More generic changes from 2to3

tools/docs/docload.py

@@ -8,7 +8,7 @@ import tarfile
 import re
 import tidy
 from optparse import OptionParser
-from ConfigParser import ConfigParser
+from configparser import ConfigParser
 
 import psycopg2
 

tools/ftp/spider_ftp.py

@@ -9,7 +9,7 @@
 import sys
 import os
 from datetime import datetime
-import cPickle as pickle
+import pickle as pickle
 import codecs
 import urllib2
 

tools/ftp/spider_yum.py

@@ -28,7 +28,7 @@ archs = ['x86_64', 'i386', 'i686', 'ppc64le']
 
 
 def generate_platform(dirname, familyprefix, ver, installer, systemd):
-    for f in platform_names.keys():
+    for f in list(platform_names.keys()):
         yield ('%s-%s' % (f, ver), {
             't': platform_names[f].format(ver),
             'p': os.path.join(dirname, '{0}-{1}'.format(familyprefix, ver)),
@@ -66,7 +66,7 @@ if __name__ == "__main__":
         reporpms[v] = {}
         vroot = os.path.join(args.yumroot, v)
         for dirpath, dirnames, filenames in os.walk(vroot):
-            rmatches = filter(None, (re_reporpm.match(f) for f in sorted(filenames, reverse=True)))
+            rmatches = [_f for _f in (re_reporpm.match(f) for f in sorted(filenames, reverse=True)) if _f]
 
             if rmatches:
                 familypath = os.path.join(*dirpath.split('/')[-2:])
@@ -76,7 +76,7 @@ if __name__ == "__main__":
                     shortdist, shortver, ver = r.groups(1)
 
                     found = False
-                    for p, pinfo in platforms.items():
+                    for p, pinfo in list(platforms.items()):
                         if pinfo['p'] == familypath and pinfo['f'] == shortdist:
                             if p not in reporpms[v]:
                                 reporpms[v][p] = {}
@@ -89,8 +89,8 @@ if __name__ == "__main__":
                         pass
 
     # Filter all platforms that are not used
-    platforms = {k: v for k, v in platforms.iteritems() if v['found']}
-    for k, v in platforms.iteritems():
+    platforms = {k: v for k, v in platforms.items() if v['found']}
+    for k, v in platforms.items():
         del v['found']
 
     j = json.dumps({'platforms': platforms, 'reporpms': reporpms})

tools/purgehook/purgehook.py

@@ -9,7 +9,7 @@
 import sys
 import os
 import hashlib
-from ConfigParser import ConfigParser
+from configparser import ConfigParser
 import psycopg2
 
 # Templates that we don't want to ban automatically

tools/search/crawler/lib/basecrawler.py

@@ -55,7 +55,7 @@ class BaseSiteCrawler(object):
         curs = self.dbconn.cursor()
         curs.execute("DELETE FROM webpages WHERE site=%(site)s AND NOT suburl=ANY(%(urls)s)", {
             'site': self.siteid,
-            'urls': self.pages_crawled.keys(),
+            'urls': list(self.pages_crawled.keys()),
         })
         if curs.rowcount:
             log("Deleted %s pages no longer accessible" % curs.rowcount)

tools/search/crawler/lib/genericsite.py

@@ -14,7 +14,7 @@ class GenericSiteCrawler(BaseSiteCrawler):
 
         # We need to seed the crawler with every URL we've already seen, since
         # we don't recrawl the contents if they haven't changed.
-        allpages = self.scantimes.keys()
+        allpages = list(self.scantimes.keys())
 
         # Figure out if there are any excludes to deal with (beyond the
         # robots.txt ones)

tools/search/crawler/lib/parsers.py

@@ -1,10 +1,10 @@
 import re
 import urllib
-from StringIO import StringIO
+from io import StringIO
 import dateutil.parser
 from datetime import timedelta
 
-from HTMLParser import HTMLParser
+from html.parser import HTMLParser
 
 from lib.log import log
 

tools/search/crawler/webcrawler.py

@@ -6,7 +6,7 @@ from lib.genericsite import GenericSiteCrawler
 from lib.sitemapsite import SitemapSiteCrawler
 from lib.threadwrapper import threadwrapper
 
-from ConfigParser import ConfigParser
+from configparser import ConfigParser
 import psycopg2
 import time