aboutsummaryrefslogtreecommitdiffstats
path: root/lib/bb/fetch2/__init__.py
blob: 1b99a0fe493fdcc6f5887c4abe071445201ecf71 (plain)
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
# ex:ts=4:sw=4:sts=4:et
# -*- tab-width: 4; c-basic-offset: 4; indent-tabs-mode: nil -*-
"""
BitBake 'Fetch' implementations

Classes for obtaining upstream sources for the
BitBake build tools.
"""

# Copyright (C) 2003, 2004  Chris Larson
# Copyright (C) 2012  Intel Corporation
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
#
# 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.
#
# 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.
#
# Based on functions from the base bb module, Copyright 2003 Holger Schurig

from __future__ import absolute_import
from __future__ import print_function
import os, re
import logging
import urllib
import bb.persist_data, bb.utils
import bb.checksum
from bb import data

__version__ = "2"
_checksum_cache = bb.checksum.FileChecksumCache()

logger = logging.getLogger("BitBake.Fetcher")

class BBFetchException(Exception):
    """Class all fetch exceptions inherit from"""
    def __init__(self, message):
         self.msg = message
         Exception.__init__(self, message)

    def __str__(self):
         return self.msg

class MalformedUrl(BBFetchException):
    """Exception raised when encountering an invalid url"""
    def __init__(self, url):
         msg = "The URL: '%s' is invalid and cannot be interpreted" % url
         self.url = url
         BBFetchException.__init__(self, msg)
         self.args = url

class FetchError(BBFetchException):
    """General fetcher exception when something happens incorrectly"""
    def __init__(self, message, url = None):
         if url:
            msg = "Fetcher failure for URL: '%s'. %s" % (url, message)
         else:
            msg = "Fetcher failure: %s" % message
         self.url = url
         BBFetchException.__init__(self, msg)
         self.args = (message, url)

class ChecksumError(FetchError):
    """Exception when mismatched checksum encountered"""

class UnpackError(BBFetchException):
    """General fetcher exception when something happens incorrectly when unpacking"""
    def __init__(self, message, url):
         msg = "Unpack failure for URL: '%s'. %s" % (url, message)
         self.url = url
         BBFetchException.__init__(self, msg)
         self.args = (message, url)

class NoMethodError(BBFetchException):
    """Exception raised when there is no method to obtain a supplied url or set of urls"""
    def __init__(self, url):
         msg = "Could not find a fetcher which supports the URL: '%s'" % url
         self.url = url
         BBFetchException.__init__(self, msg)
         self.args = url

class MissingParameterError(BBFetchException):
    """Exception raised when a fetch method is missing a critical parameter in the url"""
    def __init__(self, missing, url):
         msg = "URL: '%s' is missing the required parameter '%s'" % (url, missing)
         self.url = url
         self.missing = missing
         BBFetchException.__init__(self, msg)
         self.args = (missing, url)

class ParameterError(BBFetchException):
    """Exception raised when a url cannot be proccessed due to invalid parameters."""
    def __init__(self, message, url):
         msg = "URL: '%s' has invalid parameters. %s" % (url, message)
         self.url = url
         BBFetchException.__init__(self, msg)
         self.args = (message, url)

class NetworkAccess(BBFetchException):
    """Exception raised when network access is disabled but it is required."""
    def __init__(self, url, cmd):
         msg = "Network access disabled through BB_NO_NETWORK but access requested with command %s (for url %s)" % (cmd, url)
         self.url = url
         self.cmd = cmd
         BBFetchException.__init__(self, msg)
         self.args = (url, cmd)

class NonLocalMethod(Exception):
    def __init__(self):
        Exception.__init__(self)

def decodeurl(url):
    """Decodes an URL into the tokens (scheme, network location, path,
    user, password, parameters).
    """

    m = re.compile('(?P<type>[^:]*)://((?P<user>.+)@)?(?P<location>[^;]+)(;(?P<parm>.*))?').match(url)
    if not m:
        raise MalformedUrl(url)

    type = m.group('type')
    location = m.group('location')
    if not location:
        raise MalformedUrl(url)
    user = m.group('user')
    parm = m.group('parm')

    locidx = location.find('/')
    if locidx != -1 and type.lower() != 'file':
        host = location[:locidx]
        path = location[locidx:]
    else:
        host = ""
        path = location
    if user:
        m = re.compile('(?P<user>[^:]+)(:?(?P<pswd>.*))').match(user)
        if m:
            user = m.group('user')
            pswd = m.group('pswd')
    else:
        user = ''
        pswd = ''

    p = {}
    if parm:
        for s in parm.split(';'):
            s1, s2 = s.split('=')
            p[s1] = s2

    return type, host, urllib.unquote(path), user, pswd, p

def encodeurl(decoded):
    """Encodes a URL from tokens (scheme, network location, path,
    user, password, parameters).
    """

    type, host, path, user, pswd, p = decoded

    if not path:
        raise MissingParameterError('path', "encoded from the data %s" % str(decoded))
    if not type:
        raise MissingParameterError('type', "encoded from the data %s" % str(decoded))
    url = '%s://' % type
    if user and type != "file":
        url += "%s" % user
        if pswd:
            url += ":%s" % pswd
        url += "@"
    if host and type != "file":
        url += "%s" % host
    url += "%s" % urllib.quote(path)
    if p:
        for parm in p:
            url += ";%s=%s" % (parm, p[parm])

    return url

def uri_replace(ud, uri_find, uri_replace, d):
    if not ud.url or not uri_find or not uri_replace:
        logger.error("uri_replace: passed an undefined value, not replacing")
        return None
    uri_decoded = list(decodeurl(ud.url))
    uri_find_decoded = list(decodeurl(uri_find))
    uri_replace_decoded = list(decodeurl(uri_replace))
    logger.debug(2, "For url %s comparing %s to %s" % (uri_decoded, uri_find_decoded, uri_replace_decoded))
    result_decoded = ['', '', '', '', '', {}]
    for loc, i in enumerate(uri_find_decoded):
        result_decoded[loc] = uri_decoded[loc]
        if loc == 5:
            # Handle URL parameters
            if i:
                # Any specified URL parameters must match
                for k in uri_replace_decoded[loc]:
                    if uri_decoded[loc][k] != uri_replace_decoded[loc][k]:
                        return None
            # Overwrite any specified replacement parameters
            for k in uri_replace_decoded[loc]:
                result_decoded[loc][k] = uri_replace_decoded[loc][k]
        elif loc == 0:
            # Principle of least surprise. We could end up with https matching against http and 
            # generating "files://" urls if we use the regexp engine below.
            if i != uri_decoded[loc]:
                return None
            result_decoded[loc] = uri_replace_decoded[loc]
        elif (re.match(i, uri_decoded[loc])):
            if not uri_replace_decoded[loc]:
                result_decoded[loc] = ""    
            else:
                #bb.note("%s %s %s" % (i, uri_replace_decoded[loc], uri_decoded[loc]))
                result_decoded[loc] = re.sub(i, uri_replace_decoded[loc], uri_decoded[loc])
            if loc == 2:
                # Handle path manipulations
                basename = None
                if uri_decoded[0] != uri_replace_decoded[0] and ud.mirrortarball:
                    # If the source and destination url types differ, must be a mirrortarball mapping
                    basename = os.path.basename(ud.mirrortarball)
                    # Kill parameters, they make no sense for mirror tarballs
                    uri_decoded[5] = {}
                elif ud.localpath and ud.method.supports_checksum(ud):
                    basename = os.path.basename(ud.localpath)
                if basename and not result_decoded[loc].endswith(basename):
                    result_decoded[loc] = os.path.join(result_decoded[loc], basename)
        else:
            return None
    result = encodeurl(result_decoded)
    if result == ud.url:
        return None
    logger.debug(2, "For url %s returning %s" % (ud.url, result))
    return result

methods = []
urldata_cache = {}
saved_headrevs = {}

def fetcher_init(d):
    """
    Called to initialize the fetchers once the configuration data is known.
    Calls before this must not hit the cache.
    """
    # When to drop SCM head revisions controlled by user policy
    srcrev_policy = d.getVar('BB_SRCREV_POLICY', True) or "clear"
    if srcrev_policy == "cache":
        logger.debug(1, "Keeping SRCREV cache due to cache policy of: %s", srcrev_policy)
    elif srcrev_policy == "clear":
        logger.debug(1, "Clearing SRCREV cache due to cache policy of: %s", srcrev_policy)
        revs = bb.persist_data.persist('BB_URI_HEADREVS', d)
        try:
            bb.fetch2.saved_headrevs = revs.items()
        except:
            pass
        revs.clear()
    else:
        raise FetchError("Invalid SRCREV cache policy of: %s" % srcrev_policy)

    _checksum_cache.init_cache(d)

    for m in methods:
        if hasattr(m, "init"):
            m.init(d)

def fetcher_parse_save(d):
    _checksum_cache.save_extras(d)

def fetcher_parse_done(d):
    _checksum_cache.save_merge(d)

def fetcher_compare_revisions(d):
    """
    Compare the revisions in the persistant cache with current values and
    return true/false on whether they've changed.
    """

    data = bb.persist_data.persist('BB_URI_HEADREVS', d).items()
    data2 = bb.fetch2.saved_headrevs

    changed = False
    for key in data:
        if key not in data2 or data2[key] != data[key]:
            logger.debug(1, "%s changed", key)
            changed = True
            return True
        else:
            logger.debug(2, "%s did not change", key)
    return False

def mirror_from_string(data):
    return [ i.split() for i in (data or "").replace('\\n','\n').split('\n') if i ]

def verify_checksum(u, ud, d):
    """
    verify the MD5 and SHA256 checksum for downloaded src

    Raises a FetchError if one or both of the SRC_URI checksums do not match
    the downloaded file, or if BB_STRICT_CHECKSUM is set and there are no
    checksums specified.

    """

    if not ud.method.supports_checksum(ud):
        return

    md5data = bb.utils.md5_file(ud.localpath)
    sha256data = bb.utils.sha256_file(ud.localpath)

    if ud.method.recommends_checksum(ud):
        # If strict checking enabled and neither sum defined, raise error
        strict = d.getVar("BB_STRICT_CHECKSUM", True) or None
        if (strict and ud.md5_expected == None and ud.sha256_expected == None):
            raise FetchError('No checksum specified for %s, please add at least one to the recipe:\n'
                             'SRC_URI[%s] = "%s"\nSRC_URI[%s] = "%s"' %
                             (ud.localpath, ud.md5_name, md5data,
                              ud.sha256_name, sha256data), u)

        # Log missing sums so user can more easily add them
        if ud.md5_expected == None:
            logger.warn('Missing md5 SRC_URI checksum for %s, consider adding to the recipe:\n'
                        'SRC_URI[%s] = "%s"',
                        ud.localpath, ud.md5_name, md5data)

        if ud.sha256_expected == None:
            logger.warn('Missing sha256 SRC_URI checksum for %s, consider adding to the recipe:\n'
                        'SRC_URI[%s] = "%s"',
                        ud.localpath, ud.sha256_name, sha256data)

    md5mismatch = False
    sha256mismatch = False

    if ud.md5_expected != md5data:
        md5mismatch = True

    if ud.sha256_expected != sha256data:
        sha256mismatch = True

    # We want to alert the user if a checksum is defined in the recipe but
    # it does not match.
    msg = ""
    if md5mismatch and ud.md5_expected:
        msg = msg + "\nFile: '%s' has %s checksum %s when %s was expected" % (ud.localpath, 'md5', md5data, ud.md5_expected)

    if sha256mismatch and ud.sha256_expected:
        msg = msg + "\nFile: '%s' has %s checksum %s when %s was expected" % (ud.localpath, 'sha256', sha256data, ud.sha256_expected)

    if len(msg):
        raise ChecksumError('Checksum mismatch!%s' % msg, u)


def update_stamp(u, ud, d):
    """
        donestamp is file stamp indicating the whole fetching is done
        this function update the stamp after verifying the checksum
    """
    if os.path.exists(ud.donestamp):
        # Touch the done stamp file to show active use of the download
        try:
            os.utime(ud.donestamp, None)
        except:
            # Errors aren't fatal here
            pass
    else:
        verify_checksum(u, ud, d)
        open(ud.donestamp, 'w').close()

def subprocess_setup():
    import signal
    # Python installs a SIGPIPE handler by default. This is usually not what
    # non-Python subprocesses expect.
    # SIGPIPE errors are known issues with gzip/bash
    signal.signal(signal.SIGPIPE, signal.SIG_DFL)

def get_autorev(d):
    #  only not cache src rev in autorev case
    if d.getVar('BB_SRCREV_POLICY', True) != "cache":
        d.setVar('__BB_DONT_CACHE', '1')
    return "AUTOINC"

def get_srcrev(d):
    """
    Return the version string for the current package
    (usually to be used as PV)
    Most packages usually only have one SCM so we just pass on the call.
    In the multi SCM case, we build a value based on SRCREV_FORMAT which must
    have been set.
    """

    scms = []
    fetcher = Fetch(d.getVar('SRC_URI', True).split(), d)
    urldata = fetcher.ud
    for u in urldata:
        if urldata[u].method.supports_srcrev():
            scms.append(u)

    if len(scms) == 0:
        raise FetchError("SRCREV was used yet no valid SCM was found in SRC_URI")

    if len(scms) == 1 and len(urldata[scms[0]].names) == 1:
        return urldata[scms[0]].method.sortable_revision(scms[0], urldata[scms[0]], d, urldata[scms[0]].names[0])

    #
    # Mutiple SCMs are in SRC_URI so we resort to SRCREV_FORMAT
    #
    format = d.getVar('SRCREV_FORMAT', True)
    if not format:
        raise FetchError("The SRCREV_FORMAT variable must be set when multiple SCMs are used.")

    for scm in scms:
        ud = urldata[scm]
        for name in ud.names:
            rev = ud.method.sortable_revision(scm, ud, d, name)
            format = format.replace(name, rev)

    return format

def localpath(url, d):
    fetcher = bb.fetch2.Fetch([url], d)
    return fetcher.localpath(url)

def runfetchcmd(cmd, d, quiet = False, cleanup = []):
    """
    Run cmd returning the command output
    Raise an error if interrupted or cmd fails
    Optionally echo command output to stdout
    Optionally remove the files/directories listed in cleanup upon failure
    """

    import bb.process
    import subprocess

    # Need to export PATH as binary could be in metadata paths
    # rather than host provided
    # Also include some other variables.
    # FIXME: Should really include all export varaiables?
    exportvars = ['PATH', 'GIT_PROXY_COMMAND', 'GIT_PROXY_HOST',
                  'GIT_PROXY_PORT', 'GIT_CONFIG', 'http_proxy', 'ftp_proxy',
                  'https_proxy', 'no_proxy', 'ALL_PROXY', 'all_proxy',
                  'SSH_AUTH_SOCK', 'SSH_AGENT_PID', 'HOME',
                  'GIT_PROXY_IGNORE', 'SOCKS5_USER', 'SOCKS5_PASSWD']

    for var in exportvars:
        val = d.getVar(var, True)
        if val:
            cmd = 'export ' + var + '=\"%s\"; %s' % (val, cmd)

    logger.debug(1, "Running %s", cmd)

    success = False
    error_message = ""

    try:
        (output, errors) = bb.process.run(cmd, shell=True, stderr=subprocess.PIPE)
        success = True
    except bb.process.NotFoundError as e:
        error_message = "Fetch command %s" % (e.command)
    except bb.process.ExecutionError as e:
        error_message = "Fetch command %s failed with exit code %s, output:\nSTDOUT: %s\nSTDERR: %s" % (e.command, e.exitcode, e.stdout, e.stderr)
    except bb.process.CmdError as e:
        error_message = "Fetch command %s could not be run:\n%s" % (e.command, e.msg)
    if not success:
        for f in cleanup:
            try:
                bb.utils.remove(f, True)
            except OSError:
                pass

        raise FetchError(error_message)

    return output

def check_network_access(d, info = "", url = None):
    """
    log remote network access, and error if BB_NO_NETWORK is set
    """
    if d.getVar("BB_NO_NETWORK", True) == "1":
        raise NetworkAccess(url, info)
    else:
        logger.debug(1, "Fetcher accessed the network with the command %s" % info)

def build_mirroruris(origud, mirrors, ld):
    uris = []
    uds = []

    def adduri(uri, ud, uris, uds):
        for line in mirrors:
            try:
                (find, replace) = line
            except ValueError:
                continue
            newuri = uri_replace(ud, find, replace, ld)
            if not newuri or newuri in uris or newuri == origud.url:
                continue
            uris.append(newuri)
            newud = FetchData(newuri, ld)
            newud.setup_localpath(ld)
            uds.append(newud)

            adduri(newuri, newud, uris, uds)

    adduri(None, origud, uris, uds)

    return uris, uds

def try_mirror_url(newuri, origud, ud, ld, check = False):
    # Return of None or a value means we're finished
    # False means try another url
    try:
        if check:
            found = ud.method.checkstatus(newuri, ud, ld)
            if found:
                return found
            return False

        os.chdir(ld.getVar("DL_DIR", True))

        if not os.path.exists(ud.donestamp) or ud.method.need_update(newuri, ud, ld):
            ud.method.download(newuri, ud, ld)
            if hasattr(ud.method,"build_mirror_data"):
                ud.method.build_mirror_data(newuri, ud, ld)

        if not ud.localpath or not os.path.exists(ud.localpath):
            return False

        if ud.localpath == origud.localpath:
            return ud.localpath

        # We may be obtaining a mirror tarball which needs further processing by the real fetcher
        # If that tarball is a local file:// we need to provide a symlink to it
        dldir = ld.getVar("DL_DIR", True)
        if origud.mirrortarball and os.path.basename(ud.localpath) == os.path.basename(origud.mirrortarball) \
                and os.path.basename(ud.localpath) != os.path.basename(origud.localpath):
            open(ud.donestamp, 'w').close()
            dest = os.path.join(dldir, os.path.basename(ud.localpath))
            if not os.path.exists(dest):
                os.symlink(ud.localpath, dest)
            return None
        # Otherwise the result is a local file:// and we symlink to it
        if not os.path.exists(origud.localpath):
             os.symlink(ud.localpath, origud.localpath)
        update_stamp(newuri, origud, ld)
        return ud.localpath

    except bb.fetch2.NetworkAccess:
        raise

    except bb.fetch2.BBFetchException as e:
        if isinstance(e, ChecksumError):
            logger.warn("Mirror checksum failure for url %s (original url: %s)\nCleaning and trying again." % (newuri, origud.url))
            logger.warn(str(e))
        else:
            logger.debug(1, "Mirror fetch failure for url %s (original url: %s)" % (newuri, origud.url))
            logger.debug(1, str(e))
        try:
            ud.method.clean(ud, ld)
        except UnboundLocalError:
            pass
        return False

def try_mirrors(d, origud, mirrors, check = False):
    """
    Try to use a mirrored version of the sources.
    This method will be automatically called before the fetchers go.

    d Is a bb.data instance
    uri is the original uri we're trying to download
    mirrors is the list of mirrors we're going to try
    """
    ld = d.createCopy()

    uris, uds = build_mirroruris(origud, mirrors, ld)

    for index, uri in enumerate(uris):
        ret = try_mirror_url(uri, origud, uds[index], ld, check)
        if ret != False:
            return ret
    return None

def srcrev_internal_helper(ud, d, name):
    """
    Return:
        a) a source revision if specified
        b) latest revision if SRCREV="AUTOINC"
        c) None if not specified
    """

    if 'rev' in ud.parm:
        return ud.parm['rev']

    if 'tag' in ud.parm:
        return ud.parm['tag']

    rev = None
    pn = d.getVar("PN", True)
    if name != '':
        rev = d.getVar("SRCREV_%s_pn-%s" % (name, pn), True)
        if not rev:
            rev = d.getVar("SRCREV_%s" % name, True)
    if not rev:
       rev = d.getVar("SRCREV_pn-%s" % pn, True)
    if not rev:
        rev = d.getVar("SRCREV", True)
    if rev == "INVALID":
        raise FetchError("Please set SRCREV to a valid value", ud.url)
    if rev == "AUTOINC":
        rev = ud.method.latest_revision(ud.url, ud, d, name)

    return rev


def get_checksum_file_list(d):
    """ Get a list of files checksum in SRC_URI

    Returns the resolved local paths of all local file entries in
    SRC_URI as a space-separated string
    """
    fetch = Fetch([], d, cache = False, localonly = True)

    dl_dir = d.getVar('DL_DIR', True)
    filelist = []
    for u in fetch.urls:
        ud = fetch.ud[u]

        if ud and isinstance(ud.method, local.Local):
            ud.setup_localpath(d)
            f = ud.localpath
            if f.startswith(dl_dir):
                # The local fetcher's behaviour is to return a path under DL_DIR if it couldn't find the file anywhere else
                if os.path.exists(f):
                    bb.warn("Getting checksum for %s SRC_URI entry %s: file not found except in DL_DIR" % (d.getVar('PN', True), os.path.basename(f)))
                else:
                    bb.warn("Unable to get checksum for %s SRC_URI entry %s: file could not be found" % (d.getVar('PN', True), os.path.basename(f)))
                    continue
            filelist.append(f)

    return " ".join(filelist)


def get_file_checksums(filelist, pn):
    """Get a list of the checksums for a list of local files

    Returns the checksums for a list of local files, caching the results as
    it proceeds

    """

    def checksum_file(f):
        try:
            checksum = _checksum_cache.get_checksum(f)
        except OSError as e:
            import traceback
            bb.warn("Unable to get checksum for %s SRC_URI entry %s: %s" % (pn, os.path.basename(f), e))
            return None
        return checksum

    checksums = []
    for pth in filelist.split():
        checksum = None
        if '*' in pth:
            # Handle globs
            import glob
            for f in glob.glob(pth):
                checksum = checksum_file(f)
                if checksum:
                    checksums.append((f, checksum))
        elif os.path.isdir(pth):
            # Handle directories
            for root, dirs, files in os.walk(pth):
                for name in files:
                    fullpth = os.path.join(root, name)
                    checksum = checksum_file(fullpth)
                    if checksum:
                        checksums.append((fullpth, checksum))
        else:
            checksum = checksum_file(pth)

        if checksum:
            checksums.append((pth, checksum))

    checksums.sort()
    return checksums


class FetchData(object):
    """
    A class which represents the fetcher state for a given URI.
    """
    def __init__(self, url, d, localonly = False):
        # localpath is the location of a downloaded result. If not set, the file is local.
        self.donestamp = None
        self.localfile = ""
        self.localpath = None
        self.lockfile = None
        self.mirrortarball = None
        self.basename = None
        (self.type, self.host, self.path, self.user, self.pswd, self.parm) = decodeurl(data.expand(url, d))
        self.date = self.getSRCDate(d)
        self.url = url
        if not self.user and "user" in self.parm:
            self.user = self.parm["user"]
        if not self.pswd and "pswd" in self.parm:
            self.pswd = self.parm["pswd"]
        self.setup = False

        if "name" in self.parm:
            self.md5_name = "%s.md5sum" % self.parm["name"]
            self.sha256_name = "%s.sha256sum" % self.parm["name"]
        else:
            self.md5_name = "md5sum"
            self.sha256_name = "sha256sum"
        if self.md5_name in self.parm:
            self.md5_expected = self.parm[self.md5_name]
        elif self.type not in ["http", "https", "ftp", "ftps"]:
            self.md5_expected = None
        else:
            self.md5_expected = d.getVarFlag("SRC_URI", self.md5_name)
        if self.sha256_name in self.parm:
            self.sha256_expected = self.parm[self.sha256_name]
        elif self.type not in ["http", "https", "ftp", "ftps"]:
            self.sha256_expected = None
        else:
            self.sha256_expected = d.getVarFlag("SRC_URI", self.sha256_name)

        self.names = self.parm.get("name",'default').split(',')

        self.method = None
        for m in methods:
            if m.supports(url, self, d):
                self.method = m
                break                

        if not self.method:
            raise NoMethodError(url)

        if localonly and not isinstance(self.method, local.Local):
            raise NonLocalMethod()

        if hasattr(self.method, "urldata_init"):
            self.method.urldata_init(self, d)

        if "localpath" in self.parm:
            # if user sets localpath for file, use it instead.
            self.localpath = self.parm["localpath"]
            self.basename = os.path.basename(self.localpath)
        elif self.localfile:
            self.localpath = self.method.localpath(self.url, self, d)

        # Note: These files should always be in DL_DIR whereas localpath may not be.
        basepath = d.expand("${DL_DIR}/%s" % os.path.basename(self.localpath or self.basename))
        self.donestamp = basepath + '.done'
        self.lockfile = basepath + '.lock'

    def setup_revisons(self, d):
        self.revisions = {}
        for name in self.names:
            self.revisions[name] = srcrev_internal_helper(self, d, name)

        # add compatibility code for non name specified case
        if len(self.names) == 1:
            self.revision = self.revisions[self.names[0]]

    def setup_localpath(self, d):
        if not self.localpath:
            self.localpath = self.method.localpath(self.url, self, d)

    def getSRCDate(self, d):
        """
        Return the SRC Date for the component

        d the bb.data module
        """
        if "srcdate" in self.parm:
            return self.parm['srcdate']

        pn = d.getVar("PN", True)

        if pn:
            return d.getVar("SRCDATE_%s" % pn, True) or d.getVar("SRCDATE", True) or d.getVar("DATE", True)

        return d.getVar("SRCDATE", True) or d.getVar("DATE", True)

class FetchMethod(object):
    """Base class for 'fetch'ing data"""

    def __init__(self, urls = []):
        self.urls = []

    def supports(self, url, urldata, d):
        """
        Check to see if this fetch class supports a given url.
        """
        return 0

    def localpath(self, url, urldata, d):
        """
        Return the local filename of a given url assuming a successful fetch.
        Can also setup variables in urldata for use in go (saving code duplication
        and duplicate code execution)
        """
        return os.path.join(data.getVar("DL_DIR", d, True), urldata.localfile)

    def supports_checksum(self, urldata):
        """
        Is localpath something that can be represented by a checksum?
        """

        # We cannot compute checksums for directories
        if os.path.isdir(urldata.localpath) == True:
            return False
        if urldata.localpath.find("*") != -1:
             return False

        return True

    def recommends_checksum(self, urldata):
        """
        Is the backend on where checksumming is recommended (should warnings 
        by displayed if there is no checksum)?
        """
        return False

    def _strip_leading_slashes(self, relpath):
        """
        Remove leading slash as os.path.join can't cope
        """
        while os.path.isabs(relpath):
            relpath = relpath[1:]
        return relpath

    def setUrls(self, urls):
        self.__urls = urls

    def getUrls(self):
        return self.__urls

    urls = property(getUrls, setUrls, None, "Urls property")

    def need_update(self, url, ud, d):
        """
        Force a fetch, even if localpath exists?
        """
        if os.path.exists(ud.localpath):
            return False
        return True

    def supports_srcrev(self):
        """
        The fetcher supports auto source revisions (SRCREV)
        """
        return False

    def download(self, url, urldata, d):
        """
        Fetch urls
        Assumes localpath was called first
        """
        raise NoMethodError(url)

    def unpack(self, urldata, rootdir, data):
        import subprocess
        iterate = False
        file = urldata.localpath

        try:
            unpack = bb.utils.to_boolean(urldata.parm.get('unpack'), True)
        except ValueError as exc:
            bb.fatal("Invalid value for 'unpack' parameter for %s: %s" %
                     (file, urldata.parm.get('unpack')))

        dots = file.split(".")
        if dots[-1] in ['gz', 'bz2', 'Z']:
            efile = os.path.join(rootdir, os.path.basename('.'.join(dots[0:-1])))
        else:
            efile = file
        cmd = None

        if unpack:
            if file.endswith('.tar'):
                cmd = 'tar x --no-same-owner -f %s' % file
            elif file.endswith('.tgz') or file.endswith('.tar.gz') or file.endswith('.tar.Z'):
                cmd = 'tar xz --no-same-owner -f %s' % file
            elif file.endswith('.tbz') or file.endswith('.tbz2') or file.endswith('.tar.bz2'):
                cmd = 'bzip2 -dc %s | tar x --no-same-owner -f -' % file
            elif file.endswith('.gz') or file.endswith('.Z') or file.endswith('.z'):
                cmd = 'gzip -dc %s > %s' % (file, efile)
            elif file.endswith('.bz2'):
                cmd = 'bzip2 -dc %s > %s' % (file, efile)
            elif file.endswith('.tar.xz'):
                cmd = 'xz -dc %s | tar x --no-same-owner -f -' % file
            elif file.endswith('.xz'):
                cmd = 'xz -dc %s > %s' % (file, efile)
            elif file.endswith('.zip') or file.endswith('.jar'):
                try:
                    dos = bb.utils.to_boolean(urldata.parm.get('dos'), False)
                except ValueError as exc:
                    bb.fatal("Invalid value for 'dos' parameter for %s: %s" %
                             (file, urldata.parm.get('dos')))
                cmd = 'unzip -q -o'
                if dos:
                    cmd = '%s -a' % cmd
                cmd = "%s '%s'" % (cmd, file)
            elif file.endswith('.src.rpm') or file.endswith('.srpm'):
                if 'extract' in urldata.parm:
                    unpack_file = urldata.parm.get('extract')
                    cmd = 'rpm2cpio.sh %s | cpio -i %s' % (file, unpack_file)
                    iterate = True
                    iterate_file = unpack_file
                else:
                    cmd = 'rpm2cpio.sh %s | cpio -i' % (file)

        if not unpack or not cmd:
            # If file == dest, then avoid any copies, as we already put the file into dest!
            dest = os.path.join(rootdir, os.path.basename(file))
            if (file != dest) and not (os.path.exists(dest) and os.path.samefile(file, dest)):
                if os.path.isdir(file):
                    filesdir = os.path.realpath(data.getVar("FILESDIR", True))
                    destdir = "."
                    if file[0:len(filesdir)] == filesdir:
                        destdir = file[len(filesdir):file.rfind('/')]
                        destdir = destdir.strip('/')
                        if len(destdir) < 1:
                            destdir = "."
                        elif not os.access("%s/%s" % (rootdir, destdir), os.F_OK):
                            os.makedirs("%s/%s" % (rootdir, destdir))
                    cmd = 'cp -pPR %s %s/%s/' % (file, rootdir, destdir)
                    #cmd = 'tar -cf - -C "%d" -ps . | tar -xf - -C "%s/%s/"' % (file, rootdir, destdir)
                else:
                    # The "destdir" handling was specifically done for FILESPATH
                    # items.  So, only do so for file:// entries.
                    if urldata.type == "file" and urldata.path.find("/") != -1:
                       destdir = urldata.path.rsplit("/", 1)[0]
                    else:
                       destdir = "."
                    bb.utils.mkdirhier("%s/%s" % (rootdir, destdir))
                    cmd = 'cp %s %s/%s/' % (file, rootdir, destdir)

        if not cmd:
            return

        # Change to subdir before executing command
        save_cwd = os.getcwd();
        os.chdir(rootdir)
        if 'subdir' in urldata.parm:
            newdir = ("%s/%s" % (rootdir, urldata.parm.get('subdir')))
            bb.utils.mkdirhier(newdir)
            os.chdir(newdir)

        path = data.getVar('PATH', True)
        if path:
            cmd = "PATH=\"%s\" %s" % (path, cmd)
        bb.note("Unpacking %s to %s/" % (file, os.getcwd()))
        ret = subprocess.call(cmd, preexec_fn=subprocess_setup, shell=True)

        os.chdir(save_cwd)

        if ret != 0:
            raise UnpackError("Unpack command %s failed with return value %s" % (cmd, ret), urldata.url)

        if iterate is True:
            iterate_urldata = urldata
            iterate_urldata.localpath = "%s/%s" % (rootdir, iterate_file)
            self.unpack(urldata, rootdir, data)

        return

    def clean(self, urldata, d):
       """
       Clean any existing full or partial download
       """
       bb.utils.remove(urldata.localpath)

    def try_premirror(self, url, urldata, d):
        """
        Should premirrors be used?
        """
        return True

    def checkstatus(self, url, urldata, d):
        """
        Check the status of a URL
        Assumes localpath was called first
        """
        logger.info("URL %s could not be checked for status since no method exists.", url)
        return True

    def localcount_internal_helper(ud, d, name):
        """
        Return:
            a) a locked localcount if specified
            b) None otherwise
        """

        localcount = None
        if name != '':
            pn = d.getVar("PN", True)
            localcount = d.getVar("LOCALCOUNT_" + name, True)
        if not localcount:
            localcount = d.getVar("LOCALCOUNT", True)
        return localcount

    localcount_internal_helper = staticmethod(localcount_internal_helper)

    def latest_revision(self, url, ud, d, name):
        """
        Look in the cache for the latest revision, if not present ask the SCM.
        """
        if not hasattr(self, "_latest_revision"):
            raise ParameterError("The fetcher for this URL does not support _latest_revision", url)

        revs = bb.persist_data.persist('BB_URI_HEADREVS', d)
        key = self.generate_revision_key(url, ud, d, name)
        try:
            return revs[key]
        except KeyError:
            revs[key] = rev = self._latest_revision(url, ud, d, name)
            return rev

    def sortable_revision(self, url, ud, d, name):
        """

        """
        if hasattr(self, "_sortable_revision"):
            return self._sortable_revision(url, ud, d)

        localcounts = bb.persist_data.persist('BB_URI_LOCALCOUNT', d)
        key = self.generate_revision_key(url, ud, d, name)

        latest_rev = self._build_revision(url, ud, d, name)
        last_rev = localcounts.get(key + '_rev')
        uselocalcount = d.getVar("BB_LOCALCOUNT_OVERRIDE", True) or False
        count = None
        if uselocalcount:
            count = FetchMethod.localcount_internal_helper(ud, d, name)
        if count is None:
            count = localcounts.get(key + '_count') or "0"

        if last_rev == latest_rev:
            return str(count + "+" + latest_rev)

        buildindex_provided = hasattr(self, "_sortable_buildindex")
        if buildindex_provided:
            count = self._sortable_buildindex(url, ud, d, latest_rev)

        if count is None:
            count = "0"
        elif uselocalcount or buildindex_provided:
            count = str(count)
        else:
            count = str(int(count) + 1)

        localcounts[key + '_rev'] = latest_rev
        localcounts[key + '_count'] = count

        return str(count + "+" + latest_rev)

    def generate_revision_key(self, url, ud, d, name):
        key = self._revision_key(url, ud, d, name)
        return "%s-%s" % (key, d.getVar("PN", True) or "")

class Fetch(object):
    def __init__(self, urls, d, cache = True, localonly = False):
        if localonly and cache:
            raise Exception("bb.fetch2.Fetch.__init__: cannot set cache and localonly at same time")

        if len(urls) == 0:
            urls = d.getVar("SRC_URI", True).split()
        self.urls = urls
        self.d = d
        self.ud = {}

        fn = d.getVar('FILE', True)
        if cache and fn and fn in urldata_cache:
            self.ud = urldata_cache[fn]

        for url in urls:
            if url not in self.ud:
                try:
                    self.ud[url] = FetchData(url, d, localonly)
                except NonLocalMethod:
                    if localonly:
                        self.ud[url] = None
                        pass

        if fn and cache:
            urldata_cache[fn] = self.ud

    def localpath(self, url):
        if url not in self.urls:
            self.ud[url] = FetchData(url, self.d)

        self.ud[url].setup_localpath(self.d)
        return self.d.expand(self.ud[url].localpath)

    def localpaths(self):
        """
        Return a list of the local filenames, assuming successful fetch
        """
        local = []

        for u in self.urls:
            ud = self.ud[u]
            ud.setup_localpath(self.d)
            local.append(ud.localpath)

        return local

    def download(self, urls = []):
        """
        Fetch all urls
        """
        if len(urls) == 0:
            urls = self.urls

        network = self.d.getVar("BB_NO_NETWORK", True)
        premirroronly = (self.d.getVar("BB_FETCH_PREMIRRORONLY", True) == "1")

        for u in urls:
            ud = self.ud[u]
            ud.setup_localpath(self.d)
            m = ud.method
            localpath = ""

            lf = bb.utils.lockfile(ud.lockfile)

            try:
                self.d.setVar("BB_NO_NETWORK", network)
 
                if os.path.exists(ud.donestamp) and not m.need_update(u, ud, self.d):
                    localpath = ud.localpath
                elif m.try_premirror(u, ud, self.d):
                    logger.debug(1, "Trying PREMIRRORS")
                    mirrors = mirror_from_string(self.d.getVar('PREMIRRORS', True))
                    localpath = try_mirrors(self.d, ud, mirrors, False)

                if premirroronly:
                    self.d.setVar("BB_NO_NETWORK", "1")

                os.chdir(self.d.getVar("DL_DIR", True))

                firsterr = None
                if not localpath and ((not os.path.exists(ud.donestamp)) or m.need_update(u, ud, self.d)):
                    try:
                        logger.debug(1, "Trying Upstream")
                        m.download(u, ud, self.d)
                        if hasattr(m, "build_mirror_data"):
                            m.build_mirror_data(u, ud, self.d)
                        localpath = ud.localpath
                        # early checksum verify, so that if checksum mismatched,
                        # fetcher still have chance to fetch from mirror
                        update_stamp(u, ud, self.d)

                    except bb.fetch2.NetworkAccess:
                        raise

                    except BBFetchException as e:
                        if isinstance(e, ChecksumError):
                            logger.warn("Checksum error encountered with download (will attempt other sources): %s" % str(e))
                        else:
                            logger.warn('Failed to fetch URL %s, attempting MIRRORS if available' % u)
                            logger.debug(1, str(e))
                        firsterr = e
                        # Remove any incomplete fetch
                        m.clean(ud, self.d)
                        logger.debug(1, "Trying MIRRORS")
                        mirrors = mirror_from_string(self.d.getVar('MIRRORS', True))
                        localpath = try_mirrors (self.d, ud, mirrors)

                if not localpath or ((not os.path.exists(localpath)) and localpath.find("*") == -1):
                    if firsterr:
                        logger.error(str(firsterr))
                    raise FetchError("Unable to fetch URL from any source.", u)

                update_stamp(u, ud, self.d)

            finally:
                bb.utils.unlockfile(lf)

    def checkstatus(self, urls = []):
        """
        Check all urls exist upstream
        """

        if len(urls) == 0:
            urls = self.urls

        for u in urls:
            ud = self.ud[u]
            ud.setup_localpath(self.d)
            m = ud.method
            logger.debug(1, "Testing URL %s", u)
            # First try checking uri, u, from PREMIRRORS
            mirrors = mirror_from_string(self.d.getVar('PREMIRRORS', True))
            ret = try_mirrors(self.d, ud, mirrors, True)
            if not ret:
                # Next try checking from the original uri, u
                try:
                    ret = m.checkstatus(u, ud, self.d)
                except:
                    # Finally, try checking uri, u, from MIRRORS
                    mirrors = mirror_from_string(self.d.getVar('MIRRORS', True))
                    ret = try_mirrors(self.d, ud, mirrors, True)

            if not ret:
                raise FetchError("URL %s doesn't work" % u, u)

    def unpack(self, root, urls = []):
        """
        Check all urls exist upstream
        """

        if len(urls) == 0:
            urls = self.urls

        for u in urls:
            ud = self.ud[u]
            ud.setup_localpath(self.d)

            if self.d.expand(self.localpath) is None:
                continue

            if ud.lockfile:
                lf = bb.utils.lockfile(ud.lockfile)

            ud.method.unpack(ud, root, self.d)

            if ud.lockfile:
                bb.utils.unlockfile(lf)

    def clean(self, urls = []):
        """
        Clean files that the fetcher gets or places
        """

        if len(urls) == 0:
            urls = self.urls

        for url in urls:
            if url not in self.ud:
                self.ud[url] = FetchData(url, d)
            ud = self.ud[url]
            ud.setup_localpath(self.d)

            if not ud.localfile or self.localpath is None:
                continue

            if ud.lockfile:
                lf = bb.utils.lockfile(ud.lockfile)

            ud.method.clean(ud, self.d)
            if ud.donestamp:
                bb.utils.remove(ud.donestamp)

            if ud.lockfile:
                bb.utils.unlockfile(lf)

from . import cvs
from . import git
from . import local
from . import svn
from . import wget
from . import svk
from . import ssh
from . import perforce
from . import bzr
from . import hg
from . import osc
from . import repo

methods.append(local.Local())
methods.append(wget.Wget())
methods.append(svn.Svn())
methods.append(git.Git())
methods.append(cvs.Cvs())
methods.append(svk.Svk())
methods.append(ssh.SSH())
methods.append(perforce.Perforce())
methods.append(bzr.Bzr())
methods.append(hg.Hg())
methods.append(osc.Osc())
methods.append(repo.Repo())