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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# This file is part of the LibreOffice project.
#
# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this
# file, You can obtain one at http://mozilla.org/MPL/2.0/.
#
# This digs through a pile of bugzilla's and populates the cwd with a big
# collection of bug-docs in per-filetype dirs with bug-ids as names with
# prefixes to indicate which bug-tracker, e.g.
#
# fdo-bugid-X.suffix
# rhbz-bugid-X.suffix
# moz-bugid-X.suffix
#
# where X is the n'th attachment of that type in the bug
#
# The results are stored in the current directory, categorized by the
# extension of the downloaded file. When a file already exists, it is assumed
# it is already downloaded by a previous run, and up-to-date.
from __future__ import print_function
import feedparser
import base64
import datetime
import glob
import re
import os, os.path
import stat
import sys
import threading
try:
import queue
except:
import Queue as queue
try:
from urllib.request import urlopen
except:
from urllib import urlopen
try:
import xmlrpc.client as xmlrpclib
except:
import xmlrpclib
from xml.dom import minidom
from xml.sax.saxutils import escape
def urlopen_retry(url):
maxretries = 3
for i in range(maxretries + 1):
try:
return urlopen(url)
except IOError as e:
print("caught IOError: " + str(e))
if maxretries == i:
raise
print("retrying...")
def get_from_bug_url_via_xml(url, mimetype, prefix, suffix):
id = url.rsplit('=', 2)[1]
print("id is " + prefix + id + " " + suffix)
print("parsing " + id)
sock = urlopen_retry(url+"&ctype=xml")
dom = minidom.parse(sock)
sock.close()
attachmentid=0
for attachment in dom.getElementsByTagName('attachment'):
attachmentid += 1
print(" mimetype is", end=' ')
for node in attachment.childNodes:
if node.nodeName == 'type':
print(node.firstChild.nodeValue, end=' ')
if node.firstChild.nodeValue.lower() != mimetype.lower():
print('skipping')
break
elif node.nodeName == 'data':
# check if attachment is deleted (i.e. https://bugs.kde.org/show_bug.cgi?id=53343&ctype=xml)
if not node.firstChild:
print('deleted attachment, skipping')
continue
download = suffix + '/' +prefix + id + '-' + str(attachmentid) + '.' + suffix
if os.path.isfile(download):
print("assuming " + download + " is up to date")
continue
# prevent re-downloading FDO attachments from TDF
if prefix == "tdf" and int(id) < 88776:
fdodownload = download.replace("tdf", "fdo")
if os.path.isfile(fdodownload):
print("assuming FDO " + fdodownload + " is up to date")
continue
print('downloading as ' + download)
tmpfile = download + ".tmp"
f = open(tmpfile, 'wb')
f.write(base64.b64decode(node.firstChild.nodeValue))
f.close()
os.rename(tmpfile, download)
break
def get_novell_bug_via_xml(url, mimetype, prefix, suffix):
id = url.rsplit('=', 2)[1]
print("id is " + prefix + id + " " + suffix)
print("parsing " + id)
sock = urlopen_retry(url+"&ctype=xml")
dom = minidom.parse(sock)
sock.close()
attachmentid=0
for comment in dom.getElementsByTagName('thetext'):
commentText = comment.firstChild.nodeValue
match = re.search(r".*Created an attachment \(id=([0-9]+)\)", commentText)
if not match:
continue
attachmentid += 1
download = suffix + '/' + prefix + id + '-' + str(attachmentid) + '.' + suffix
if os.path.isfile(download):
print("assuming " + download + " is up to date")
continue
realAttachmentId = match.group(1)
handle = urlopen_retry(novellattach + realAttachmentId)
if not handle:
print("attachment %s is not accessible" % realAttachmentId)
continue
print(" mimetype is", end=' ')
info = handle.info()
if info.get_content_type:
remoteMime = info.get_content_type()
else:
remoteMime = info.gettype()
print(remoteMime, end=' ')
if remoteMime != mimetype:
print("skipping")
continue
print('downloading as ' + download)
tmpfile = download + ".tmp"
f = open(tmpfile, 'wb')
f.write(handle.read())
f.close()
os.rename(tmpfile, download)
def create_query(mimetype):
query = dict()
query['query_format']='advanced'
query['field0-0-0']='attachments.mimetype'
query['type0-0-0']='equals'
query['value0-0-0']=mimetype
return query
def get_downloaded_files(prefix, suffix):
return glob.glob(os.path.join(suffix, '%s*.%s' % (prefix, suffix)))
def get_file_bz_ids(files, prefix):
return set([os.path.basename(f).split('-')[0].replace(prefix, '', 1) for f in files])
def get_changed_date(files):
newest = max([os.stat(f)[stat.ST_MTIME] for f in files])
# Subtract a day to avoid timezone differences. The worst thing that
# can happen is that we are going to process more bugs than necessary.
return datetime.date.fromtimestamp(newest - 24 * 60 * 60)
def get_through_rpc_query(rpcurl, showurl, mimetype, prefix, suffix):
try:
os.mkdir(suffix)
except:
pass
def process(query, full, have=[]):
try:
proxy = xmlrpclib.ServerProxy(rpcurl)
result = proxy.Bug.search(query)
bugs = result['bugs']
print(str(len(bugs)) + ' bugs to process')
if full:
available = set([str(bug['id']) for bug in bugs])
# we already have files from all available bugs
if available.difference(set(have)) == set():
print("assuming all downloaded files are up to date")
return
for bug in bugs:
url = showurl + str(bug['id'])
get_from_bug_url_via_xml(url, mimetype, prefix, suffix)
except xmlrpclib.Fault as err:
print("A fault occurred")
print("Fault code: %s" % err.faultCode)
print(err.faultString)
query = create_query(mimetype)
query['column_list']='bug_id'
files = get_downloaded_files(prefix, suffix)
if files != []:
print('looking for updated bugs having %s attachment(s)' % mimetype)
query_changed = query.copy()
query_changed['field0-1-0'] = 'days_elapsed'
query_changed['type0-1-0'] = 'lessthaneq'
query_changed['value0-1-0'] = str((datetime.date.today() - get_changed_date(files)).days)
process(query_changed, False)
print('looking for all bugs having %s attachment(s)' % mimetype)
process(query, True, get_file_bz_ids(files, prefix))
def get_through_rss_query(queryurl, mimetype, prefix, suffix):
try:
os.mkdir(suffix)
except:
pass
#Getting detailed bug information and downloading an attachment body is not possible without logging in to Novell bugzilla
#get_novell_bug_via_xml function is a workaround for that situation
get_bug_function = get_novell_bug_via_xml if prefix == "novell" else get_from_bug_url_via_xml
def process(query, full, have=[]):
url = queryurl + '?' + '&'.join(['='.join(kv) for kv in query.items()])
print('url is ' + url)
d = feedparser.parse(url)
print(str(len(d['entries'])) + ' bugs to process')
entries = []
for entry in d['entries']:
bugid = entry['id'].split('=')[-1]
entries.append(entry)
if full:
available = set([str(entry['id'].split('=')[-1]) for entry in entries])
# we already have files from all available bugs
if available.difference(set(have)) == set():
print("assuming all downloaded files are up to date")
return
for entry in entries:
try:
get_bug_function(entry['id'], mimetype, prefix, suffix)
except KeyboardInterrupt:
raise # Ctrl+C should work
except:
print(entry['id'] + " failed: " + str(sys.exc_info()[0]))
pass
query = create_query(escape(mimetype.replace("+","%2B")))
query['ctype'] = 'rss'
files = get_downloaded_files(prefix, suffix)
if files != []:
print('looking for updated bugs having %s attachment(s)' % mimetype)
query_changed = query.copy()
query_changed['field0-1-0'] = 'changed'
query_changed['type0-1-0'] = 'changedbefore'
query_changed['value0-1-0'] = get_changed_date(files).isoformat()
process(query_changed, False)
print('looking for all bugs having %s attachment(s)' % mimetype)
process(query, True, get_file_bz_ids(files, prefix))
#since searching bugs having attachments with specific mimetypes is not available in launchpad API
#we're iterating over all bugs of the most interesting source packages
launchpad_pkgs = (
"abiword",
"calibre",
"calligra",
"gnumeric",
"inkscape",
"koffice",
"libabw",
"libcdr",
"libe-book",
"libetonyek",
"libfreehand",
"libmspub",
"libmwaw",
"liborcus",
"libpagemaker",
"libreoffice",
"libvisio",
"libwpd",
"libwpg",
"libwps",
"openoffice.org",
"python-uniconvertor",
"scribus",
"sk1",
"unoconv",
)
def get_launchpad_bugs(prefix):
#launchpadlib python module is required to download launchpad attachments
from launchpadlib.launchpad import Launchpad
launchpad = Launchpad.login_anonymously("attachmentdownload", "production")
ubuntu = launchpad.distributions["ubuntu"]
for pkg in launchpad_pkgs:
srcpkg = ubuntu.getSourcePackage(name=pkg)
pkgbugs = srcpkg.searchTasks(status=["New", "Fix Committed", "Invalid", "Won't Fix", "Confirmed", "Triaged", "In Progress", "Incomplete", "Incomplete (with response)", "Incomplete (without response)", "Fix Released", "Opinion", "Expired"])
for bugtask in pkgbugs:
bug = bugtask.bug
id = str(bug.id)
print("parsing " + id + " status: " + bugtask.status + " title: " + bug.title[:50])
attachmentid = 0
for attachment in bug.attachments:
attachmentid += 1
handle = attachment.data.open()
if not handle.content_type in mimetypes:
#print "skipping"
continue
suffix = mimetypes[handle.content_type]
if not os.path.isdir(suffix):
try:
os.mkdir(suffix)
except:
pass
download = suffix + '/' + prefix + id + '-' + str(attachmentid) + '.' + suffix
if os.path.isfile(download):
print("assuming " + id + " is up to date")
break
print('mimetype is ' + handle.content_type + ' downloading as ' + download)
tmpfile = download + ".tmp"
f = open(tmpfile, "wb")
f.write(handle.read())
f.close()
os.rename(tmpfile, download)
rss_bugzillas = (
( 'abi', 'http://bugzilla.abisource.com/buglist.cgi' ), #added for abiword
( 'fdo', 'http://bugs.freedesktop.org/buglist.cgi' ),
( 'gentoo', 'http://bugs.gentoo.org/buglist.cgi' ),
( 'gnome', 'http://bugzilla.gnome.org/buglist.cgi' ), # added for gnumeric
( 'kde', 'http://bugs.kde.org/buglist.cgi' ), # added for koffice/calligra
( 'mandriva', 'https://qa.mandriva.com/buglist.cgi' ),
( 'moz', 'https://bugzilla.mozilla.org/buglist.cgi' ),
# It seems something has changed and it is no longer possible to
# download any files from there.
# NOTE: I am leaving it in the list, commented out, just so someone
# does not add it back immediately .-)
# 'novell': 'https://bugzilla.novell.com/buglist.cgi',
( 'ooo', 'https://bz.apache.org/ooo/buglist.cgi' ),
( 'tdf', 'http://bugs.documentfoundation.org/buglist.cgi' ),
)
redhatrpc = 'https://bugzilla.redhat.com/xmlrpc.cgi'
redhatbug = 'https://bugzilla.redhat.com/show_bug.cgi?id='
#Novell Bugzilla requires users to log in, in order to get details of the bugs such as attachment bodies etc.
#As a dirty workaround, we parse comments containing "Created an attachment (id=xxxxxx)" and download attachments manually
#python-bugzilla claims that it supports Novell bugzilla login but it's not working right now and novell bugzilla login
#system is a nightmare
novellattach = 'https://bugzilla.novell.com/attachment.cgi?id='
mimetypes = {
# ODF
'application/vnd.oasis.opendocument.base': 'odb',
'application/vnd.oasis.opendocument.database': 'odb',
'application/vnd.oasis.opendocument.chart': 'odc',
'application/vnd.oasis.opendocument.chart-template': 'otc',
'application/vnd.oasis.opendocument.formula': 'odf',
'application/vnd.oasis.opendocument.formula-template': 'otf',
'application/vnd.oasis.opendocument.graphics': 'odg',
'application/vnd.oasis.opendocument.graphics-template': 'otg',
'application/vnd.oasis.opendocument.graphics-flat-xml': 'fodg',
'application/vnd.oasis.opendocument.presentation': 'odp',
'application/vnd.oasis.opendocument.presentation-template': 'otp',
'application/vnd.oasis.opendocument.presentation-flat-xml': 'fodp',
'application/vnd.oasis.opendocument.spreadsheet': 'ods',
'application/vnd.oasis.opendocument.spreadsheet-template': 'ots',
'application/vnd.oasis.opendocument.spreadsheet-flat-xml': 'fods',
'application/vnd.oasis.opendocument.text': 'odt',
'application/vnd.oasis.opendocument.text-flat-xml': 'fodt',
'application/vnd.oasis.opendocument.text-master': 'odm',
'application/vnd.oasis.opendocument.text-template': 'ott',
'application/vnd.oasis.opendocument.text-master-template': 'otm',
'application/vnd.oasis.opendocument.text-web': 'oth',
# OOo XML
'application/vnd.sun.xml.base': 'odb',
'application/vnd.sun.xml.calc': 'sxc',
'application/vnd.sun.xml.calc.template': 'stc',
'application/vnd.sun.xml.chart': 'sxs',
'application/vnd.sun.xml.draw': 'sxd',
'application/vnd.sun.xml.draw.template': 'std',
'application/vnd.sun.xml.impress': 'sxi',
'application/vnd.sun.xml.impress.template': 'sti',
'application/vnd.sun.xml.math': 'sxm',
'application/vnd.sun.xml.writer': 'sxw',
'application/vnd.sun.xml.writer.global': 'sxg',
'application/vnd.sun.xml.writer.template': 'stw',
'application/vnd.sun.xml.writer.web': 'stw',
# MSO
'application/rtf': 'rtf',
'text/rtf': 'rtf',
'application/msword': 'doc',
'application/vnd.ms-powerpoint': 'ppt',
'application/vnd.ms-excel': 'xls',
'application/vnd.ms-excel.sheet.binary.macroEnabled.12': 'xlsb',
'application/vnd.ms-excel.sheet.macroEnabled.12': 'xlsm',
'application/vnd.ms-excel.template.macroEnabled.12': 'xltm',
'application/vnd.ms-powerpoint.presentation.macroEnabled.12': 'pptm',
'application/vnd.ms-powerpoint.slide.macroEnabled.12': 'sldm',
'application/vnd.ms-powerpoint.slideshow.macroEnabled.12': 'ppsm',
'application/vnd.ms-powerpoint.template.macroEnabled.12': 'potm',
'application/vnd.ms-word.document.macroEnabled.12': 'docm',
'application/vnd.ms-word.template.macroEnabled.12': 'dotm',
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': 'xlsx',
'application/vnd.openxmlformats-officedocument.spreadsheetml.template': 'xltx',
'application/vnd.openxmlformats-officedocument.presentationml.presentation': 'pptx',
'application/vnd.openxmlformats-officedocument.presentationml.template': 'ppotx',
'application/vnd.openxmlformats-officedocument.presentationml.slideshow': 'ppsx',
'application/vnd.openxmlformats-officedocument.presentationml.slide': 'sldx',
'application/vnd.openxmlformats-officedocument.wordprocessingml.document': 'docx',
'application/vnd.openxmlformats-officedocument.wordprocessingml.template': 'dotx',
'application/vnd.visio': 'vsd',
'application/visio.drawing': 'vsd',
'application/vnd.visio.xml': 'vdx',
'application/x-mspublisher': 'pub',
# W3C
'application/xhtml+xml': 'xhtml',
'application/mathml+xml': 'mml',
'text/html': 'html',
'application/docbook+xml': 'docbook',
# misc
'text/csv': 'csv',
'text/spreadsheet': 'slk',
'application/x-qpro': 'qpro',
'application/x-dbase': 'dbf',
'application/vnd.corel-draw': 'cdr',
'application/vnd.lotus-wordpro': 'lwp',
'application/vnd.lotus-1-2-3': 'wks',
'application/vnd.wordperfect': 'wpd',
'application/wordperfect5.1': 'wpd',
'application/vnd.ms-works': 'wps',
'application/clarisworks' : 'cwk',
'application/macwriteii' : 'mw',
'application/vnd.apple.keynote': 'key',
'application/vnd.apple.numbers': 'numbers',
'application/vnd.apple.pages': 'pages',
'application/x-iwork-keynote-sffkey': 'key',
'application/x-iwork-numbers-sffnumbers': 'numbers',
'application/x-iwork-pages-sffpages': 'pages',
'application/x-hwp': 'hwp',
'application/x-aportisdoc': 'pdb',
'application/prs.plucker' : 'pdb_plucker',
'application/vnd.palm' : 'pdb_palm',
'application/x-sony-bbeb' : 'lrf',
'application/x-pocket-word': 'psw',
'application/x-t602': '602',
'application/x-fictionbook+xml': 'fb2',
'application/x-abiword': 'abw',
'application/x-pagemaker': 'pmd',
'application/x-gnumeric': 'gnumeric',
# relatively uncommon image mimetypes
'image/x-freehand': 'fh',
'image/cgm': 'cgm',
'image/tiff': 'tiff',
'image/vnd.dxf': 'dxf',
'image/x-emf': 'emf',
'image/x-targa': 'tga',
'image/x-sgf': 'sgf',
'image/x-svm': 'svm',
'image/x-wmf': 'wmf',
'image/x-pict': 'pict',
'image/x-cmx': 'cmx',
'image/svg+xml': 'svg',
'image/x-MS-bmp': 'bmp',
'image/x-wpg': 'wpg',
'image/x-eps': 'eps',
'image/x-met': 'met',
'image/x-portable-bitmap': 'pbm',
'image/x-photo-cd': 'pcd',
'image/x-pcx': 'pcx',
'image/x-portable-graymap': 'pgm',
'image/x-portable-pixmap': 'ppm',
'image/vnd.adobe.photoshop': 'psd',
'image/x-cmu-raster': 'ras',
'image/x-sun-raster': 'ras',
'image/x-xbitmap': 'xbm',
'image/x-xpixmap': 'xpm',
}
# disabled for now, this would download gigs of pngs/jpegs...
common_noncore_mimetypes = {
# graphics
'image/gif': 'gif',
'image/jpeg': 'jpeg',
'image/png': 'png',
# pdf, etc.
'application/pdf': 'pdf',
}
class manage_threads(threading.Thread):
def run(self):
#print(threading.current_thread().get_ident())
while 1:
# Try to receive a job from queue
try:
# Get job from queue
# Use job parameters to call our query
# Then let the queue know we are done with this job
(uri, mimetype, prefix, extension) = jobs.get(True,6)
try:
get_through_rss_query(uri, mimetype, prefix, extension)
finally:
jobs.task_done()
except KeyboardInterrupt:
raise # Ctrl+C should work
except queue.Empty:
break
def generate_multi_threading():
for (prefix, uri) in rss_bugzillas:
# Initialize threads
for i in range(max_threads):
manage_threads().start()
# Create a job for every mimetype for a bugzilla
for (mimetype,extension) in mimetypes.items():
# It seems that bugzilla has problems returing that many results
# (10000 results is probably a limit set somewhere) so we always
# end processing the complete list.
if mimetype == 'text/html' and prefix == 'moz':
continue
jobs.put([uri, mimetype, prefix, extension], block=True)
print("successfully placed a job in the queue searching for " + mimetype + " in bugtracker " + prefix)
# Continue when all mimetypes are done for a bugzilla
jobs.join()
print("DONE with bugtracker " + prefix)
max_threads = 20 # Number of threads to create, (1 = without multi-threading)
jobs = queue.Queue()
generate_multi_threading()
for (mimetype,extension) in mimetypes.items():
get_through_rpc_query(redhatrpc, redhatbug, mimetype, "rhbz", extension)
try:
get_launchpad_bugs("lp")
except ImportError:
print("launchpadlib unavailable, skipping Ubuntu tracker")
# vim:set shiftwidth=4 softtabstop=4 expandtab:
|