summaryrefslogtreecommitdiffstats
path: root/bin/reproducible_common.py
blob: 78a64c3d96c58c5ea24e45548ec3219cd30adaa6 (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
#!/usr/bin/python3
# -*- coding: utf-8 -*-
#
# Copyright © 2015 Mattia Rizzolo <mattia@mapreri.org>
# Copyright © 2015-2017 Holger Levsen <holger@layer-acht.org>
# Based on the reproducible_common.sh by © 2014 Holger Levsen <holger@layer-acht.org>
# Licensed under GPL-2
#
# Depends: python3 python3-psycopg2
#
# This is included by all reproducible_*.py scripts, it contains common functions

import os
import re
import sys
import csv
import json
import errno
import atexit
import hashlib
import logging
import argparse
import pystache
import psycopg2
import html as HTML
from string import Template
from traceback import print_exception
from subprocess import call, check_call
from tempfile import NamedTemporaryFile
from datetime import datetime, timedelta
from sqlalchemy import MetaData, Table, sql, create_engine
from sqlalchemy.exc import NoSuchTableError, OperationalError

DEBUG = False
QUIET = False

# don't try to run on test system
if os.uname()[1] == 'jenkins-test-vm':
    sys.exit()

# tested suites
SUITES = ['stretch', 'buster', 'unstable', 'experimental']
# tested architectures
ARCHS = ['amd64', 'i386', 'arm64', 'armhf']
# defaults
defaultsuite = 'unstable'
defaultarch = 'amd64'

BIN_PATH = '/srv/jenkins/bin'
BASE = '/var/lib/jenkins/userContent/reproducible'
DEBIAN_BASE = '/var/lib/jenkins/userContent/reproducible/debian'
TEMPLATE_PATH = '/srv/jenkins/mustache-templates/reproducible'
PKGSET_DEF_PATH = '/srv/reproducible-results'
TEMP_PATH="/tmp/reproducible"

REPRODUCIBLE_JSON = BASE + '/reproducible.json'
REPRODUCIBLE_TRACKER_JSON = BASE + '/reproducible-tracker.json'
REPRODUCIBLE_STYLES = BASE +'/static/style.css'

DEBIAN_URI = '/debian'
DBD_URI = '/debian/dbd'
DBDTXT_URI = '/debian/dbdtxt'
LOGS_URI = '/debian/logs'
DIFFS_URI = '/debian/logdiffs'
NOTES_URI = '/debian/notes'
ISSUES_URI = '/debian/issues'
RB_PKG_URI = '/debian/rb-pkg'
RBUILD_URI = '/debian/rbuild'
HISTORY_URI = '/debian/history'
BUILDINFO_URI = '/debian/buildinfo'
DBD_PATH = BASE + DBD_URI
DBDTXT_PATH = BASE + DBDTXT_URI
LOGS_PATH = BASE + LOGS_URI
DIFFS_PATH = BASE + DIFFS_URI
NOTES_PATH = BASE + NOTES_URI
ISSUES_PATH = BASE + ISSUES_URI
RB_PKG_PATH = BASE + RB_PKG_URI
RBUILD_PATH = BASE + RBUILD_URI
HISTORY_PATH = BASE + HISTORY_URI
BUILDINFO_PATH = BASE + BUILDINFO_URI

REPRODUCIBLE_URL = 'https://tests.reproducible-builds.org'
DEBIAN_URL = 'https://tests.reproducible-builds.org/debian'
DEBIAN_DASHBOARD_URI = '/debian/reproducible.html'
JENKINS_URL = 'https://jenkins.debian.net'

# global package set definitions
# META_PKGSET[pkgset_id] = (pkgset_name, pkgset_group)
# csv file columns: (pkgset_group, pkgset_name)
META_PKGSET = []
with open(os.path.join(BIN_PATH, './reproducible_pkgsets.csv'), newline='') as f:
    for line in csv.reader(f):
        META_PKGSET.append((line[1], line[0]))

# DATABSE CONSTANT
PGDATABASE = 'reproducibledb'

parser = argparse.ArgumentParser()
group = parser.add_mutually_exclusive_group()
group.add_argument("-d", "--debug", action="store_true")
group.add_argument("-q", "--quiet", action="store_true")
parser.add_argument("--skip-database-connection", action="store_true",
                   help="skip connecting to database")
parser.add_argument("--ignore-missing-files", action="store_true",
                    help="useful for local testing, where you don't have all the build logs, etc..")
args, unknown_args = parser.parse_known_args()
log_level = logging.INFO
if args.debug or DEBUG:
    DEBUG = True
    log_level = logging.DEBUG
if args.quiet or QUIET:
    log_level = logging.ERROR
log = logging.getLogger(__name__)
log.setLevel(log_level)
sh = logging.StreamHandler()
sh.setFormatter(logging.Formatter('[%(asctime)s] %(levelname)s: %(message)s', datefmt='%Y-%m-%d %H:%M:%S'))
log.addHandler(sh)

started_at = datetime.now()
log.info('Starting at %s', started_at)

# init the database data and connection
if not args.skip_database_connection:
    DB_ENGINE = create_engine("postgresql:///%s" % PGDATABASE)
    DB_METADATA = MetaData(DB_ENGINE)  # Get all table definitions
    conn_db = DB_ENGINE.connect()      # the local postgres reproducible db

log.debug("BIN_PATH:\t" + BIN_PATH)
log.debug("BASE:\t\t" + BASE)
log.debug("DBD_URI:\t\t" + DBD_URI)
log.debug("DBD_PATH:\t" + DBD_PATH)
log.debug("DBDTXT_URI:\t" + DBDTXT_URI)
log.debug("DBDTXT_PATH:\t" + DBDTXT_PATH)
log.debug("LOGS_URI:\t" + LOGS_URI)
log.debug("LOGS_PATH:\t" + LOGS_PATH)
log.debug("DIFFS_URI:\t" + DIFFS_URI)
log.debug("DIFFS_PATH:\t" + DIFFS_PATH)
log.debug("NOTES_URI:\t" + NOTES_URI)
log.debug("ISSUES_URI:\t" + ISSUES_URI)
log.debug("NOTES_PATH:\t" + NOTES_PATH)
log.debug("ISSUES_PATH:\t" + ISSUES_PATH)
log.debug("RB_PKG_URI:\t" + RB_PKG_URI)
log.debug("RB_PKG_PATH:\t" + RB_PKG_PATH)
log.debug("RBUILD_URI:\t" + RBUILD_URI)
log.debug("RBUILD_PATH:\t" + RBUILD_PATH)
log.debug("HISTORY_URI:\t" + HISTORY_URI)
log.debug("HISTORY_PATH:\t" + HISTORY_PATH)
log.debug("BUILDINFO_URI:\t" + BUILDINFO_URI)
log.debug("BUILDINFO_PATH:\t" + BUILDINFO_PATH)
log.debug("REPRODUCIBLE_JSON:\t" + REPRODUCIBLE_JSON)
log.debug("JENKINS_URL:\t\t" + JENKINS_URL)
log.debug("REPRODUCIBLE_URL:\t" + REPRODUCIBLE_URL)
log.debug("DEBIAN_URL:\t" + DEBIAN_URL)

if args.ignore_missing_files:
    log.warning("Missing files will be ignored!")

tab = '  '

# take a SHA1 of the css page for style version
hasher = hashlib.sha1()
with open(REPRODUCIBLE_STYLES, 'rb') as f:
        hasher.update(f.read())
REPRODUCIBLE_STYLE_SHA1 = hasher.hexdigest()

# Templates used for creating package pages
renderer = pystache.Renderer()
status_icon_link_template = renderer.load_template(
    TEMPLATE_PATH + '/status_icon_link')
default_page_footer_template = renderer.load_template(
    TEMPLATE_PATH + '/default_page_footer')
pkg_legend_template = renderer.load_template(
    TEMPLATE_PATH + '/pkg_symbol_legend')
project_links_template = renderer.load_template(
    os.path.join(TEMPLATE_PATH, 'project_links'))
main_navigation_template = renderer.load_template(
    os.path.join(TEMPLATE_PATH, 'main_navigation'))
basic_page_template = renderer.load_template(
    os.path.join(TEMPLATE_PATH, 'basic_page'))

try:
    JOB_URL = os.environ['JOB_URL']
except KeyError:
    JOB_URL = ''
    JOB_NAME = ''
else:
    JOB_NAME = os.path.basename(JOB_URL[:-1])

def create_default_page_footer(date):
    return renderer.render(default_page_footer_template, {
            'date': date,
            'job_url': JOB_URL,
            'job_name': JOB_NAME,
            'jenkins_url': JENKINS_URL,
        })

url2html = re.compile(r'((mailto\:|((ht|f)tps?)\://|file\:///){1}\S+)')

# filter used on the index_FTBFS pages and for the reproducible.json
filtered_issues = (
    'ftbfs_in_jenkins_setup',
    'ftbfs_build_depends_not_available_on_amd64',
    'ftbfs_build-indep_not_build_on_some_archs'
)
filter_query = ''
for issue in filtered_issues:
    if filter_query == '':
        filter_query = "n.issues LIKE '%%" + issue + "%%'"
        filter_html = '<a href="' + REPRODUCIBLE_URL + ISSUES_URI + '/$suite/' + issue + '_issue.html">' + issue + '</a>'
    else:
        filter_query += " OR n.issues LIKE '%%" + issue + "%%'"
        filter_html += ' or <a href="' + REPRODUCIBLE_URL + ISSUES_URI + '/$suite/' + issue + '_issue.html">' + issue + '</a>'


@atexit.register
def print_time():
    log.info('Finished at %s, took: %s', datetime.now(),
             datetime.now()-started_at)


def print_critical_message(msg):
    print('\n\n\n')
    try:
        for line in msg.splitlines():
            log.critical(line)
    except AttributeError:
        log.critical(msg)
    print('\n\n\n')


def percent(part, whole):
    return round(100 * float(part)/float(whole), 1)


def create_temp_file(mode='w+b'):
    os.makedirs(TEMP_PATH, exist_ok=True)
    return NamedTemporaryFile(suffix=JOB_NAME, dir=TEMP_PATH, mode=mode)


class bcolors:
    BOLD = '\033[1m'
    UNDERLINE = '\033[4m'
    RED = '\033[91m'
    GOOD = '\033[92m'
    WARN = '\033[93m' + UNDERLINE
    FAIL = RED + BOLD + UNDERLINE
    ENDC = '\033[0m'


def convert_into_hms_string(duration):
    if not duration:
        duration = ''
    else:
        duration = int(duration)
        hours = int(duration/3600)
        minutes = int((duration-(hours*3600))/60)
        seconds = int(duration-(hours*3600)-(minutes*60))
        duration = ''
        if hours > 0:
            duration = str(hours)+'h ' + str(minutes)+'m ' + str(seconds) + 's'
        elif minutes > 0:
            duration = str(minutes)+'m ' + str(seconds) + 's'
        else:
            duration = str(seconds)+'s'
    return duration


def gen_suite_arch_nav_context(suite, arch, suite_arch_nav_template=None,
                               ignore_experimental=False, no_suite=None,
                               no_arch=None):
    # if a template is not passed in to navigate between suite and archs the
    # current page, we use the "default" suite/arch summary view.
    default_nav_template = '/debian/{{suite}}/index_suite_{{arch}}_stats.html'
    if not suite_arch_nav_template:
        suite_arch_nav_template = default_nav_template

    suite_list = []
    if not no_suite:
        for s in SUITES:
            include_suite = True
            if s == 'experimental' and ignore_experimental:
                include_suite = False
            suite_list.append({
                's': s,
                'class': 'current' if s == suite else '',
                'uri': renderer.render(suite_arch_nav_template,
                                       {'suite': s, 'arch': arch})
                if include_suite else '',
            })

    arch_list = []
    if not no_arch:
        for a in ARCHS:
            arch_list.append({
                'a': a,
                'class': 'current' if a == arch else '',
                'uri': renderer.render(suite_arch_nav_template,
                                       {'suite': suite, 'arch': a}),
            })
    return (suite_list, arch_list)

# See bash equivelent: reproducible_common.sh's "write_page_header()"
def create_main_navigation(suite=defaultsuite, arch=defaultarch,
                           displayed_page=None, suite_arch_nav_template=None,
                           ignore_experimental=False, no_suite=None,
                           no_arch=None):
    suite_list, arch_list = gen_suite_arch_nav_context(suite, arch,
        suite_arch_nav_template, ignore_experimental, no_suite, no_arch)
    context = {
        'suite': suite,
        'arch': arch,
        'project_links_html': renderer.render(project_links_template),
        'suite_nav': {
            'suite_list': suite_list
        } if len(suite_list) else '',
        'arch_nav': {
            'arch_list': arch_list
        } if len(arch_list) else '',
        'debian_uri': DEBIAN_DASHBOARD_URI,
        'cross_suite_arch_nav': True if suite_arch_nav_template else False,
    }
    if suite != 'experimental':
        # there are not package sets in experimental
        context['include_pkgset_link'] = True
    # the "display_page" argument controls which of the main page navigation
    # items will be highlighted.
    if displayed_page:
       context[displayed_page] = True
    return renderer.render(main_navigation_template, context)


def write_html_page(title, body, destfile, no_header=False, style_note=False,
                    noendpage=False, refresh_every=None, displayed_page=None,
                    left_nav_html=None):
    meta_refresh_html = '<meta http-equiv="refresh" content="%d"></meta>' % \
        refresh_every if refresh_every is not None else ''
    if style_note:
        body += renderer.render(pkg_legend_template, {})
    if not noendpage:
        now = datetime.utcnow().strftime('%Y-%m-%d %H:%M UTC')
        body += create_default_page_footer(now)
    context = {
        'page_title': title,
        'meta_refresh_html': meta_refresh_html,
        'navigation_html': left_nav_html,
        'main_header': title if not no_header else "",
        'main_html': body,
        'style_dot_css_sha1sum': REPRODUCIBLE_STYLE_SHA1,
    }
    html = renderer.render(basic_page_template, context)

    try:
        os.makedirs(destfile.rsplit('/', 1)[0], exist_ok=True)
    except OSError as e:
        if e.errno != errno.EEXIST:  # that's 'File exists' error (errno 17)
            raise
    log.debug("Writing " + destfile)
    with open(destfile, 'w', encoding='UTF-8') as fd:
        fd.write(html)


def db_table(table_name):
    """Returns a SQLAlchemy Table objects to be used in queries
    using SQLAlchemy's Expressive Language.

    Arguments:
        table_name: a string corrosponding to an existing table name
    """
    try:
        return Table(table_name, DB_METADATA, autoload=True)
    except NoSuchTableError:
        log.error("Table %s does not exist or schema for %s could not be loaded",
                  table_name, PGDATABASE)
        raise


def query_db(query):
    """Excutes a raw SQL query. Return depends on query type.

    Returns:
        select:
            list of tuples
        update or delete:
            the number of rows affected
        insert:
            None
    """
    try:
        result = conn_db.execute(query)
    except OperationalError as ex:
        print_critical_message('Error executing this query:\n' + query)
        raise

    if result.returns_rows:
        return result.fetchall()
    elif result.supports_sane_rowcount() and result.rowcount > -1:
        return result.rowcount
    else:
        return None


def start_udd_connection():
    username = "public-udd-mirror"
    password = "public-udd-mirror"
    host = "public-udd-mirror.xvm.mit.edu"
    port = 5432
    db = "udd"
    try:
        try:
            log.debug("Starting connection to the UDD database")
            conn = psycopg2.connect(
                database=db,
                user=username,
                host=host,
                password=password,
                connect_timeout=5,
            )
        except psycopg2.OperationalError as err:
            if str(err) == 'timeout expired\n':
                log.error('Connection to the UDD database replice timed out. '
                          'Maybe the machine is offline or just unavailable.')
                log.error('Failing nicely anyway, all queries will return an '
                          'empty response.')
                return None
            else:
                raise
    except:
        log.error('Erorr connecting to the UDD database replica.' +
                  'The full error is:')
        exc_type, exc_value, exc_traceback = sys.exc_info()
        print_exception(exc_type, exc_value, exc_traceback)
        log.error('Failing nicely anyway, all queries will return an empty ' +
                  'response.')
        return None
    conn.set_client_encoding('utf8')
    return conn

def query_udd(query):
    if not conn_udd:
        log.error('There has been an error connecting to the UDD database. ' +
                  'Please look for a previous error for more information.')
        log.error('Failing nicely anyway, returning an empty response.')
        return []
    try:
        cursor = conn_udd.cursor()
        cursor.execute(query)
    except:
        log.error('The UDD server encountered a issue while executing the ' +
                  'query. The full error is:')
        exc_type, exc_value, exc_traceback = sys.exc_info()
        print_exception(exc_type, exc_value, exc_traceback)
        log.error('Failing nicely anyway, returning an empty response.')
        return []
    return cursor.fetchall()


def package_has_notes(package):
    # not a really serious check, it'd be better to check the yaml file
    path = NOTES_PATH + '/' + package + '_note.html'
    if os.access(path, os.R_OK):
        return True
    else:
        return False


def link_package(package, suite, arch, bugs={}, popcon=None, is_popular=None):
    url = RB_PKG_URI + '/' + suite + '/' + arch + '/' + package + '.html'
    query = """SELECT n.issues, n.bugs, n.comments
               FROM notes AS n JOIN sources AS s ON s.id=n.package_id
               WHERE s.name='{pkg}' AND s.suite='{suite}'
               AND s.architecture='{arch}'"""
    css_classes = []
    if is_popular:
        css_classes += ["package-popular"]
    title = ''
    if popcon is not None:
        title += 'popcon score: ' + str(popcon) + '\n'
    try:
        notes = query_db(query.format(pkg=package, suite=suite, arch=arch))[0]
    except IndexError:  # no notes for this package
        css_classes += ["package"]
    else:
        css_classes += ["noted"]
        for issue in json.loads(notes[0]):
            title += issue + '\n'
        for bug in json.loads(notes[1]):
            title += '#' + str(bug) + '\n'
        if notes[2]:
            title += notes[2]
    html = '<a href="' + url + '" class="' + ' '.join(css_classes) \
         + '" title="' + HTML.escape(title.strip()) + '">' + package + '</a>' \
         + get_trailing_icon(package, bugs) + '\n'
    return html


def link_packages(packages, suite, arch, bugs=None):
    if bugs is None:
        bugs = get_bugs()
    html = ''
    for pkg in packages:
        html += link_package(pkg, suite, arch, bugs)
    return html


def get_status_icon(status):
    table = {'reproducible' : 'weather-clear.png',
             'FTBFS': 'weather-storm.png',
             'FTBR' : 'weather-showers-scattered.png',
             '404': 'weather-severe-alert.png',
             'depwait': 'weather-snow.png',
             'not for us': 'weather-few-clouds-night.png',
             'not_for_us': 'weather-few-clouds-night.png',
             'untested': 'weather-clear-night.png',
             'blacklisted': 'error.png'}
    spokenstatus = status
    if status == 'unreproducible':
            status = 'FTBR'
    elif status == 'not for us':
            status = 'not_for_us'
    try:
        return (status, table[status], spokenstatus)
    except KeyError:
        log.error('Status ' + status + ' not recognized')
        return (status, '', spokenstatus)


def gen_status_link_icon(status, spokenstatus, icon, suite, arch):
    """
    Returns the html for "<icon> <spokenstatus>" with both icon and status
    linked to the appropriate index page for the status, arch and suite.

    If icon is set to None, the icon will be ommited.
    If spokenstatus is set to None, the spokenstatus link be ommited.
    """
    context = {
        'status': status,
        'spokenstatus': spokenstatus,
        'icon': icon,
        'suite': suite,
        'arch': arch,
        'untested': True if status == 'untested' else False,
    }
    return renderer.render(status_icon_link_template, context)


def strip_epoch(version):
    """
    Stip the epoch out of the version string. Some file (e.g. buildlogs, debs)
    do not have epoch in their filenames.
    """
    try:
        return version.split(':', 1)[1]
    except IndexError:
        return version

def pkg_has_buildinfo(package, version=False, suite=defaultsuite, arch=defaultarch):
    """
    if there is no version specified it will use the version listed in
    reproducible db
    """
    if not version:
        query = """SELECT r.version
                   FROM results AS r JOIN sources AS s ON r.package_id=s.id
                   WHERE s.name='{}' AND s.suite='{}' AND s.architecture='{}'"""
        query = query.format(package, suite, arch)
        version = str(query_db(query)[0][0])
    buildinfo = BUILDINFO_PATH + '/' + suite + '/' + arch + '/' + package + \
                '_' + strip_epoch(version) + '_' + arch + '.buildinfo'
    if os.access(buildinfo, os.R_OK):
        return True
    else:
        return False


def pkg_has_rbuild(package, version=False, suite=defaultsuite, arch=defaultarch):
    if not version:
        query = """SELECT r.version
                   FROM results AS r JOIN sources AS s ON r.package_id=s.id
                   WHERE s.name='{}' AND s.suite='{}' AND s.architecture='{}'"""
        query = query.format(package, suite, arch)
        version = str(query_db(query)[0][0])
    rbuild = RBUILD_PATH + '/' + suite + '/' + arch + '/' + package + '_' + \
             strip_epoch(version) + '.rbuild.log'
    if os.access(rbuild, os.R_OK):
        return (rbuild, os.stat(rbuild).st_size)
    elif os.access(rbuild+'.gz', os.R_OK):
        return (rbuild+'.gz', os.stat(rbuild+'.gz').st_size)
    else:
        return ()


def get_bugs():
    """
    This function returns a dict:
    { "package_name": {
        bug1: {patch: True, done: False, title: "string"},
        bug2: {patch: False, done: False, title: "string"},
       }
    }
    """
    query = """
        SELECT bugs.id, bugs.source, bugs.done, ARRAY_AGG(tags.tag), bugs.title
        FROM bugs JOIN bugs_usertags ON bugs.id = bugs_usertags.id
                  LEFT JOIN (
                    SELECT id, tag FROM bugs_tags
                    WHERE tag='patch' OR tag='pending'
                  ) AS tags ON bugs.id = tags.id
        WHERE bugs_usertags.email = 'reproducible-builds@lists.alioth.debian.org'
        AND bugs.id NOT IN (
            SELECT id
            FROM bugs_usertags
            WHERE email = 'reproducible-builds@lists.alioth.debian.org'
            AND (
                bugs_usertags.tag = 'toolchain'
                OR bugs_usertags.tag = 'infrastructure')
            )
        GROUP BY bugs.id, bugs.source, bugs.done
    """
    # returns a list of tuples [(id, source, done)]
    global conn_udd
    if not conn_udd:
        conn_udd = start_udd_connection()
    global bugs
    if bugs:
        return bugs
    rows = query_udd(query)
    log.info("finding out which usertagged bugs have been closed or at least have patches")
    packages = {}

    for bug in rows:
        if bug[1] not in packages:
            packages[bug[1]] = {}
        # bug[0] = bug_id, bug[1] = source_name, bug[2] = who_when_done,
        # bug[3] = tag (patch or pending), bug[4] = title
        packages[bug[1]][bug[0]] = {
            'done': False, 'patch': False, 'pending': False, 'title': bug[4]
        }
        if bug[2]:  # if the bug is done
            packages[bug[1]][bug[0]]['done'] = True
        if 'patch' in bug[3]:  # the bug is patched
            packages[bug[1]][bug[0]]['patch'] = True
        if 'pending' in bug[3]:  # the bug is pending
            packages[bug[1]][bug[0]]['pending'] = True
    return packages


def get_trailing_icon(package, bugs):
    html = ''
    if package in bugs:
        for bug in bugs[package]:
            html += '<a href="https://bugs.debian.org/{bug}">'.format(bug=bug)
            html += '<span class="'
            if bugs[package][bug]['done']:
                html += 'bug-done" title="#' + str(bug) + ', done">#</span>'
            elif bugs[package][bug]['pending']:
                html += 'bug-pending" title="#' + str(bug) + ', pending">P</span>'
            elif bugs[package][bug]['patch']:
                html += 'bug-patch" title="#' + str(bug) + ', with patch">+</span>'
            else:
                html += 'bug" title="#' + str(bug) + '">#</span>'
            html += '</a>'
    return html


def get_trailing_bug_icon(bug, bugs, package=None):
    html = ''
    if not package:
        for pkg in bugs.keys():
            if get_trailing_bug_icon(bug, bugs, pkg):
                return get_trailing_bug_icon(bug, bugs, pkg)
    else:
        try:
            if bug in bugs[package].keys():
                html += '<span class="'
                if bugs[package][bug]['done']:
                    html += 'bug-done" title="#' + str(bug) + ', done">#'
                elif bugs[package][bug]['pending']:
                    html += 'bug-pending" title="#' + str(bug) + ', pending">P'
                elif bugs[package][bug]['patch']:
                    html += 'bug-patch" title="#' + str(bug) + ', with patch">+'
                else:
                    html += 'bug">'
                html += '</span>'
        except KeyError:
            pass
    return html


def irc_msg(msg, channel='debian-reproducible'):
    kgb = ['kgb-client', '--conf', '/srv/jenkins/kgb/%s.conf' % channel,
           '--relay-msg']
    kgb.extend(str(msg).strip().split())
    call(kgb)


class Bug:
    def __init__(self, bug):
        self.bug = bug

    def __str__(self):
        return str(self.bug)


class Issue:
    def __init__(self, name):
        self.name = name
        query = "SELECT url, description  FROM issues WHERE name='{}'"
        result = query_db(query.format(self.name))
        try:
            self.url = result[0][0]
        except IndexError:
            self.url = ''
        try:
            self.desc = result[0][0]
        except IndexError:
            self.desc = ''


class Note:
    def __init__(self, pkg, results):
        log.debug(str(results))
        self.issues = [Issue(x) for x in json.loads(results[0])]
        self.bugs = [Bug(x) for x in json.loads(results[1])]
        self.comment = results[2]


class NotedPkg:
    def __init__(self, package, suite, arch):
        self.package = package
        self.suite = suite
        self.arch = arch
        query = """SELECT n.issues, n.bugs, n.comments
                   FROM sources AS s JOIN notes AS n ON s.id=n.package_id
                   WHERE s.name='{}' AND s.suite='{}' AND s.architecture='{}'"""
        result = query_db(query.format(self.package, self.suite, self.arch))
        try:
            result = result[0]
        except IndexError:
            self.note = None
        else:
            self.note = Note(self, result)

class Build:
    def __init__(self, package, suite, arch):
        self.package = package
        self.suite = suite
        self.arch = arch
        self.status = False
        self.version = False
        self.build_date = False
        self._get_package_status()

    def _get_package_status(self):
        try:
            query = """SELECT r.status, r.version, r.build_date
                       FROM results AS r JOIN sources AS s
                       ON r.package_id=s.id WHERE s.name='{}'
                       AND s.architecture='{}' AND s.suite='{}'"""
            query = query.format(self.package, self.arch, self.suite)
            result = query_db(query)[0]
        except IndexError:  # not tested, look whether it actually exists
            query = """SELECT version FROM sources WHERE name='{}'
                       AND suite='{}' AND architecture='{}'"""
            query = query.format(self.package, self.suite, self.arch)
            try:
                result = query_db(query)[0][0]
                if result:
                    result = ('untested', str(result), False)
            except IndexError:  # there is no package with this name in this
                return          # suite/arch, or none at all
        self.status = str(result[0])
        self.version = str(result[1])
        if result[2]:
            self.build_date = str(result[2]) + ' UTC'


class Package:
    def __init__(self, name, no_notes=False):
        self.name = name
        self._status = {}
        for suite in SUITES:
            self._status[suite] = {}
            for arch in ARCHS:
                self._status[suite][arch] = Build(self.name, suite, arch)
                if not no_notes:
                    self.note = NotedPkg(self.name, suite, arch).note
                else:
                    self.note = False
        try:
            self.status = self._status[defaultsuite][defaultarch].status
        except KeyError:
            self.status = False
        query = "SELECT notify_maintainer FROM sources WHERE name='{}'"
        try:
            result = int(query_db(query.format(self.name))[0][0])
        except IndexError:
            result = 0
        self.notify_maint = '⚑' if result == 1 else ''
        self.history = []
        self._load_history()

    def _load_history(self):
        keys = ['build ID', 'version', 'suite', 'architecture', 'result',
            'build date', 'build duration', 'node1', 'node2', 'job',
            'schedule message']
        query = """
                SELECT id, version, suite, architecture, status, build_date,
                    build_duration, node1, node2, job, schedule_message
                FROM stats_build WHERE name='{}' ORDER BY build_date DESC
            """.format(self.name)
        results = query_db(query)
        for record in results:
            self.history.append(dict(zip(keys, record)))

    def get_status(self, suite, arch):
        """ This returns False if the package does not exists in this suite """
        try:
            return self._status[suite][arch].status
        except KeyError:
            return False

    def get_build_date(self, suite, arch):
        """ This returns False if the package does not exists in this suite """
        try:
            return self._status[suite][arch].build_date
        except KeyError:
            return False

    def get_tested_version(self, suite, arch):
        """ This returns False if the package does not exists in this suite """
        try:
            return self._status[suite][arch].version
        except KeyError:
            return False


# get_bugs() is the only user of this, let it initialize the connection itself,
# during it's first call to speed up things when unneeded
# also "share" the bugs, to avoid collecting them multiple times per run
conn_udd = None
bugs = None