Issue 4767 - Improve error reporting in update_update_manifests

sitescripts/extensions/utils.py

 # This file is part of the Adblock Plus web scripts,
 # Copyright (C) 2006-2016 Eyeo GmbH
 #
 # Adblock Plus is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License version 3 as
 # published by the Free Software Foundation.
 #
 # Adblock Plus 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 Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
 
 import codecs
 import os
 import json
 import re
 import subprocess
 import traceback
 import time
 import urlparse
 import urllib
 import xml.dom.minidom as dom
 from ConfigParser import SafeConfigParser, NoOptionError
 from StringIO import StringIO
 from sitescripts.utils import get_config
+from xml.parsers.expat import ExpatError
 
 PACKAGE_SUFFIXES = {
     'gecko': '.xpi',
     'gecko-webext': '.xpi',
     'chrome': '.crx',
     'safari': '.safariextz',
     'ie': '.exe',
     'android': '.apk'
 }
 
@@ skipping 204 matching lines @@
 
 
 def _urlopen(url, attempts=3):
     """
     Tries to open a particular URL, retries on failure.
     """
     for i in range(attempts):
         try:
             return urllib.urlopen(url)
         except IOError as e:
             error = e

[Vasily Kuznetsov, 2017/01/13 18:12:11]

It would probably be good to improve the error reporting here as well. Otherwise
`urllib.urlopen` throws exceptions like this:

IOError: [Errno socket error] [Errno 8] nodename nor servname provided, or not
known

and that is also not superhelpful (e.g. it doesn't have the URL).

             time.sleep(5)
     raise error
 
 
+def _parseXMLDocument(url, attempts=2):
+    for i in range(attempts):
+        page = _urlopen(url)
+        content = page.read()
+        page.close()
+        try:
+            return dom.parseString(content)
+        except ExpatError as err:
+            exception = Exception('Error {0} while parsing xml:\n{1}\nfrom {2}'
+                                  .format(err, content, url))
+    raise exception
+
+
 def _getMozillaDownloadLink(galleryID):
     """
     gets download link for a Gecko add-on from the Mozilla Addons site
     """
     url = 'https://services.addons.mozilla.org/en-US/firefox/api/1/addon/%s' % _urlencode(galleryID)
-    document = dom.parse(_urlopen(url))
+    document = _parseXMLDocument(url)
     linkTags = document.getElementsByTagName('install')
     linkTag = linkTags[0] if len(linkTags) > 0 else None
     versionTags = document.getElementsByTagName('version')
     versionTag = versionTags[0] if len(versionTags) > 0 else None
     if linkTag and versionTag and linkTag.firstChild and versionTag.firstChild:
         return (linkTag.firstChild.data, versionTag.firstChild.data)
     else:
         return (None, None)
 
 
@@ skipping 105 matching lines @@
     if not extensions:
         return
 
     updates = {}
     for extension in extensions:
         updates[extension['basename']] = {
             'url': extension['updateURL'],
             'version': extension['version']
         }
     writeLibabpUpdateManifest(path, updates)