_file)
        return manifest
    else:
        log.debug("tried to load absent file '%s' as manifest" % manifest_file)
        log.debug("tried to load absent file '%s' as manifest" % manifest_file)
        raise InvalidManifest(
            "manifest file '%s' does not exist" % manifest_file)


def list_manifest(manifest_file):
def list_manifest(manifest_file):
    """I know how print all the files in a location"""
    try:
        manifest = open_manifest(manifest_file)
    except InvalidManifest as e:
        log.error("failed to load manifest file at '%s': %s" % (
        log.error("failed to load manifest file at '%s': %s" % (
            manifest_file,
            str(e),
        ))
        ))
        return False
    for f in manifest.file_records:
        print("{}\t{}\t{}".format("P" if f.present() else "-",
                                  "V" if f.present() and f.validate() else "-",
                                  f.filename))
                                  f.filename))
    return True


def validate_manifest(manifest_file):
    """I validate that all files in a manifest are present and valid but
    don't fetch or delete them if they aren't"""
    try:
    try:
        manifest = open_manifest(manifest_file)
    except InvalidManifest as e:
        log.error("failed to load manifest file at '%s': %s" % (
            manifest_file,
            str(e),
            str(e),
        ))
        return False
    invalid_files = []
    absent_files = []
    for f in manifest.file_records:
        if not f.present():
            absent_files.append(f)
        else:
            if not f.validate():
            if not f.validate():
                invalid_files.append(f)
    if len(invalid_files + absent_files) == 0:
        return True
    else:
        return False
        return False


def add_files(manifest_file, algorithm, filenames, version, visibility, unpack):
    # returns True if all files successfully added, False if not
    # and doesn't catch library Exceptions.  If any files are already
    # and doesn't catch library Exceptions.  If any files are already
    # tracked in the manifest, return will be False because they weren't
    # added
    all_files_added = True
    # Create a old_manifest object to add to
    if os.path.exists(manifest_file):
    if os.path.exists(manifest_file):
        old_manifest = open_manifest(manifest_file)
    else:
        old_manifest = Manifest()
        log.debug("creating a new manifest file")
        log.debug("creating a new manifest file")
    new_manifest = Manifest()  # use a different manifest for the output
    for filename in filenames:
        log.debug("adding %s" % filename)
        path, name = os.path.split(filename)
        new_fr = create_file_record(filename, algorithm)
        new_fr = create_file_record(filename, algorithm)
        new_fr.version = version
        new_fr.visibility = visibility
        new_fr.unpack = unpack
        log.debug("appending a new file record to manifest file")
        add = True
        add = True
        for fr in old_manifest.file_records:
            log.debug("manifest file has '%s'" % "', ".join(
                [x.filename for x in old_manifest.file_records]))
            if new_fr == fr:
                log.info("file already in old_manifest")
                log.info("file already in old_manifest")
                add = False
            elif filename == fr.filename:
                log.error("manifest already contains a different file named %s" % filename)
                add = False
        if add:
        if add:
            new_manifest.file_records.append(new_fr)
            log.debug("added '%s' to manifest" % filename)
        else:
        else:
            all_files_added = False
            all_files_added = False
    # copy any files in the old manifest that aren't in the new one
    new_filenames = set(fr.filename for fr in new_manifest.file_records)
    for old_fr in old_manifest.file_records:
        if old_fr.filename not in new_filenames:
            new_manifest.file_records.append(old_fr)
            new_manifest.file_records.append(old_fr)
    if PY3:
        with open(manifest_file, mode="w") as output:
            new_manifest.dump(output, fmt='json')
    else:
        with open(manifest_file, mode="wb") as output:
        with open(manifest_file, mode="wb") as output:
            new_manifest.dump(output, fmt='json')
    return all_files_added


def touch(f):
def touch(f):
    """Used to modify mtime in cached files;
    mtime is used by the purge command"""
    try:
        os.utime(f, None)
    except OSError:
        log.warn('impossible to update utime of file %s' % f)



@contextmanager
@retriable(sleeptime=2)
def request(url, auth_file=None):
    req = Request(url)
    req = Request(url)
    _authorize(req, auth_file)
    with closing(urllib2.urlopen(req)) as f:
        log.debug("opened %s for reading" % url)
        yield f
        yield f


def fetch_file(base_urls, file_record, grabchunk=1024 * 4, auth_file=None, region=None):
    # A file which is requested to be fetched that exists locally will be
    # overwritten by this function
    # overwritten by this function
    fd, temp_path = tempfile.mkstemp(dir=os.getcwd())
    os.close(fd)
    fetched_path = None
    for base_url in base_urls:
        # Generate the URL for the file on the server side
        # Generate the URL for the file on the server side
        url = urljoin(base_url,
                      '%s/%s' % (file_record.algorithm, file_record.digest))
        if region is not None:
            url += '?region=' + region


        log.info("Attempting to fetch from '%s'..." % base_url)

        # Well, the file doesn't exist locally.  Let's fetch it.
        try:
        try:
            with request(url, auth_file) as f, open(temp_path, mode='wb') as out:
                k = True
                size = 0
                while k:
                    # TODO: print statistics as file transfers happen both for info and to stop
                    # buildbot timeouts
                    indata = f.read(grabchunk)
                    indata = f.read(grabchunk)
                    out.write(indata)
                    size += len(indata)
                    if len(indata) == 0:
                        k = False
                log.info("File %s fetched from %s as %s" %
                log.info("File %s fetched from %s as %s" %
                         (file_record.filename, base_url, temp_path))
                fetched_path = temp_path
                break
        except (URLError, HTTPError, ValueError):
            log.info("...failed to fetch '%s' from %s" %
            log.info("...failed to fetch '%s' from %s" %
                     (file_record.filename, base_url), exc_info=True)
        except IOError:  # pragma: no cover
            log.info("failed to write to temporary file for '%s'" %
                     file_record.filename, exc_info=True)

    # cleanup temp file in case of issues
    # cleanup temp file in case of issues
    if fetched_path:
        return os.path.split(fetched_path)[1]
    else:
        try:
            os.remove(temp_path)
            os.remove(temp_path)
        except OSError:  # pragma: no cover
            pass
        return None
        return None



def clean_path(dirname):
def clean_path(dirname):
    """Remove a subtree if is exists. Helper for unpack_file()."""
    if os.path.exists(dirname):
        log.info('rm tree: %s' % dirname)
        shutil.rmtree(dirname)



CHECKSUM_SUFFIX = ".checksum"


def unpack_file(filename):
    """Untar `filename`, assuming it is uncompressed or compressed with bzip2,
    xz, gzip, or unzip a zip file. The file is assumed to contain a single
    directory with a name matching the base of the given filename.
    Xz support is handled by shelling out to 'tar'."""
    if os.path.isfile(filename) and tarfile.is_tarfile(filename):
    if os.path.isfile(filename) and tarfile.is_tarfile(filename):
        tar_file, zip_ext = os.path.splitext(filename)
        base_file, tar_ext = os.path.splitext(tar_file)
        clean_path(base_file)
        log.info('untarring "%s"' % filename)
        tar = tarfile.open(filename)
        tar = tarfile.open(filename)
        tar.extractall()
        tar.close()
    elif os.path.isfile(filename) and filename.endswith('.tar.xz'):
        base_file = filename.replace('.tar.xz', '')
        clean_path(base_file)
        clean_path(base_file)
        log.info('untarring "%s"' % filename)
        # Not using tar -Jxf because it fails on Windows for some reason.
        process = Popen(['xz', '-d', '-c', filename], stdout=PIPE)
        stdout, stderr = process.communicate()
        if process.returncode != 0:
        if process.returncode != 0:
            return False
        fileobj = BytesIO()
        fileobj.write(stdout)
        fileobj.write(stdout)
        fileobj.seek(0)
        fileobj.seek(0)
        tar = tarfile.open(fileobj=fileobj, mode='r|')
        tar.extractall()
        tar.close()
        tar.close()
    elif os.path.isfile(filename) and zipfile.is_zipfile(filename):
        base_file = filename.replace('.zip', '')
        clean_path(base_file)
        log.info('unzipping "%s"' % filename)
        z = zipfile.ZipFile(filename)
        z = zipfile.ZipFile(filename)
        z.extractall()
        z.close()
    else:
        log.error("Unknown archive extension for filename '%s'" % filename)
        return False
        return False
    return True


def fetch_files(manifest_file, base_urls, filenames=[], cache_folder=None,
                auth_file=None, region=None):
                auth_file=None, region=None):
    # Lets load the manifest file
    try:
        manifest = open_manifest(manifest_file)
    except InvalidManifest as e:
        log.error("failed to load manifest file at '%s': %s" % (
        log.error("failed to load manifest file at '%s': %s" % (
            manifest_file,
            str(e),
        ))
        return False


    # we want to track files already in current working directory AND valid
    # we will not need to fetch these
    present_files = []

    # We want to track files that fail to be fetched as well as
    # files that are fetched
    failed_files = []
    failed_files = []
    fetched_files = []

    # Files that we want to unpack.
    unpack_files = []


    # Lets go through the manifest and fetch the files that we want
    for f in manifest.file_records:
        # case 1: files are already present
        if f.present():
            if f.validate():
            if f.validate():
                present_files.append(f.filename)
                if f.unpack:
                    unpack_files.append(f.filename)
                    unpack_files.append(f.filename)
            else:
                # we have an invalid file here, better to cleanup!
                # this invalid file needs to be replaced with a good one
                # from the local cash or fetched from a tooltool server
                log.info("File %s is present locally but it is invalid, so I will remove it "
                log.info("File %s is present locally but it is invalid, so I will remove it "
                         "and try to fetch it" % f.filename)
                os.remove(os.path.join(os.getcwd(), f.filename))

        # check if file is already in cache
        if cache_folder and f.filename not in present_files:
        if cache_folder and f.filename not in present_files:
            try:
                shutil.copy(os.path.join(cache_folder, f.digest),
                            os.path.join(os.getcwd(), f.filename))
                log.info("File %s retrieved from local cache %s" %
                         (f.filename, cache_folder))
                         (f.filename, cache_folder))
                touch(os.path.join(cache_folder, f.digest))

                filerecord_for_validation = FileRecord(
                    f.filename, f.size, f.digest, f.algorithm)
                if filerecord_for_validation.validate():
                if filerecord_for_validation.validate():
                    present_files.append(f.filename)
                    if f.unpack:
                    if f.unpack:
                        unpack_files.append(f.filename)
                else:
                    # the file copied from the cache is invalid, better to
                    # clean up the cache version itself as well
                    log.warn("File %s retrieved from cache is invalid! I am deleting it from the "
                    log.warn("File %s retrieved from cache is invalid! I am deleting it from the "
                             "cache as well" % f.filename)
                    os.remove(os.path.join(os.getcwd(), f.filename))
                    os.remove(os.path.join(cache_folder, f.digest))
            except IOError:
                log.info("File %s not present in local cache folder %s" %
                log.info("File %s not present in local cache folder %s" %
                         (f.filename, cache_folder))

        # now I will try to fetch all files which are not already present and
        # valid, appending a suffix to avoid race conditions
        temp_file_name = None
        # 'filenames' is the list of filenames to be managed, if this variable
        # is a non empty list it can be used to filter if filename is in
        # is a non empty list it can be used to filter if filename is in
        # present_files, it means that I have it already because it was already
        # either in the working dir or in the cache
        if (f.filename in filenames or len(filenames) == 0) and f.filename not in present_files:
            log.debug("fetching %s" % f.filename)
            temp_file_name = fetch_file(base_urls, f, auth_file=auth_file, region=region)
            if temp_file_name:
                fetched_files.append((f, temp_file_name))
                fetched_files.append((f, temp_file_name))
            else:
                failed_files.append(f.filename)
        else:
        else:
            log.debug("skipping %s" % f.filename)
            log.debug("skipping %s" % f.filename)

    # lets ensure that fetched files match what the manifest specified
    for localfile, temp_file_name in fetched_files:
    for localfile, temp_file_name in fetched_files:
        # since I downloaded to a temp file, I need to perform all validations on the temp file
        # this is why filerecord_for_validation is created

        filerecord_for_validation = FileRecord(
            temp_file_name, localfile.size, localfile.digest, localfile.algorithm)
            temp_file_name, localfile.size, localfile.digest, localfile.algorithm)

        if filerecord_for_validation.validate():
            # great!
            # I can rename the temp file
            log.info("File integrity verified, renaming %s to %s" %
            log.info("File integrity verified, renaming %s to %s" %
                     (temp_file_name, localfile.filename))
            os.rename(os.path.join(os.getcwd(), temp_file_name),
                      os.path.join(os.getcwd(), localfile.filename))

            if localfile.unpack:
            if localfile.unpack:
                unpack_files.append(localfile.filename)

            # if I am using a cache and a new file has just been retrieved from a
            # remote location, I need to update the cache as well
            if cache_folder:
            if cache_folder:
                log.info("Updating local cache %s..." % cache_folder)
                try:
                    if not os.path.exists(cache_folder):
                        log.info("Creating cache in %s..." % cache_folder)
                        os.makedirs(cache_folder, 0o0700)
                        os.makedirs(cache_folder, 0o0700)
                    shutil.copy(os.path.join(os.getcwd(), localfile.filename),
                                os.path.join(cache_folder, localfile.digest))
                    log.info("Local cache %s updated with %s" % (cache_folder,
                                                                 localfile.filename))
                                                                 localfile.filename))
                    touch(os.path.join(cache_folder, localfile.digest))
                except (OSError, IOError):
                    log.warning('Impossible to add file %s to cache folder %s' %
                                (localfile.filename, cache_folder), exc_info=True)
        else:
        else:
            failed_files.append(localfile.filename)
            log.error("'%s'" % filerecord_for_validation.describe())
            log.error("'%s'" % filerecord_for_validation.describe())
            os.remove(temp_file_name)

    # Unpack files that need to be unpacked.
    for filename in unpack_files:
        if not unpack_file(filename):
            failed_files.append(filename)


    # If we failed to fetch or validate a file, we need to fail
    if len(failed_files) > 0:
        log.error("The following files failed: '%s'" %
                  "', ".join(failed_files))
        return False
        return False
    return True


def freespace(p):
    "Returns the number of bytes free under directory `p`"
    "Returns the number of bytes free under directory `p`"
    if sys.platform == 'win32':  # pragma: no cover
        # os.statvfs doesn't work on Windows
        import win32file

        secsPerClus, bytesPerSec, nFreeClus, totClus = win32file.GetDiskFreeSpace(
            p)
            p)
        return secsPerClus * bytesPerSec * nFreeClus
        return secsPerClus * bytesPerSec * nFreeClus
    else:
        r = os.statvfs(p)
        return r.f_frsize * r.f_bavail
        return r.f_frsize * r.f_bavail


def purge(folder, gigs):
    """If gigs is non 0, it deletes files in `folder` until `gigs` GB are free,
    starting from older files.  If gigs is 0, a full purge will be performed.
    starting from older files.  If gigs is 0, a full purge will be performed.
    No recursive deletion of files in subfolder is performed."""

    full_purge = bool(gigs == 0)
    gigs *= 1024 * 1024 * 1024


    if not full_purge and freespace(folder) >= gigs:
        log.info("No need to cleanup")
        return

    files = []
    files = []
    for f in os.listdir(folder):
        p = os.path.join(folder, f)
        # it deletes files in folder without going into subfolders,
        # assuming the cache has a flat structure
        if not os.path.isfile(p):
        if not os.path.isfile(p):
            continue
        mtime = os.path.getmtime(p)
        files.append((mtime, p))
        files.append((mtime, p))

    # iterate files sorted by mtime
    for _, f in sorted(files):
        log.info("removing %s to free up space" % f)
        try:
        try:
            os.remove(f)
        except OSError:
            log.info("Impossible to remove %s" % f, exc_info=True)
        if not full_purge and freespace(folder) >= gigs:
            break
            break


def _log_api_error(e):
    if hasattr(e, 'hdrs') and e.hdrs['content-type'] == 'application/json':
        json_resp = json.load(e.fp)
        json_resp = json.load(e.fp)
        log.error("%s: %s" % (json_resp['error']['name'],
                              json_resp['error']['description']))
    else:
        log.exception("Error making RelengAPI request:")



def _authorize(req, auth_file):
    if not auth_file:
        return
        return

    is_taskcluster_auth = False
    with open(auth_file) as f:
        auth_file_content = f.read().strip()
        try:
        try:
            auth_file_content = json.loads(auth_file_content)
            is_taskcluster_auth = True
        except Exception:
            pass


    if is_taskcluster_auth:
        taskcluster_header = make_taskcluster_header(auth_file_content, req)
        log.debug("Using taskcluster credentials in %s" % auth_file)
        req.add_unredirected_header('Authorization', taskcluster_header)
    else:
    else:
        log.debug("Using Bearer token in %s" % auth_file)
        req.add_unredirected_header('Authorization', 'Bearer %s' % auth_file_content)


def _send_batch(base_url, auth_file, batch, region):
def _send_batch(base_url, auth_file, batch, region):
    url = urljoin(base_url, 'upload')
    if region is not None:
        url += "?region=" + region
    data = json.dumps(batch)
    if PY3:
    if PY3:
        data = data.encode("utf-8")
    req = Request(url, data, {'Content-Type': 'application/json'})
    _authorize(req, auth_file)
    try:
        resp = urllib2.urlopen(req)
        resp = urllib2.urlopen(req)
    except (URLError, HTTPError) as e:
        _log_api_error(e)
        return None
    return json.load(resp)['result']



def _s3_upload(filename, file):
    # urllib2 does not support streaming, so we fall back to good old httplib
    url = urlparse(file['put_url'])
    cls = HTTPSConnection if url.scheme == 'https' else HTTPConnection
    host, port = url.netloc.split(':') if ':' in url.netloc else (url.netloc, 443)
    port = int(port)
    conn = cls(host, port)
    try:
    try:
        req_path = "%s?%s" % (url.path, url.query) if url.query else url.path
        with open(filename, 'rb') as f:
            content = f.read()
            content_length = len(content)
            f.seek(0)
            f.seek(0)
            conn.request(
                'PUT',
                req_path,
                f,
                {
                {
                    'Content-Type': 'application/octet-stream',
                    'Content-Length': str(content_length),
                },
            )
            resp = conn.getresponse()
            resp = conn.getresponse()
            resp_body = resp.read()
            conn.close()
        if resp.status != 200:
            raise RuntimeError("Non-200 return from AWS: %s %s\n%s" %
                               (resp.status, resp.reason, resp_body))
                               (resp.status, resp.reason, resp_body))
    except Exception:
        file['upload_exception'] = sys.exc_info()
        file['upload_ok'] = False
    else:
        file['upload_ok'] = True
        file['upload_ok'] = True


def _notify_upload_complete(base_url, auth_file, file):
    req = Request(
        urljoin(
        urljoin(
            base_url,
            'upload/complete/%(algorithm)s/%(digest)s' % file))
    _authorize(req, auth_file)
    try:
        urllib2.urlopen(req)
        urllib2.urlopen(req)
    except HTTPError as e:
        if e.code != 409:
            _log_api_error(e)
            return
        # 409 indicates that the upload URL hasn't expired yet and we
        # should retry after a delay
        to_wait = int(e.headers.get('X-Retry-After', 60))
        log.warning("Waiting %d seconds for upload URLs to expire" % to_wait)
        time.sleep(to_wait)
        _notify_upload_complete(base_url, auth_file, file)
        _notify_upload_complete(base_url, auth_file, file)
    except Exception:
        log.exception("While notifying server of upload completion:")


def upload(manifest, message, base_urls, auth_file, region):
    try:
        manifest = open_manifest(manifest)
    except InvalidManifest:
        log.exception("failed to load manifest file at '%s'")
        log.exception("failed to load manifest file at '%s'")
        return False

    # verify the manifest, since we'll need the files present to upload
    if not manifest.validate():
        log.error('manifest is invalid')
        log.error('manifest is invalid')
        return False

    if any(fr.visibility is None for fr in manifest.file_records):
        log.error('All files in a manifest for upload must have a visibility set')


    # convert the manifest to an upload batch
    # convert the manifest to an upload batch
    batch = {
        'message': message,
        'files': {},
    }
    for fr in manifest.file_records:
    for fr in manifest.file_records:
        batch['files'][fr.filename] = {
            'size': fr.size,
            'digest': fr.digest,
            'algorithm': fr.algorithm,
            'visibility': fr.visibility,
            'visibility': fr.visibility,
        }

    # make the upload request
    resp = _send_batch(base_urls[0], auth_file, batch, region)
    if not resp:
    if not resp:
        return None
    files = resp['files']

    # Upload the files, each in a thread.  This allows us to start all of the
    # uploads before any of the URLs expire.
    # uploads before any of the URLs expire.
    threads = {}
    for filename, file in files.items():
        if 'put_url' in file:
            log.info("%s: starting upload" % (filename,))
            thd = threading.Thread(target=_s3_upload,
                                   args=(filename, file))
            thd.daemon = 1
            thd.start()
            thd.start()
            threads[filename] = thd
        else:
            log.info("%s: already exists on server" % (filename,))

    # re-join all of those threads as they exit
    # re-join all of those threads as they exit
    success = True
    while threads:
        for filename, thread in list(threads.items()):
            if not thread.is_alive():
                # _s3_upload has annotated file with result information
                file = files[filename]
                thread.join()
                if file['upload_ok']:
                    log.info("%s: uploaded" % filename)
                    log.info("%s: uploaded" % filename)
                else:
                    log.error("%s: failed" % filename,
                              exc_info=file['upload_exception'])
                    success = False
                del threads[filename]

    # notify the server that the uploads are completed.  If the notification
    # fails, we don't consider that an error (the server will notice
    # fails, we don't consider that an error (the server will notice
    # eventually)
    for filename, file in files.items():
        if 'put_url' in file and file['upload_ok']:
            log.info("notifying server of upload completion for %s" % (filename,))
            _notify_upload_complete(base_urls[0], auth_file, file)
            _notify_upload_complete(base_urls[0], auth_file, file)

    return success


def send_operation_on_file(data, base_urls, digest, auth_file):
def send_operation_on_file(data, base_urls, digest, auth_file):
    url = base_urls[0]
    url = urljoin(url, 'file/sha512/' + digest)

    data = json.dumps(data)


    req = Request(url, data, {'Content-Type': 'application/json'})
    req.get_method = lambda: 'PATCH'

    _authorize(req, auth_file)


    try:
    try:
        urllib2.urlopen(req)
    except (URLError, HTTPError) as e:
        _log_api_error(e)
        return False
    return True
    return True


def change_visibility(base_urls, digest, visibility, auth_file):
    data = [{
        "op": "set_visibility",
        "op": "set_visibility",
        "visibility": visibility,
    }]
    return send_operation_on_file(data, base_urls, digest, visibility, auth_file)



def delete_instances(base_urls, digest, auth_file):
    data = [{
        "op": "delete_instances",
    }]
    }]
    return send_operation_on_file(data, base_urls, digest, auth_file)


def process_command(options, args):
    """ I know how to take a list of program arguments and
    """ I know how to take a list of program arguments and
    start doing the right thing with them"""
    cmd = args[0]
    cmd_args = args[1:]
    log.debug("processing '%s' command with args '%s'" %
    log.debug("processing '%s' command with args '%s'" %
              (cmd, '", "'.join(cmd_args)))
    log.debug("using options: %s" % options)

    if cmd == 'list':
        return list_manifest(options['manifest'])
        return list_manifest(options['manifest'])
    if cmd == 'validate':
        return validate_manifest(options['manifest'])
    elif cmd == 'add':
    elif cmd == 'add':
        return add_files(options['manifest'], options['algorithm'], cmd_args,
        return add_files(options['manifest'], options['algorithm'], cmd_args,
                         options['version'], options['visibility'],
                         options['unpack'])
    elif cmd == 'purge':
    elif cmd == 'purge':
        if options['cache_folder']:
            purge(folder=options['cache_folder'], gigs=options['size'])
        else:
            log.critical('please specify the cache folder to be purged')
            log.critical('please specify the cache folder to be purged')
            return False
    elif cmd == 'fetch':
        return fetch_files(
            options['manifest'],
            options['base_url'],
            options['base_url'],
            cmd_args,
            cache_folder=options['cache_folder'],
            auth_file=options.get("auth_file"),
            region=options.get('region'))
    elif cmd == 'upload':
    elif cmd == 'upload':
        if not options.get('message'):
            log.critical('upload command requires a message')
            return False
        return upload(
            options.get('manifest'),
            options.get('manifest'),
            options.get('message'),
            options.get('base_url'),
            options.get('auth_file'),
            options.get('region'))
    elif cmd == 'change-visibility':
        if not options.get('digest'):
            log.critical('change-visibility command requires a digest option')
            log.critical('change-visibility command requires a digest option')
            return False
        if not options.get('visibility'):
            log.critical('change-visibility command requires a visibility option')
            return False
        return change_visibility(
        return change_visibility(
            options.get('base_url'),
            options.get('digest'),
            options.get('visibility'),
            options.get('auth_file'),
        )
        )
    elif cmd == 'delete':
        if not options.get('digest'):
            log.critical('change-visibility command requires a digest option')
            return False
        return delete_instances(
            options.get('base_url'),
            options.get('digest'),
            options.get('auth_file'),
            options.get('auth_file'),
        )
    else:
        log.critical('command "%s" is not implemented' % cmd)
        return False



def main(argv, _skip_logging=False):
    # Set up option parsing
    parser = optparse.OptionParser()
    parser.add_option('-q', '--quiet', default=logging.INFO,
                      dest='loglevel', action='store_const', const=logging.ERROR)
    parser.add_option('-v', '--verbose',
                      dest='loglevel', action='store_const', const=logging.DEBUG)
    parser.add_option('-m', '--manifest', default=DEFAULT_MANIFEST_NAME,
    parser.add_option('-m', '--manifest', default=DEFAULT_MANIFEST_NAME,
                      dest='manifest', action='store',
                      help='specify the manifest file to be operated on')
    parser.add_option('-d', '--algorithm', default='sha512',
                      dest='algorithm', action='store',
                      help='hashing algorithm to use (only sha512 is allowed)')
    parser.add_option('--digest', default=None,
                      dest='digest', action='store',
                      dest='digest', action='store',
                      help='digest hash to change visibility for')
    parser.add_option('--visibility', default=None,
                      dest='visibility', choices=['internal', 'public'],
                      help='Visibility level of this file; "internal" is for '
                           'files that cannot be distributed out of the company '
                           'files that cannot be distributed out of the company '
                           'but not for secrets; "public" files are available to '
                           'anyone without restriction')
    parser.add_option('--unpack', default=False,
                      dest='unpack', action='store_true',
                      dest='unpack', action='store_true',
                      help='Request unpacking this file after fetch.'
                           ' This is helpful with tarballs.')
    parser.add_option('--version', default=None,
                      dest='version', action='store',
                      help='Version string for this file. This annotates the '
                      help='Version string for this file. This annotates the '
                           'manifest entry with a version string to help '
                           'identify the contents.')
    parser.add_option('-o', '--overwrite', default=False,
                      dest='overwrite', action='store_true',
                      help='UNUSED; present for backward compatibility')
                      help='UNUSED; present for backward compatibility')
    parser.add_option('--url', dest='base_url', action='append',
                      help='RelengAPI URL ending with /tooltool/; default '
                      'is appropriate for Mozilla')
    parser.add_option('-c', '--cache-folder', dest='cache_folder',
                      help='Local cache folder')
                      help='Local cache folder')
    parser.add_option('-s', '--size',
                      help='free space required (in GB)', dest='size',
                      type='float', default=0.)
    parser.add_option('-r', '--region', help='Preferred AWS region for upload or fetch; '
                      'example: --region=us-west-2')
    parser.add_option('--message',
                      help='The "commit message" for an upload; format with a bug number '
                           'and brief comment',
                           'and brief comment',
                      dest='message')
    parser.add_option('--authentication-file',
                      help='Use the RelengAPI token found in the given file to '
                           'authenticate to the RelengAPI server.',
                      dest='auth_file')
                      dest='auth_file')

    (options_obj, args) = parser.parse_args(argv[1:])

    if not options_obj.base_url:
        tooltool_host = os.environ.get('TOOLTOOL_HOST', 'tooltool.mozilla-releng.net')
        tooltool_host = os.environ.get('TOOLTOOL_HOST', 'tooltool.mozilla-releng.net')
        taskcluster_proxy_url = os.environ.get('TASKCLUSTER_PROXY_URL')
        if taskcluster_proxy_url:
            tooltool_url = '{}/{}'.format(taskcluster_proxy_url, tooltool_host)
        else:
            tooltool_url = 'https://{}'.format(tooltool_host)
            tooltool_url = 'https://{}'.format(tooltool_host)

        options_obj.base_url = [tooltool_url]

    # ensure all URLs have a trailing slash
    def add_slash(url):
    def add_slash(url):
        return url if url.endswith('/') else (url + '/')
    options_obj.base_url = [add_slash(u) for u in options_obj.base_url]

    # expand ~ in --authentication-file
    if options_obj.auth_file:
    if options_obj.auth_file:
        options_obj.auth_file = os.path.expanduser(options_obj.auth_file)

    # Dictionaries are easier to work with
    options = vars(options_obj)


    log.setLevel(options['loglevel'])

    # Set up logging, for now just to the console
    if not _skip_logging:  # pragma: no cover
        ch = logging.StreamHandler()
        cf = logging.Formatter("%(levelname)s - %(message)s")
        ch.setFormatter(cf)
        ch.setFormatter(cf)
        log.addHandler(ch)


    if options['algorithm'] != 'sha512':
        parser.error('only --algorithm sha512 is supported')

    if len(args) < 1:
        parser.error('You must specify a command')
        parser.error('You must specify a command')

    return 0 if process_command(options, args) else 1


if __name__ == "__main__":  # pragma: no cover
    sys.exit(main(sys.argv))